diff --git a/.github/.OwlBot.lock.yaml b/.github/.OwlBot.lock.yaml index d49860b32..a9fcd07cc 100644 --- a/.github/.OwlBot.lock.yaml +++ b/.github/.OwlBot.lock.yaml @@ -1,4 +1,3 @@ docker: - digest: sha256:457583330eec64daa02aeb7a72a04d33e7be2428f646671ce4045dcbc0191b1e - image: gcr.io/repo-automation-bots/owlbot-python:latest - + image: gcr.io/repo-automation-bots/owlbot-python:latest + digest: sha256:9743664022bd63a8084be67f144898314c7ca12f0a03e422ac17c733c129d803 diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index ae570eb01..6763f258c 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -8,4 +8,4 @@ * @googleapis/api-bigquery @googleapis/yoshi-python # The python-samples-reviewers team is the default owner for samples changes -/samples/ @googleapis/python-samples-owners +/samples/ @googleapis/api-bigquery @googleapis/python-samples-owners @googleapis/yoshi-python diff --git a/.github/sync-repo-settings.yaml b/.github/sync-repo-settings.yaml index b18fb9c29..8634a3043 100644 --- a/.github/sync-repo-settings.yaml +++ b/.github/sync-repo-settings.yaml @@ -4,6 +4,19 @@ branchProtectionRules: # Identifies the protection rule pattern. Name of the branch to be protected. # Defaults to `master` - pattern: master + requiresCodeOwnerReviews: true + requiresStrictStatusChecks: true + requiredStatusCheckContexts: + - 'Kokoro' + - 'Kokoro snippets-3.8' + - 'cla/google' + - 'Samples - Lint' + - 'Samples - Python 3.6' + - 'Samples - Python 3.7' + - 'Samples - Python 3.8' +- pattern: v3 + requiresCodeOwnerReviews: true + requiresStrictStatusChecks: true requiredStatusCheckContexts: - 'Kokoro' - 'Kokoro snippets-3.8' diff --git a/.kokoro/docker/docs/Dockerfile b/.kokoro/docker/docs/Dockerfile index 412b0b56a..4e1b1fb8b 100644 --- a/.kokoro/docker/docs/Dockerfile +++ b/.kokoro/docker/docs/Dockerfile @@ -40,6 +40,7 @@ RUN apt-get update \ libssl-dev \ libsqlite3-dev \ portaudio19-dev \ + python3-distutils \ redis-server \ software-properties-common \ ssh \ @@ -59,40 +60,8 @@ RUN apt-get update \ && rm -rf /var/lib/apt/lists/* \ && rm -f /var/cache/apt/archives/*.deb - -COPY fetch_gpg_keys.sh /tmp -# Install the desired versions of Python. -RUN set -ex \ - && export GNUPGHOME="$(mktemp -d)" \ - && echo "disable-ipv6" >> "${GNUPGHOME}/dirmngr.conf" \ - && /tmp/fetch_gpg_keys.sh \ - && for PYTHON_VERSION in 3.7.8 3.8.5; do \ - wget --no-check-certificate -O python-${PYTHON_VERSION}.tar.xz "https://www.python.org/ftp/python/${PYTHON_VERSION%%[a-z]*}/Python-$PYTHON_VERSION.tar.xz" \ - && wget --no-check-certificate -O python-${PYTHON_VERSION}.tar.xz.asc "https://www.python.org/ftp/python/${PYTHON_VERSION%%[a-z]*}/Python-$PYTHON_VERSION.tar.xz.asc" \ - && gpg --batch --verify python-${PYTHON_VERSION}.tar.xz.asc python-${PYTHON_VERSION}.tar.xz \ - && rm -r python-${PYTHON_VERSION}.tar.xz.asc \ - && mkdir -p /usr/src/python-${PYTHON_VERSION} \ - && tar -xJC /usr/src/python-${PYTHON_VERSION} --strip-components=1 -f python-${PYTHON_VERSION}.tar.xz \ - && rm python-${PYTHON_VERSION}.tar.xz \ - && cd /usr/src/python-${PYTHON_VERSION} \ - && ./configure \ - --enable-shared \ - # This works only on Python 2.7 and throws a warning on every other - # version, but seems otherwise harmless. - --enable-unicode=ucs4 \ - --with-system-ffi \ - --without-ensurepip \ - && make -j$(nproc) \ - && make install \ - && ldconfig \ - ; done \ - && rm -rf "${GNUPGHOME}" \ - && rm -rf /usr/src/python* \ - && rm -rf ~/.cache/ - RUN wget -O /tmp/get-pip.py 'https://bootstrap.pypa.io/get-pip.py' \ - && python3.7 /tmp/get-pip.py \ && python3.8 /tmp/get-pip.py \ && rm /tmp/get-pip.py -CMD ["python3.7"] +CMD ["python3.8"] diff --git a/.kokoro/samples/python3.6/periodic-head.cfg b/.kokoro/samples/python3.6/periodic-head.cfg index f9cfcd33e..5aa01bab5 100644 --- a/.kokoro/samples/python3.6/periodic-head.cfg +++ b/.kokoro/samples/python3.6/periodic-head.cfg @@ -7,5 +7,5 @@ env_vars: { env_vars: { key: "TRAMPOLINE_BUILD_FILE" - value: "github/python-pubsub/.kokoro/test-samples-against-head.sh" + value: "github/python-bigquery/.kokoro/test-samples-against-head.sh" } diff --git a/.kokoro/samples/python3.7/periodic-head.cfg b/.kokoro/samples/python3.7/periodic-head.cfg index f9cfcd33e..5aa01bab5 100644 --- a/.kokoro/samples/python3.7/periodic-head.cfg +++ b/.kokoro/samples/python3.7/periodic-head.cfg @@ -7,5 +7,5 @@ env_vars: { env_vars: { key: "TRAMPOLINE_BUILD_FILE" - value: "github/python-pubsub/.kokoro/test-samples-against-head.sh" + value: "github/python-bigquery/.kokoro/test-samples-against-head.sh" } diff --git a/.kokoro/samples/python3.8/periodic-head.cfg b/.kokoro/samples/python3.8/periodic-head.cfg index f9cfcd33e..5aa01bab5 100644 --- a/.kokoro/samples/python3.8/periodic-head.cfg +++ b/.kokoro/samples/python3.8/periodic-head.cfg @@ -7,5 +7,5 @@ env_vars: { env_vars: { key: "TRAMPOLINE_BUILD_FILE" - value: "github/python-pubsub/.kokoro/test-samples-against-head.sh" + value: "github/python-bigquery/.kokoro/test-samples-against-head.sh" } diff --git a/.kokoro/samples/python3.9/common.cfg b/.kokoro/samples/python3.9/common.cfg new file mode 100644 index 000000000..f179577a5 --- /dev/null +++ b/.kokoro/samples/python3.9/common.cfg @@ -0,0 +1,40 @@ +# Format: //devtools/kokoro/config/proto/build.proto + +# Build logs will be here +action { + define_artifacts { + regex: "**/*sponge_log.xml" + } +} + +# Specify which tests to run +env_vars: { + key: "RUN_TESTS_SESSION" + value: "py-3.9" +} + +# Declare build specific Cloud project. +env_vars: { + key: "BUILD_SPECIFIC_GCLOUD_PROJECT" + value: "python-docs-samples-tests-py39" +} + +env_vars: { + key: "TRAMPOLINE_BUILD_FILE" + value: "github/python-bigquery/.kokoro/test-samples.sh" +} + +# Configure the docker image for kokoro-trampoline. +env_vars: { + key: "TRAMPOLINE_IMAGE" + value: "gcr.io/cloud-devrel-kokoro-resources/python-samples-testing-docker" +} + +# Download secrets for samples +gfile_resources: "/bigstore/cloud-devrel-kokoro-resources/python-docs-samples" + +# Download trampoline resources. +gfile_resources: "/bigstore/cloud-devrel-kokoro-resources/trampoline" + +# Use the trampoline script to run in docker. +build_file: "python-bigquery/.kokoro/trampoline.sh" \ No newline at end of file diff --git a/.kokoro/samples/python3.9/continuous.cfg b/.kokoro/samples/python3.9/continuous.cfg new file mode 100644 index 000000000..a1c8d9759 --- /dev/null +++ b/.kokoro/samples/python3.9/continuous.cfg @@ -0,0 +1,6 @@ +# Format: //devtools/kokoro/config/proto/build.proto + +env_vars: { + key: "INSTALL_LIBRARY_FROM_SOURCE" + value: "True" +} \ No newline at end of file diff --git a/.kokoro/samples/python3.9/periodic-head.cfg b/.kokoro/samples/python3.9/periodic-head.cfg new file mode 100644 index 000000000..5aa01bab5 --- /dev/null +++ b/.kokoro/samples/python3.9/periodic-head.cfg @@ -0,0 +1,11 @@ +# Format: //devtools/kokoro/config/proto/build.proto + +env_vars: { + key: "INSTALL_LIBRARY_FROM_SOURCE" + value: "True" +} + +env_vars: { + key: "TRAMPOLINE_BUILD_FILE" + value: "github/python-bigquery/.kokoro/test-samples-against-head.sh" +} diff --git a/.kokoro/samples/python3.9/periodic.cfg b/.kokoro/samples/python3.9/periodic.cfg new file mode 100644 index 000000000..50fec9649 --- /dev/null +++ b/.kokoro/samples/python3.9/periodic.cfg @@ -0,0 +1,6 @@ +# Format: //devtools/kokoro/config/proto/build.proto + +env_vars: { + key: "INSTALL_LIBRARY_FROM_SOURCE" + value: "False" +} \ No newline at end of file diff --git a/.kokoro/samples/python3.9/presubmit.cfg b/.kokoro/samples/python3.9/presubmit.cfg new file mode 100644 index 000000000..a1c8d9759 --- /dev/null +++ b/.kokoro/samples/python3.9/presubmit.cfg @@ -0,0 +1,6 @@ +# Format: //devtools/kokoro/config/proto/build.proto + +env_vars: { + key: "INSTALL_LIBRARY_FROM_SOURCE" + value: "True" +} \ No newline at end of file diff --git a/.kokoro/test-samples-impl.sh b/.kokoro/test-samples-impl.sh index cf5de74c1..311a8d54b 100755 --- a/.kokoro/test-samples-impl.sh +++ b/.kokoro/test-samples-impl.sh @@ -20,9 +20,9 @@ set -eo pipefail # Enables `**` to include files nested inside sub-folders shopt -s globstar -# Exit early if samples directory doesn't exist -if [ ! -d "./samples" ]; then - echo "No tests run. `./samples` not found" +# Exit early if samples don't exist +if ! find samples -name 'requirements.txt' | grep -q .; then + echo "No tests run. './samples/**/requirements.txt' not found" exit 0 fi diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 1bbd78783..62eb5a77d 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -16,7 +16,7 @@ # See https://pre-commit.com/hooks.html for more hooks repos: - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v3.4.0 + rev: v4.0.1 hooks: - id: trailing-whitespace - id: end-of-file-fixer @@ -26,6 +26,6 @@ repos: hooks: - id: black - repo: https://gitlab.com/pycqa/flake8 - rev: 3.9.1 + rev: 3.9.2 hooks: - id: flake8 diff --git a/CHANGELOG.md b/CHANGELOG.md index ef184dffb..8a21df6fe 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,180 @@ [1]: https://pypi.org/project/google-cloud-bigquery/#history + +### [2.25.1](https://www.github.com/googleapis/python-bigquery/compare/v2.25.0...v2.25.1) (2021-08-25) + + +### Bug Fixes + +* populate default `timeout` and retry after client-side timeout ([#896](https://www.github.com/googleapis/python-bigquery/issues/896)) ([b508809](https://www.github.com/googleapis/python-bigquery/commit/b508809c0f887575274309a463e763c56ddd017d)) +* use REST API in cell magic when requested ([#892](https://www.github.com/googleapis/python-bigquery/issues/892)) ([1cb3e55](https://www.github.com/googleapis/python-bigquery/commit/1cb3e55253e824e3a1da5201f6ec09065fb6b627)) + +## [2.25.0](https://www.github.com/googleapis/python-bigquery/compare/v2.24.1...v2.25.0) (2021-08-24) + + +### Features + +* Support using GeoPandas for GEOGRAPHY columns ([#848](https://www.github.com/googleapis/python-bigquery/issues/848)) ([16f65e6](https://www.github.com/googleapis/python-bigquery/commit/16f65e6ae15979217ceea6c6d398c9057a363a13)) + +### [2.24.1](https://www.github.com/googleapis/python-bigquery/compare/v2.24.0...v2.24.1) (2021-08-13) + + +### Bug Fixes + +* remove pytz dependency and require pyarrow>=3.0.0 ([#875](https://www.github.com/googleapis/python-bigquery/issues/875)) ([2cb3563](https://www.github.com/googleapis/python-bigquery/commit/2cb3563ee863edef7eaf5d04d739bcfe7bc6438e)) + +## [2.24.0](https://www.github.com/googleapis/python-bigquery/compare/v2.23.3...v2.24.0) (2021-08-11) + + +### Features + +* add support for transaction statistics ([#849](https://www.github.com/googleapis/python-bigquery/issues/849)) ([7f7b1a8](https://www.github.com/googleapis/python-bigquery/commit/7f7b1a808d50558772a0deb534ca654da65d629e)) +* make the same `Table*` instances equal to each other ([#867](https://www.github.com/googleapis/python-bigquery/issues/867)) ([c1a3d44](https://www.github.com/googleapis/python-bigquery/commit/c1a3d4435739a21d25aa154145e36d3a7c42eeb6)) +* retry failed query jobs in `result()` ([#837](https://www.github.com/googleapis/python-bigquery/issues/837)) ([519d99c](https://www.github.com/googleapis/python-bigquery/commit/519d99c20e7d1101f76981f3de036fdf3c7a4ecc)) +* support `ScalarQueryParameterType` for `type_` argument in `ScalarQueryParameter` constructor ([#850](https://www.github.com/googleapis/python-bigquery/issues/850)) ([93d15e2](https://www.github.com/googleapis/python-bigquery/commit/93d15e2e5405c2cc6d158c4e5737361344193dbc)) + + +### Bug Fixes + +* make unicode characters working well in load_table_from_json ([#865](https://www.github.com/googleapis/python-bigquery/issues/865)) ([ad9c802](https://www.github.com/googleapis/python-bigquery/commit/ad9c8026f0e667f13dd754279f9dc40d06f4fa78)) + +### [2.23.3](https://www.github.com/googleapis/python-bigquery/compare/v2.23.2...v2.23.3) (2021-08-06) + + +### Bug Fixes + +* increase default retry deadline to 10 minutes ([#859](https://www.github.com/googleapis/python-bigquery/issues/859)) ([30770fd](https://www.github.com/googleapis/python-bigquery/commit/30770fd0575fbd5aaa70c14196a4cc54627aecd2)) + +### [2.23.2](https://www.github.com/googleapis/python-bigquery/compare/v2.23.1...v2.23.2) (2021-07-29) + + +### Dependencies + +* expand pyarrow pins to support 5.x releases ([#833](https://www.github.com/googleapis/python-bigquery/issues/833)) ([80e3a61](https://www.github.com/googleapis/python-bigquery/commit/80e3a61c60419fb19b70b664c6415cd01ba82f5b)) + +### [2.23.1](https://www.github.com/googleapis/python-bigquery/compare/v2.23.0...v2.23.1) (2021-07-28) + + +### Bug Fixes + +* `insert_rows()` accepts float column values as strings again ([#824](https://www.github.com/googleapis/python-bigquery/issues/824)) ([d9378af](https://www.github.com/googleapis/python-bigquery/commit/d9378af13add879118a1d004529b811f72c325d6)) + +## [2.23.0](https://www.github.com/googleapis/python-bigquery/compare/v2.22.1...v2.23.0) (2021-07-27) + + +### Features + +* Update proto definitions for bigquery/v2 to support new proto fields for BQML. ([#817](https://www.github.com/googleapis/python-bigquery/issues/817)) ([fe7a902](https://www.github.com/googleapis/python-bigquery/commit/fe7a902e8b3e723ace335c9b499aea6d180a025b)) + + +### Bug Fixes + +* no longer raise a warning in `to_dataframe` if `max_results` set ([#815](https://www.github.com/googleapis/python-bigquery/issues/815)) ([3c1be14](https://www.github.com/googleapis/python-bigquery/commit/3c1be149e76b1d1d8879fdcf0924ddb1c1839e94)) +* retry ChunkedEncodingError by default ([#802](https://www.github.com/googleapis/python-bigquery/issues/802)) ([419d36d](https://www.github.com/googleapis/python-bigquery/commit/419d36d6b1887041e5795dbc8fc808890e91ab11)) + + +### Documentation + +* correct docs for `LoadJobConfig.destination_table_description` ([#810](https://www.github.com/googleapis/python-bigquery/issues/810)) ([da87fd9](https://www.github.com/googleapis/python-bigquery/commit/da87fd921cc8067b187d7985c978aac8eb58d107)) + +### [2.22.1](https://www.github.com/googleapis/python-bigquery/compare/v2.22.0...v2.22.1) (2021-07-22) + + +### Bug Fixes + +* issue a warning if buggy pyarrow is detected ([#787](https://www.github.com/googleapis/python-bigquery/issues/787)) ([e403721](https://www.github.com/googleapis/python-bigquery/commit/e403721af1373eb1f1a1c7be5b2182e3819ed1f9)) +* use a larger chunk size when loading data ([#799](https://www.github.com/googleapis/python-bigquery/issues/799)) ([b804373](https://www.github.com/googleapis/python-bigquery/commit/b804373277c1c1baa3370ebfb4783503b7ff360f)) + + +### Documentation + +* add Samples section to CONTRIBUTING.rst ([#785](https://www.github.com/googleapis/python-bigquery/issues/785)) ([e587029](https://www.github.com/googleapis/python-bigquery/commit/e58702967d572e83b4c774278818302594a511b7)) +* add sample to delete job metadata ([#798](https://www.github.com/googleapis/python-bigquery/issues/798)) ([be9b242](https://www.github.com/googleapis/python-bigquery/commit/be9b242f2180f5b795dfb3a168a97af1682999fd)) + +## [2.22.0](https://www.github.com/googleapis/python-bigquery/compare/v2.21.0...v2.22.0) (2021-07-19) + + +### Features + +* add `LoadJobConfig.projection_fields` to select DATASTORE_BACKUP fields ([#736](https://www.github.com/googleapis/python-bigquery/issues/736)) ([c45a738](https://www.github.com/googleapis/python-bigquery/commit/c45a7380871af3dfbd3c45524cb606c60e1a01d1)) +* add standard sql table type, update scalar type enums ([#777](https://www.github.com/googleapis/python-bigquery/issues/777)) ([b8b5433](https://www.github.com/googleapis/python-bigquery/commit/b8b5433898ec881f8da1303614780a660d94733a)) +* add support for more detailed DML stats ([#758](https://www.github.com/googleapis/python-bigquery/issues/758)) ([36fe86f](https://www.github.com/googleapis/python-bigquery/commit/36fe86f41c1a8f46167284f752a6d6bbf886a04b)) +* add support for user defined Table View Functions ([#724](https://www.github.com/googleapis/python-bigquery/issues/724)) ([8c7b839](https://www.github.com/googleapis/python-bigquery/commit/8c7b839a6ac1491c1c3b6b0e8755f4b70ed72ee3)) + + +### Bug Fixes + +* avoid possible job already exists error ([#751](https://www.github.com/googleapis/python-bigquery/issues/751)) ([45b9308](https://www.github.com/googleapis/python-bigquery/commit/45b93089f5398740413104285cc8acfd5ebc9c08)) + + +### Dependencies + +* allow 2.x versions of `google-api-core`, `google-cloud-core`, `google-resumable-media` ([#770](https://www.github.com/googleapis/python-bigquery/issues/770)) ([87a09fa](https://www.github.com/googleapis/python-bigquery/commit/87a09fa3f2a9ab35728a1ac925f9d5f2e6616c65)) + + +### Documentation + +* add loading data from Firestore backup sample ([#737](https://www.github.com/googleapis/python-bigquery/issues/737)) ([22fd848](https://www.github.com/googleapis/python-bigquery/commit/22fd848cae4af1148040e1faa31dd15a4d674687)) + +## [2.21.0](https://www.github.com/googleapis/python-bigquery/compare/v2.20.0...v2.21.0) (2021-07-12) + + +### Features + +* Add max_results parameter to some of the `QueryJob` methods. ([#698](https://www.github.com/googleapis/python-bigquery/issues/698)) ([2a9618f](https://www.github.com/googleapis/python-bigquery/commit/2a9618f4daaa4a014161e1a2f7376844eec9e8da)) +* Add support for decimal target types. ([#735](https://www.github.com/googleapis/python-bigquery/issues/735)) ([7d2d3e9](https://www.github.com/googleapis/python-bigquery/commit/7d2d3e906a9eb161911a198fb925ad79de5df934)) +* Add support for table snapshots. ([#740](https://www.github.com/googleapis/python-bigquery/issues/740)) ([ba86b2a](https://www.github.com/googleapis/python-bigquery/commit/ba86b2a6300ae5a9f3c803beeb42bda4c522e34c)) +* Enable unsetting policy tags on schema fields. ([#703](https://www.github.com/googleapis/python-bigquery/issues/703)) ([18bb443](https://www.github.com/googleapis/python-bigquery/commit/18bb443c7acd0a75dcb57d9aebe38b2d734ff8c7)) +* Make it easier to disable best-effort deduplication with streaming inserts. ([#734](https://www.github.com/googleapis/python-bigquery/issues/734)) ([1246da8](https://www.github.com/googleapis/python-bigquery/commit/1246da86b78b03ca1aa2c45ec71649e294cfb2f1)) +* Support passing struct data to the DB API. ([#718](https://www.github.com/googleapis/python-bigquery/issues/718)) ([38b3ef9](https://www.github.com/googleapis/python-bigquery/commit/38b3ef96c3dedc139b84f0ff06885141ae7ce78c)) + + +### Bug Fixes + +* Inserting non-finite floats with `insert_rows()`. ([#728](https://www.github.com/googleapis/python-bigquery/issues/728)) ([d047419](https://www.github.com/googleapis/python-bigquery/commit/d047419879e807e123296da2eee89a5253050166)) +* Use `pandas` function to check for `NaN`. ([#750](https://www.github.com/googleapis/python-bigquery/issues/750)) ([67bc5fb](https://www.github.com/googleapis/python-bigquery/commit/67bc5fbd306be7cdffd216f3791d4024acfa95b3)) + + +### Documentation + +* Add docs for all enums in module. ([#745](https://www.github.com/googleapis/python-bigquery/issues/745)) ([145944f](https://www.github.com/googleapis/python-bigquery/commit/145944f24fedc4d739687399a8309f9d51d43dfd)) +* Omit mention of Python 2.7 in `CONTRIBUTING.rst`. ([#706](https://www.github.com/googleapis/python-bigquery/issues/706)) ([27d6839](https://www.github.com/googleapis/python-bigquery/commit/27d6839ee8a40909e4199cfa0da8b6b64705b2e9)) + +## [2.20.0](https://www.github.com/googleapis/python-bigquery/compare/v2.19.0...v2.20.0) (2021-06-07) + + +### Features + +* support script options in query job config ([#690](https://www.github.com/googleapis/python-bigquery/issues/690)) ([1259e16](https://www.github.com/googleapis/python-bigquery/commit/1259e16394784315368e8be959c1ac097782b62e)) + +## [2.19.0](https://www.github.com/googleapis/python-bigquery/compare/v2.18.0...v2.19.0) (2021-06-06) + + +### Features + +* list_tables, list_projects, list_datasets, list_models, list_routines, and list_jobs now accept a page_size parameter to control page size ([#686](https://www.github.com/googleapis/python-bigquery/issues/686)) ([1f1c4b7](https://www.github.com/googleapis/python-bigquery/commit/1f1c4b7ba4390fc4c5c8186bc22b83b45304ca06)) + +## [2.18.0](https://www.github.com/googleapis/python-bigquery/compare/v2.17.0...v2.18.0) (2021-06-02) + + +### Features + +* add support for Parquet options ([#679](https://www.github.com/googleapis/python-bigquery/issues/679)) ([d792ce0](https://www.github.com/googleapis/python-bigquery/commit/d792ce09388a6ee3706777915dd2818d4c854f79)) + +## [2.17.0](https://www.github.com/googleapis/python-bigquery/compare/v2.16.1...v2.17.0) (2021-05-21) + + +### Features + +* detect obsolete BQ Storage extra at runtime ([#666](https://www.github.com/googleapis/python-bigquery/issues/666)) ([bd7dbda](https://www.github.com/googleapis/python-bigquery/commit/bd7dbdae5c972b16bafc53c67911eeaa3255a880)) +* Support parameterized NUMERIC, BIGNUMERIC, STRING, and BYTES types ([#673](https://www.github.com/googleapis/python-bigquery/issues/673)) ([45421e7](https://www.github.com/googleapis/python-bigquery/commit/45421e73bfcddb244822e6a5cd43be6bd1ca2256)) + + +### Bug Fixes + +* **tests:** invalid path to strptime() ([#672](https://www.github.com/googleapis/python-bigquery/issues/672)) ([591cdd8](https://www.github.com/googleapis/python-bigquery/commit/591cdd851bb1321b048a05a378a0ef48d3ade462)) + ### [2.16.1](https://www.github.com/googleapis/python-bigquery/compare/v2.16.0...v2.16.1) (2021-05-12) diff --git a/CONTRIBUTING.rst b/CONTRIBUTING.rst index 20ba9e62e..2faf5aed3 100644 --- a/CONTRIBUTING.rst +++ b/CONTRIBUTING.rst @@ -68,15 +68,12 @@ Using ``nox`` We use `nox `__ to instrument our tests. - To test your changes, run unit tests with ``nox``:: + $ nox -s unit - $ nox -s unit-2.7 - $ nox -s unit-3.8 - $ ... +- To run a single unit test:: -- Args to pytest can be passed through the nox command separated by a `--`. For - example, to run a single test:: + $ nox -s unit-3.9 -- -k - $ nox -s unit-3.8 -- -k .. note:: @@ -143,8 +140,7 @@ Running System Tests - To run system tests, you can execute:: # Run all system tests - $ nox -s system-3.8 - $ nox -s system-2.7 + $ nox -s system # Run a single system test $ nox -s system-3.8 -- -k @@ -152,9 +148,8 @@ Running System Tests .. note:: - System tests are only configured to run under Python 2.7 and - Python 3.8. For expediency, we do not run them in older versions - of Python 3. + System tests are only configured to run under Python 3.8. + For expediency, we do not run them in older versions of Python 3. This alone will not run the tests. You'll need to change some local auth settings and change some configuration in your project to @@ -182,6 +177,30 @@ Build the docs via: $ nox -s docs +************************* +Samples and code snippets +************************* + +Code samples and snippets live in the `samples/` catalogue. Feel free to +provide more examples, but make sure to write tests for those examples. +Each folder containing example code requires its own `noxfile.py` script +which automates testing. If you decide to create a new folder, you can +base it on the `samples/snippets` folder (providing `noxfile.py` and +the requirements files). + +The tests will run against a real Google Cloud Project, so you should +configure them just like the System Tests. + +- To run sample tests, you can execute:: + + # Run all tests in a folder + $ cd samples/snippets + $ nox -s py-3.8 + + # Run a single sample test + $ cd samples/snippets + $ nox -s py-3.8 -- -k + ******************************************** Note About ``README`` as it pertains to PyPI ******************************************** @@ -218,8 +237,8 @@ Supported versions can be found in our ``noxfile.py`` `config`_. .. _config: https://github.com/googleapis/python-bigquery/blob/master/noxfile.py -We also explicitly decided to support Python 3 beginning with version -3.6. Reasons for this include: +We also explicitly decided to support Python 3 beginning with version 3.6. +Reasons for this include: - Encouraging use of newest versions of Python 3 - Taking the lead of `prominent`_ open-source `projects`_ diff --git a/docs/conf.py b/docs/conf.py index fdea01aad..59a2d8fb3 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -80,9 +80,9 @@ master_doc = "index" # General information about the project. -project = u"google-cloud-bigquery" -copyright = u"2019, Google" -author = u"Google APIs" +project = "google-cloud-bigquery" +copyright = "2019, Google" +author = "Google APIs" # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the @@ -110,6 +110,7 @@ # directories to ignore when looking for source files. exclude_patterns = [ "_build", + "**/.nox/**/*", "samples/AUTHORING_GUIDE.md", "samples/CONTRIBUTING.md", "samples/snippets/README.rst", @@ -282,7 +283,7 @@ ( master_doc, "google-cloud-bigquery.tex", - u"google-cloud-bigquery Documentation", + "google-cloud-bigquery Documentation", author, "manual", ) @@ -317,7 +318,7 @@ ( master_doc, "google-cloud-bigquery", - u"google-cloud-bigquery Documentation", + "google-cloud-bigquery Documentation", [author], 1, ) @@ -336,7 +337,7 @@ ( master_doc, "google-cloud-bigquery", - u"google-cloud-bigquery Documentation", + "google-cloud-bigquery Documentation", author, "google-cloud-bigquery", "google-cloud-bigquery Library", @@ -364,6 +365,9 @@ "google.api_core": ("https://googleapis.dev/python/google-api-core/latest/", None,), "grpc": ("https://grpc.github.io/grpc/python/", None), "proto-plus": ("https://proto-plus-python.readthedocs.io/en/latest/", None), + "protobuf": ("https://googleapis.dev/python/protobuf/latest/", None), + "pandas": ("http://pandas.pydata.org/pandas-docs/dev", None), + "geopandas": ("https://geopandas.org/", None), } diff --git a/docs/dbapi.rst b/docs/dbapi.rst index 41ec85833..81f000bc7 100644 --- a/docs/dbapi.rst +++ b/docs/dbapi.rst @@ -25,7 +25,7 @@ and using named parameters:: Providing explicit type information ----------------------------------- -BigQuery requires type information for parameters. The The BigQuery +BigQuery requires type information for parameters. The BigQuery DB-API can usually determine parameter types for parameters based on provided values. Sometimes, however, types can't be determined (for example when `None` is passed) or are determined incorrectly (for @@ -37,7 +37,14 @@ colon, as in:: insert into people (name, income) values (%(name:string)s, %(income:numeric)s) -For unnamed parameters, use the named syntax with a type, but now +For unnamed parameters, use the named syntax with a type, but no name, as in:: insert into people (name, income) values (%(:string)s, %(:numeric)s) + +Providing type information is the *only* way to pass `struct` data:: + + cursor.execute( + "insert into points (point) values (%(:struct)s)", + [{"x": 10, "y": 20}], + ) diff --git a/docs/enums.rst b/docs/enums.rst new file mode 100644 index 000000000..57608968a --- /dev/null +++ b/docs/enums.rst @@ -0,0 +1,6 @@ +BigQuery Enums +============== + +.. automodule:: google.cloud.bigquery.enums + :members: + :undoc-members: diff --git a/docs/reference.rst b/docs/reference.rst index 52d916f96..d8738e67b 100644 --- a/docs/reference.rst +++ b/docs/reference.rst @@ -58,7 +58,9 @@ Job-Related Types job.Compression job.CreateDisposition job.DestinationFormat + job.DmlStats job.Encoding + job.OperationType job.QueryPlanEntry job.QueryPlanEntryStep job.QueryPriority @@ -66,6 +68,7 @@ Job-Related Types job.SourceFormat job.WriteDisposition job.SchemaUpdateOption + job.TransactionInfo Dataset @@ -90,6 +93,7 @@ Table table.RangePartitioning table.Row table.RowIterator + table.SnapshotDefinition table.Table table.TableListItem table.TableReference @@ -115,6 +119,7 @@ Routine routine.Routine routine.RoutineArgument routine.RoutineReference + routine.RoutineType Schema ====== @@ -133,6 +138,7 @@ Query query.ArrayQueryParameter query.ScalarQueryParameter + query.ScalarQueryParameterType query.StructQueryParameter query.UDFResource @@ -173,10 +179,11 @@ Magics Enums ===== -.. autosummary:: - :toctree: generated +.. toctree:: + :maxdepth: 2 + + enums - enums.StandardSqlDataTypes Encryption Configuration ======================== diff --git a/docs/snippets.py b/docs/snippets.py index 3f9b9a88c..c62001fc0 100644 --- a/docs/snippets.py +++ b/docs/snippets.py @@ -363,7 +363,6 @@ def test_update_table_expiration(client, to_delete): # [START bigquery_update_table_expiration] import datetime - import pytz # from google.cloud import bigquery # client = bigquery.Client() @@ -375,7 +374,9 @@ def test_update_table_expiration(client, to_delete): assert table.expires is None # set table to expire 5 days from now - expiration = datetime.datetime.now(pytz.utc) + datetime.timedelta(days=5) + expiration = datetime.datetime.now(datetime.timezone.utc) + datetime.timedelta( + days=5 + ) table.expires = expiration table = client.update_table(table, ["expires"]) # API request diff --git a/docs/usage/pandas.rst b/docs/usage/pandas.rst index 9db98dfbb..92eee67cf 100644 --- a/docs/usage/pandas.rst +++ b/docs/usage/pandas.rst @@ -37,6 +37,21 @@ To retrieve table rows as a :class:`pandas.DataFrame`: :start-after: [START bigquery_list_rows_dataframe] :end-before: [END bigquery_list_rows_dataframe] + +Retrieve BigQuery GEOGRAPHY data as a GeoPandas GeoDataFrame +------------------------------------------------------------ + +`GeoPandas `_ adds geospatial analytics +capabilities to Pandas. To retrieve query results containing +GEOGRAPHY data as a :class:`geopandas.GeoDataFrame`: + +.. literalinclude:: ../samples/geography/to_geodataframe.py + :language: python + :dedent: 4 + :start-after: [START bigquery_query_results_geodataframe] + :end-before: [END bigquery_query_results_geodataframe] + + Load a Pandas DataFrame to a BigQuery Table ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/google/cloud/bigquery/__init__.py b/google/cloud/bigquery/__init__.py index f609468f5..a7a0da3dd 100644 --- a/google/cloud/bigquery/__init__.py +++ b/google/cloud/bigquery/__init__.py @@ -37,8 +37,12 @@ from google.cloud.bigquery.dataset import Dataset from google.cloud.bigquery.dataset import DatasetReference from google.cloud.bigquery import enums +from google.cloud.bigquery.enums import AutoRowIDs +from google.cloud.bigquery.enums import DecimalTargetType +from google.cloud.bigquery.enums import KeyResultStatementKind from google.cloud.bigquery.enums import SqlTypeNames from google.cloud.bigquery.enums import StandardSqlDataTypes +from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError from google.cloud.bigquery.external_config import ExternalConfig from google.cloud.bigquery.external_config import BigtableOptions from google.cloud.bigquery.external_config import BigtableColumnFamily @@ -46,22 +50,27 @@ from google.cloud.bigquery.external_config import CSVOptions from google.cloud.bigquery.external_config import GoogleSheetsOptions from google.cloud.bigquery.external_config import ExternalSourceFormat +from google.cloud.bigquery.format_options import ParquetOptions from google.cloud.bigquery.job import Compression from google.cloud.bigquery.job import CopyJob from google.cloud.bigquery.job import CopyJobConfig from google.cloud.bigquery.job import CreateDisposition from google.cloud.bigquery.job import DestinationFormat +from google.cloud.bigquery.job import DmlStats from google.cloud.bigquery.job import Encoding from google.cloud.bigquery.job import ExtractJob from google.cloud.bigquery.job import ExtractJobConfig from google.cloud.bigquery.job import LoadJob from google.cloud.bigquery.job import LoadJobConfig +from google.cloud.bigquery.job import OperationType from google.cloud.bigquery.job import QueryJob from google.cloud.bigquery.job import QueryJobConfig from google.cloud.bigquery.job import QueryPriority from google.cloud.bigquery.job import SchemaUpdateOption +from google.cloud.bigquery.job import ScriptOptions from google.cloud.bigquery.job import SourceFormat from google.cloud.bigquery.job import UnknownJob +from google.cloud.bigquery.job import TransactionInfo from google.cloud.bigquery.job import WriteDisposition from google.cloud.bigquery.model import Model from google.cloud.bigquery.model import ModelReference @@ -77,10 +86,12 @@ from google.cloud.bigquery.routine import Routine from google.cloud.bigquery.routine import RoutineArgument from google.cloud.bigquery.routine import RoutineReference +from google.cloud.bigquery.routine import RoutineType from google.cloud.bigquery.schema import SchemaField from google.cloud.bigquery.table import PartitionRange from google.cloud.bigquery.table import RangePartitioning from google.cloud.bigquery.table import Row +from google.cloud.bigquery.table import SnapshotDefinition from google.cloud.bigquery.table import Table from google.cloud.bigquery.table import TableReference from google.cloud.bigquery.table import TimePartitioningType @@ -109,6 +120,7 @@ "PartitionRange", "RangePartitioning", "Row", + "SnapshotDefinition", "TimePartitioning", "TimePartitioningType", # Jobs @@ -133,18 +145,27 @@ "BigtableOptions", "BigtableColumnFamily", "BigtableColumn", + "DmlStats", "CSVOptions", "GoogleSheetsOptions", + "ParquetOptions", + "ScriptOptions", + "TransactionInfo", "DEFAULT_RETRY", # Enum Constants "enums", + "AutoRowIDs", "Compression", "CreateDisposition", + "DecimalTargetType", "DestinationFormat", "DeterminismLevel", "ExternalSourceFormat", "Encoding", + "KeyResultStatementKind", + "OperationType", "QueryPriority", + "RoutineType", "SchemaUpdateOption", "SourceFormat", "SqlTypeNames", @@ -152,6 +173,8 @@ "WriteDisposition", # EncryptionConfiguration "EncryptionConfiguration", + # Custom exceptions + "LegacyBigQueryStorageError", ] diff --git a/google/cloud/bigquery/_helpers.py b/google/cloud/bigquery/_helpers.py index 4fe29291d..0a1f71444 100644 --- a/google/cloud/bigquery/_helpers.py +++ b/google/cloud/bigquery/_helpers.py @@ -17,7 +17,9 @@ import base64 import datetime import decimal +import math import re +from typing import Union from google.cloud._helpers import UTC from google.cloud._helpers import _date_from_iso8601_date @@ -25,6 +27,10 @@ from google.cloud._helpers import _RFC3339_MICROS from google.cloud._helpers import _RFC3339_NO_FRACTION from google.cloud._helpers import _to_bytes +import packaging.version + +from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + _RFC3339_MICROS_NO_ZULU = "%Y-%m-%dT%H:%M:%S.%f" _TIMEONLY_WO_MICROS = "%H:%M:%S" @@ -36,6 +42,66 @@ re.VERBOSE, ) +_MIN_BQ_STORAGE_VERSION = packaging.version.Version("2.0.0") +_BQ_STORAGE_OPTIONAL_READ_SESSION_VERSION = packaging.version.Version("2.6.0") + + +class BQStorageVersions: + """Version comparisons for google-cloud-bigqueyr-storage package.""" + + def __init__(self): + self._installed_version = None + + @property + def installed_version(self) -> packaging.version.Version: + """Return the parsed version of google-cloud-bigquery-storage.""" + if self._installed_version is None: + from google.cloud import bigquery_storage + + self._installed_version = packaging.version.parse( + # Use 0.0.0, since it is earlier than any released version. + # Legacy versions also have the same property, but + # creating a LegacyVersion has been deprecated. + # https://github.com/pypa/packaging/issues/321 + getattr(bigquery_storage, "__version__", "0.0.0") + ) + + return self._installed_version + + @property + def is_read_session_optional(self) -> bool: + """True if read_session is optional to rows(). + + See: https://github.com/googleapis/python-bigquery-storage/pull/228 + """ + return self.installed_version >= _BQ_STORAGE_OPTIONAL_READ_SESSION_VERSION + + def verify_version(self): + """Verify that a recent enough version of BigQuery Storage extra is + installed. + + The function assumes that google-cloud-bigquery-storage extra is + installed, and should thus be used in places where this assumption + holds. + + Because `pip` can install an outdated version of this extra despite the + constraints in `setup.py`, the calling code can use this helper to + verify the version compatibility at runtime. + + Raises: + LegacyBigQueryStorageError: + If the google-cloud-bigquery-storage package is outdated. + """ + if self.installed_version < _MIN_BQ_STORAGE_VERSION: + msg = ( + "Dependency google-cloud-bigquery-storage is outdated, please upgrade " + f"it to version >= 2.0.0 (version found: {self.installed_version})." + ) + raise LegacyBigQueryStorageError(msg) + + +BQ_STORAGE_VERSIONS = BQStorageVersions() + def _not_null(value, field): """Check whether 'value' should be coerced to 'field' type.""" @@ -273,9 +339,15 @@ def _int_to_json(value): return value -def _float_to_json(value): +def _float_to_json(value) -> Union[None, str, float]: """Coerce 'value' to an JSON-compatible representation.""" - return value if value is None else float(value) + if value is None: + return None + + if isinstance(value, str): + value = float(value) + + return str(value) if (math.isnan(value) or math.isinf(value)) else float(value) def _decimal_to_json(value): diff --git a/google/cloud/bigquery/_pandas_helpers.py b/google/cloud/bigquery/_pandas_helpers.py index e93a99eba..ab58b1729 100644 --- a/google/cloud/bigquery/_pandas_helpers.py +++ b/google/cloud/bigquery/_pandas_helpers.py @@ -20,12 +20,40 @@ import queue import warnings -from packaging import version - try: import pandas except ImportError: # pragma: NO COVER pandas = None +else: + import numpy + +try: + # _BaseGeometry is used to detect shapely objevys in `bq_to_arrow_array` + from shapely.geometry.base import BaseGeometry as _BaseGeometry +except ImportError: # pragma: NO COVER + # No shapely, use NoneType for _BaseGeometry as a placeholder. + _BaseGeometry = type(None) +else: + if pandas is not None: # pragma: NO COVER + + def _to_wkb(): + # Create a closure that: + # - Adds a not-null check. This allows the returned function to + # be used directly with apply, unlike `shapely.wkb.dumps`. + # - Avoid extra work done by `shapely.wkb.dumps` that we don't need. + # - Caches the WKBWriter (and write method lookup :) ) + # - Avoids adding WKBWriter, lgeos, and notnull to the module namespace. + from shapely.geos import WKBWriter, lgeos + + write = WKBWriter(lgeos).write + notnull = pandas.notnull + + def _to_wkb(v): + return write(v) if notnull(v) else v + + return _to_wkb + + _to_wkb = _to_wkb() try: import pyarrow @@ -41,6 +69,7 @@ # Having BQ Storage available implies that pyarrow >=1.0.0 is available, too. _ARROW_COMPRESSION_SUPPORT = True +from google.cloud.bigquery import _helpers from google.cloud.bigquery import schema @@ -70,6 +99,7 @@ "uint8": "INTEGER", "uint16": "INTEGER", "uint32": "INTEGER", + "geometry": "GEOGRAPHY", } @@ -92,6 +122,8 @@ def pyarrow_numeric(): def pyarrow_bignumeric(): + # 77th digit is partial. + # https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#decimal_types return pyarrow.decimal256(76, 38) @@ -107,6 +139,7 @@ def pyarrow_timestamp(): # This dictionary is duplicated in bigquery_storage/test/unite/test_reader.py # When modifying it be sure to update it there as well. BQ_TO_ARROW_SCALARS = { + "BIGNUMERIC": pyarrow_bignumeric, "BOOL": pyarrow.bool_, "BOOLEAN": pyarrow.bool_, "BYTES": pyarrow.binary, @@ -143,23 +176,15 @@ def pyarrow_timestamp(): pyarrow.date64().id: "DATETIME", # because millisecond resolution pyarrow.binary().id: "BYTES", pyarrow.string().id: "STRING", # also alias for pyarrow.utf8() - # The exact scale and precision don't matter, see below. - pyarrow.decimal128(38, scale=9).id: "NUMERIC", - } - - if version.parse(pyarrow.__version__) >= version.parse("3.0.0"): - BQ_TO_ARROW_SCALARS["BIGNUMERIC"] = pyarrow_bignumeric # The exact decimal's scale and precision are not important, as only # the type ID matters, and it's the same for all decimal256 instances. - ARROW_SCALAR_IDS_TO_BQ[pyarrow.decimal256(76, scale=38).id] = "BIGNUMERIC" - _BIGNUMERIC_SUPPORT = True - else: - _BIGNUMERIC_SUPPORT = False + pyarrow.decimal128(38, scale=9).id: "NUMERIC", + pyarrow.decimal256(76, scale=38).id: "BIGNUMERIC", + } else: # pragma: NO COVER BQ_TO_ARROW_SCALARS = {} # pragma: NO COVER ARROW_SCALAR_IDS_TO_BQ = {} # pragma: NO_COVER - _BIGNUMERIC_SUPPORT = False # pragma: NO COVER def bq_to_arrow_struct_data_type(field): @@ -199,14 +224,16 @@ def bq_to_arrow_data_type(field): return data_type_constructor() -def bq_to_arrow_field(bq_field): +def bq_to_arrow_field(bq_field, array_type=None): """Return the Arrow field, corresponding to a given BigQuery column. Returns: None: if the Arrow type cannot be determined. """ arrow_type = bq_to_arrow_data_type(bq_field) - if arrow_type: + if arrow_type is not None: + if array_type is not None: + arrow_type = array_type # For GEOGRAPHY, at least initially is_nullable = bq_field.mode.upper() == "NULLABLE" return pyarrow.field(bq_field.name, arrow_type, nullable=is_nullable) @@ -231,7 +258,24 @@ def bq_to_arrow_schema(bq_schema): def bq_to_arrow_array(series, bq_field): - arrow_type = bq_to_arrow_data_type(bq_field) + if bq_field.field_type.upper() == "GEOGRAPHY": + arrow_type = None + first = _first_valid(series) + if first is not None: + if series.dtype.name == "geometry" or isinstance(first, _BaseGeometry): + arrow_type = pyarrow.binary() + # Convert shapey geometry to WKB binary format: + series = series.apply(_to_wkb) + elif isinstance(first, bytes): + arrow_type = pyarrow.binary() + elif series.dtype.name == "geometry": + # We have a GeoSeries containing all nulls, convert it to a pandas series + series = pandas.Series(numpy.array(series)) + + if arrow_type is None: + arrow_type = bq_to_arrow_data_type(bq_field) + else: + arrow_type = bq_to_arrow_data_type(bq_field) field_type_upper = bq_field.field_type.upper() if bq_field.field_type else "" @@ -285,6 +329,12 @@ def list_columns_and_indexes(dataframe): return columns_and_indexes +def _first_valid(series): + first_valid_index = series.first_valid_index() + if first_valid_index is not None: + return series.at[first_valid_index] + + def dataframe_to_bq_schema(dataframe, bq_schema): """Convert a pandas DataFrame schema to a BigQuery schema. @@ -325,6 +375,13 @@ def dataframe_to_bq_schema(dataframe, bq_schema): # Otherwise, try to automatically determine the type based on the # pandas dtype. bq_type = _PANDAS_DTYPE_TO_BQ.get(dtype.name) + if bq_type is None: + sample_data = _first_valid(dataframe[column]) + if ( + isinstance(sample_data, _BaseGeometry) + and sample_data is not None # Paranoia + ): + bq_type = "GEOGRAPHY" bq_field = schema.SchemaField(column, bq_type) bq_schema_out.append(bq_field) @@ -456,11 +513,11 @@ def dataframe_to_arrow(dataframe, bq_schema): arrow_names = [] arrow_fields = [] for bq_field in bq_schema: - arrow_fields.append(bq_to_arrow_field(bq_field)) arrow_names.append(bq_field.name) arrow_arrays.append( bq_to_arrow_array(get_column_or_index(dataframe, bq_field.name), bq_field) ) + arrow_fields.append(bq_to_arrow_field(bq_field, arrow_arrays[-1].type)) if all((field is not None for field in arrow_fields)): return pyarrow.Table.from_arrays( @@ -590,7 +647,14 @@ def _bqstorage_page_to_dataframe(column_names, dtypes, page): def _download_table_bqstorage_stream( download_state, bqstorage_client, session, stream, worker_queue, page_to_item ): - rowstream = bqstorage_client.read_rows(stream.name).rows(session) + reader = bqstorage_client.read_rows(stream.name) + + # Avoid deprecation warnings for passing in unnecessary read session. + # https://github.com/googleapis/python-bigquery-storage/issues/229 + if _helpers.BQ_STORAGE_VERSIONS.is_read_session_optional: + rowstream = reader.rows() + else: + rowstream = reader.rows(session) for page in rowstream.pages: if download_state.done: @@ -780,7 +844,7 @@ def dataframe_to_json_generator(dataframe): output = {} for column, value in zip(dataframe.columns, row): # Omit NaN values. - if value != value: + if pandas.isna(value): continue output[column] = value yield output diff --git a/google/cloud/bigquery/_tqdm_helpers.py b/google/cloud/bigquery/_tqdm_helpers.py index 2fcf2a981..99e720e2b 100644 --- a/google/cloud/bigquery/_tqdm_helpers.py +++ b/google/cloud/bigquery/_tqdm_helpers.py @@ -16,6 +16,8 @@ import concurrent.futures import time +import typing +from typing import Optional import warnings try: @@ -23,6 +25,10 @@ except ImportError: # pragma: NO COVER tqdm = None +if typing.TYPE_CHECKING: # pragma: NO COVER + from google.cloud.bigquery import QueryJob + from google.cloud.bigquery.table import RowIterator + _NO_TQDM_ERROR = ( "A progress bar was requested, but there was an error loading the tqdm " "library. Please install tqdm to use the progress bar functionality." @@ -32,7 +38,7 @@ def get_progress_bar(progress_bar_type, description, total, unit): - """Construct a tqdm progress bar object, if tqdm is .""" + """Construct a tqdm progress bar object, if tqdm is installed.""" if tqdm is None: if progress_bar_type is not None: warnings.warn(_NO_TQDM_ERROR, UserWarning, stacklevel=3) @@ -53,16 +59,34 @@ def get_progress_bar(progress_bar_type, description, total, unit): return None -def wait_for_query(query_job, progress_bar_type=None): - """Return query result and display a progress bar while the query running, if tqdm is installed.""" +def wait_for_query( + query_job: "QueryJob", + progress_bar_type: Optional[str] = None, + max_results: Optional[int] = None, +) -> "RowIterator": + """Return query result and display a progress bar while the query running, if tqdm is installed. + + Args: + query_job: + The job representing the execution of the query on the server. + progress_bar_type: + The type of progress bar to use to show query progress. + max_results: + The maximum number of rows the row iterator should return. + + Returns: + A row iterator over the query results. + """ default_total = 1 current_stage = None start_time = time.time() + progress_bar = get_progress_bar( progress_bar_type, "Query is running", default_total, "query" ) if progress_bar is None: - return query_job.result() + return query_job.result(max_results=max_results) + i = 0 while True: if query_job.query_plan: @@ -75,7 +99,9 @@ def wait_for_query(query_job, progress_bar_type=None): ), ) try: - query_result = query_job.result(timeout=_PROGRESS_BAR_UPDATE_INTERVAL) + query_result = query_job.result( + timeout=_PROGRESS_BAR_UPDATE_INTERVAL, max_results=max_results + ) progress_bar.update(default_total) progress_bar.set_description( "Query complete after {:0.2f}s".format(time.time() - start_time), @@ -89,5 +115,6 @@ def wait_for_query(query_job, progress_bar_type=None): progress_bar.update(i + 1) i += 1 continue + progress_bar.close() return query_result diff --git a/google/cloud/bigquery/client.py b/google/cloud/bigquery/client.py index 8d0acb867..023346ffa 100644 --- a/google/cloud/bigquery/client.py +++ b/google/cloud/bigquery/client.py @@ -27,6 +27,7 @@ import json import math import os +import packaging.version import tempfile from typing import Any, BinaryIO, Dict, Iterable, Optional, Sequence, Tuple, Union import uuid @@ -34,6 +35,8 @@ try: import pyarrow + + _PYARROW_VERSION = packaging.version.parse(pyarrow.__version__) except ImportError: # pragma: NO COVER pyarrow = None @@ -50,30 +53,47 @@ from google.cloud import exceptions # pytype: disable=import-error from google.cloud.client import ClientWithProject # pytype: disable=import-error +try: + from google.cloud.bigquery_storage_v1.services.big_query_read.client import ( + DEFAULT_CLIENT_INFO as DEFAULT_BQSTORAGE_CLIENT_INFO, + ) +except ImportError: + DEFAULT_BQSTORAGE_CLIENT_INFO = None + from google.cloud.bigquery._helpers import _del_sub_prop from google.cloud.bigquery._helpers import _get_sub_prop from google.cloud.bigquery._helpers import _record_field_to_json from google.cloud.bigquery._helpers import _str_or_none +from google.cloud.bigquery._helpers import BQ_STORAGE_VERSIONS from google.cloud.bigquery._helpers import _verify_job_config_type from google.cloud.bigquery._http import Connection from google.cloud.bigquery import _pandas_helpers from google.cloud.bigquery.dataset import Dataset from google.cloud.bigquery.dataset import DatasetListItem from google.cloud.bigquery.dataset import DatasetReference +from google.cloud.bigquery.enums import AutoRowIDs +from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError from google.cloud.bigquery.opentelemetry_tracing import create_span from google.cloud.bigquery import job from google.cloud.bigquery.job import ( + CopyJob, + CopyJobConfig, + ExtractJob, + ExtractJobConfig, + LoadJob, LoadJobConfig, QueryJob, QueryJobConfig, - CopyJobConfig, - ExtractJobConfig, ) from google.cloud.bigquery.model import Model from google.cloud.bigquery.model import ModelReference from google.cloud.bigquery.model import _model_arg_to_model_ref from google.cloud.bigquery.query import _QueryResults -from google.cloud.bigquery.retry import DEFAULT_RETRY +from google.cloud.bigquery.retry import ( + DEFAULT_JOB_RETRY, + DEFAULT_RETRY, + DEFAULT_TIMEOUT, +) from google.cloud.bigquery.routine import Routine from google.cloud.bigquery.routine import RoutineReference from google.cloud.bigquery.schema import SchemaField @@ -85,7 +105,7 @@ from google.cloud.bigquery.table import RowIterator -_DEFAULT_CHUNKSIZE = 1048576 # 1024 * 1024 B = 1 MB +_DEFAULT_CHUNKSIZE = 100 * 1024 * 1024 # 100 MB _MAX_MULTIPART_SIZE = 5 * 1024 * 1024 _DEFAULT_NUM_RETRIES = 6 _BASE_UPLOAD_TEMPLATE = "{host}/upload/bigquery/v2/projects/{project}/jobs?uploadType=" @@ -108,6 +128,9 @@ # https://github.com/googleapis/python-bigquery/issues/438 _MIN_GET_QUERY_RESULTS_TIMEOUT = 120 +# https://github.com/googleapis/python-bigquery/issues/781#issuecomment-883497414 +_PYARROW_BAD_VERSIONS = frozenset([packaging.version.Version("2.0.0")]) + class Project(object): """Wrapper for resource describing a BigQuery project. @@ -229,7 +252,7 @@ def get_service_account_email( self, project: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> str: """Get the email address of the project's BigQuery service account @@ -276,7 +299,8 @@ def list_projects( max_results: int = None, page_token: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, + page_size: int = None, ) -> page_iterator.Iterator: """List projects for the project associated with this client. @@ -285,8 +309,8 @@ def list_projects( Args: max_results (Optional[int]): - Maximum number of projects to return, If not passed, - defaults to a value set by the API. + Maximum number of projects to return. + Defaults to a value set by the API. page_token (Optional[str]): Token representing a cursor into the projects. If not passed, @@ -301,6 +325,10 @@ def list_projects( The number of seconds to wait for the underlying HTTP transport before using ``retry``. + page_size (Optional[int]): + Maximum number of projects to return in each page. + Defaults to a value set by the API. + Returns: google.api_core.page_iterator.Iterator: Iterator of :class:`~google.cloud.bigquery.client.Project` @@ -326,6 +354,7 @@ def api_request(*args, **kwargs): items_key="projects", page_token=page_token, max_results=max_results, + page_size=page_size, ) def list_datasets( @@ -336,7 +365,8 @@ def list_datasets( max_results: int = None, page_token: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, + page_size: int = None, ) -> page_iterator.Iterator: """List datasets for the project associated with this client. @@ -366,6 +396,8 @@ def list_datasets( timeout (Optional[float]): The number of seconds to wait for the underlying HTTP transport before using ``retry``. + page_size (Optional[int]): + Maximum number of datasets to return per page. Returns: google.api_core.page_iterator.Iterator: @@ -405,6 +437,7 @@ def api_request(*args, **kwargs): page_token=page_token, max_results=max_results, extra_params=extra_params, + page_size=page_size, ) def dataset(self, dataset_id: str, project: str = None) -> DatasetReference: @@ -445,15 +478,38 @@ def dataset(self, dataset_id: str, project: str = None) -> DatasetReference: ) return DatasetReference(project, dataset_id) - def _create_bqstorage_client(self): + def _ensure_bqstorage_client( + self, + bqstorage_client: Optional[ + "google.cloud.bigquery_storage.BigQueryReadClient" + ] = None, + client_options: Optional[google.api_core.client_options.ClientOptions] = None, + client_info: Optional[ + "google.api_core.gapic_v1.client_info.ClientInfo" + ] = DEFAULT_BQSTORAGE_CLIENT_INFO, + ) -> Optional["google.cloud.bigquery_storage.BigQueryReadClient"]: """Create a BigQuery Storage API client using this client's credentials. - If a client cannot be created due to missing dependencies, raise a - warning and return ``None``. + If a client cannot be created due to a missing or outdated dependency + `google-cloud-bigquery-storage`, raise a warning and return ``None``. + + If the `bqstorage_client` argument is not ``None``, still perform the version + check and return the argument back to the caller if the check passes. If it + fails, raise a warning and return ``None``. + + Args: + bqstorage_client: + An existing BigQuery Storage client instance to check for version + compatibility. If ``None``, a new instance is created and returned. + client_options: + Custom options used with a new BigQuery Storage client instance if one + is created. + client_info: + The client info used with a new BigQuery Storage client instance if one + is created. Returns: - Optional[google.cloud.bigquery_storage.BigQueryReadClient]: - A BigQuery Storage API client. + A BigQuery Storage API client. """ try: from google.cloud import bigquery_storage @@ -464,7 +520,20 @@ def _create_bqstorage_client(self): ) return None - return bigquery_storage.BigQueryReadClient(credentials=self._credentials) + try: + BQ_STORAGE_VERSIONS.verify_version() + except LegacyBigQueryStorageError as exc: + warnings.warn(str(exc)) + return None + + if bqstorage_client is None: + bqstorage_client = bigquery_storage.BigQueryReadClient( + credentials=self._credentials, + client_options=client_options, + client_info=client_info, + ) + + return bqstorage_client def _dataset_from_arg(self, dataset): if isinstance(dataset, str): @@ -487,7 +556,7 @@ def create_dataset( dataset: Union[str, Dataset, DatasetReference], exists_ok: bool = False, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Dataset: """API call: create the dataset via a POST request. @@ -562,7 +631,7 @@ def create_routine( routine: Routine, exists_ok: bool = False, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Routine: """[Beta] Create a routine via a POST request. @@ -617,7 +686,7 @@ def create_table( table: Union[str, Table, TableReference], exists_ok: bool = False, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Table: """API call: create a table via a PUT request @@ -689,7 +758,7 @@ def get_dataset( self, dataset_ref: Union[DatasetReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Dataset: """Fetch the dataset referenced by ``dataset_ref`` @@ -733,7 +802,7 @@ def get_iam_policy( table: Union[Table, TableReference], requested_policy_version: int = 1, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Policy: if not isinstance(table, (Table, TableReference)): raise TypeError("table must be a Table or TableReference") @@ -763,7 +832,7 @@ def set_iam_policy( policy: Policy, updateMask: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Policy: if not isinstance(table, (Table, TableReference)): raise TypeError("table must be a Table or TableReference") @@ -796,7 +865,7 @@ def test_iam_permissions( table: Union[Table, TableReference], permissions: Sequence[str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Dict[str, Any]: if not isinstance(table, (Table, TableReference)): raise TypeError("table must be a Table or TableReference") @@ -821,7 +890,7 @@ def get_model( self, model_ref: Union[ModelReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Model: """[Beta] Fetch the model referenced by ``model_ref``. @@ -864,7 +933,7 @@ def get_routine( self, routine_ref: Union[Routine, RoutineReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Routine: """[Beta] Get the routine referenced by ``routine_ref``. @@ -908,7 +977,7 @@ def get_table( self, table: Union[Table, TableReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Table: """Fetch the table referenced by ``table``. @@ -950,7 +1019,7 @@ def update_dataset( dataset: Dataset, fields: Sequence[str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Dataset: """Change some fields of a dataset. @@ -1020,7 +1089,7 @@ def update_model( model: Model, fields: Sequence[str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Model: """[Beta] Change some fields of a model. @@ -1084,7 +1153,7 @@ def update_routine( routine: Routine, fields: Sequence[str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Routine: """[Beta] Change some fields of a routine. @@ -1158,7 +1227,7 @@ def update_table( table: Table, fields: Sequence[str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Table: """Change some fields of a table. @@ -1224,7 +1293,8 @@ def list_models( max_results: int = None, page_token: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, + page_size: int = None, ) -> page_iterator.Iterator: """[Beta] List models in the dataset. @@ -1243,7 +1313,7 @@ def list_models( to create a dataset reference from a string using :func:`google.cloud.bigquery.dataset.DatasetReference.from_string`. max_results (Optional[int]): - Maximum number of models to return. If not passed, defaults to a + Maximum number of models to return. Defaults to a value set by the API. page_token (Optional[str]): Token representing a cursor into the models. If not passed, @@ -1256,6 +1326,9 @@ def list_models( timeout (Optional[float]): The number of seconds to wait for the underlying HTTP transport before using ``retry``. + page_size (Optional[int]): + Maximum number of models to return per page. + Defaults to a value set by the API. Returns: google.api_core.page_iterator.Iterator: @@ -1286,6 +1359,7 @@ def api_request(*args, **kwargs): items_key="models", page_token=page_token, max_results=max_results, + page_size=page_size, ) result.dataset = dataset return result @@ -1296,7 +1370,8 @@ def list_routines( max_results: int = None, page_token: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, + page_size: int = None, ) -> page_iterator.Iterator: """[Beta] List routines in the dataset. @@ -1315,7 +1390,7 @@ def list_routines( to create a dataset reference from a string using :func:`google.cloud.bigquery.dataset.DatasetReference.from_string`. max_results (Optional[int]): - Maximum number of routines to return. If not passed, defaults + Maximum number of routines to return. Defaults to a value set by the API. page_token (Optional[str]): Token representing a cursor into the routines. If not passed, @@ -1328,6 +1403,9 @@ def list_routines( timeout (Optional[float]): The number of seconds to wait for the underlying HTTP transport before using ``retry``. + page_size (Optional[int]): + Maximum number of routines to return per page. + Defaults to a value set by the API. Returns: google.api_core.page_iterator.Iterator: @@ -1358,6 +1436,7 @@ def api_request(*args, **kwargs): items_key="routines", page_token=page_token, max_results=max_results, + page_size=page_size, ) result.dataset = dataset return result @@ -1368,7 +1447,8 @@ def list_tables( max_results: int = None, page_token: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, + page_size: int = None, ) -> page_iterator.Iterator: """List tables in the dataset. @@ -1387,7 +1467,7 @@ def list_tables( to create a dataset reference from a string using :func:`google.cloud.bigquery.dataset.DatasetReference.from_string`. max_results (Optional[int]): - Maximum number of tables to return. If not passed, defaults + Maximum number of tables to return. Defaults to a value set by the API. page_token (Optional[str]): Token representing a cursor into the tables. If not passed, @@ -1400,6 +1480,9 @@ def list_tables( timeout (Optional[float]): The number of seconds to wait for the underlying HTTP transport before using ``retry``. + page_size (Optional[int]): + Maximum number of tables to return per page. + Defaults to a value set by the API. Returns: google.api_core.page_iterator.Iterator: @@ -1429,6 +1512,7 @@ def api_request(*args, **kwargs): items_key="tables", page_token=page_token, max_results=max_results, + page_size=page_size, ) result.dataset = dataset return result @@ -1438,7 +1522,7 @@ def delete_dataset( dataset: Union[Dataset, DatasetReference, str], delete_contents: bool = False, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, not_found_ok: bool = False, ) -> None: """Delete a dataset. @@ -1497,7 +1581,7 @@ def delete_model( self, model: Union[Model, ModelReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, not_found_ok: bool = False, ) -> None: """[Beta] Delete a model @@ -1547,12 +1631,12 @@ def delete_model( def delete_job_metadata( self, - job_id, - project=None, - location=None, - retry=DEFAULT_RETRY, - timeout=None, - not_found_ok=False, + job_id: Union[str, LoadJob, CopyJob, ExtractJob, QueryJob], + project: Optional[str] = None, + location: Optional[str] = None, + retry: retries.Retry = DEFAULT_RETRY, + timeout: float = DEFAULT_TIMEOUT, + not_found_ok: bool = False, ): """[Beta] Delete job metadata from job history. @@ -1560,26 +1644,20 @@ def delete_job_metadata( :func:`~google.cloud.bigquery.client.Client.cancel_job` instead. Args: - job_id (Union[ \ - str, \ - google.cloud.bigquery.job.LoadJob, \ - google.cloud.bigquery.job.CopyJob, \ - google.cloud.bigquery.job.ExtractJob, \ - google.cloud.bigquery.job.QueryJob \ - ]): Job identifier. + job_id: Job or job identifier. Keyword Arguments: - project (Optional[str]): + project: ID of the project which owns the job (defaults to the client's project). - location (Optional[str]): + location: Location where the job was run. Ignored if ``job_id`` is a job object. - retry (Optional[google.api_core.retry.Retry]): + retry: How to retry the RPC. - timeout (Optional[float]): + timeout: The number of seconds to wait for the underlying HTTP transport before using ``retry``. - not_found_ok (Optional[bool]): + not_found_ok: Defaults to ``False``. If ``True``, ignore "not found" errors when deleting the job. """ @@ -1620,7 +1698,7 @@ def delete_routine( self, routine: Union[Routine, RoutineReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, not_found_ok: bool = False, ) -> None: """[Beta] Delete a routine. @@ -1674,7 +1752,7 @@ def delete_table( self, table: Union[Table, TableReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, not_found_ok: bool = False, ) -> None: """Delete a table @@ -1727,7 +1805,7 @@ def _get_query_results( project: str = None, timeout_ms: int = None, location: str = None, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> _QueryResults: """Get the query results object for a query job. @@ -1816,7 +1894,7 @@ def create_job( self, job_config: dict, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Union[job.LoadJob, job.CopyJob, job.ExtractJob, job.QueryJob]: """Create a new job. Args: @@ -1913,7 +1991,7 @@ def get_job( project: str = None, location: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Union[job.LoadJob, job.CopyJob, job.ExtractJob, job.QueryJob]: """Fetch a job for the project associated with this client. @@ -1987,7 +2065,7 @@ def cancel_job( project: str = None, location: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Union[job.LoadJob, job.CopyJob, job.ExtractJob, job.QueryJob]: """Attempt to cancel a job from a job ID. @@ -2064,9 +2142,10 @@ def list_jobs( all_users: bool = None, state_filter: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, min_creation_time: datetime.datetime = None, max_creation_time: datetime.datetime = None, + page_size: int = None, ) -> page_iterator.Iterator: """List jobs for the project associated with this client. @@ -2112,6 +2191,8 @@ def list_jobs( Max value for job creation time. If set, only jobs created before or at this timestamp are returned. If the datetime has no time zone assumes UTC time. + page_size (Optional[int]): + Maximum number of jobs to return per page. Returns: google.api_core.page_iterator.Iterator: @@ -2163,6 +2244,7 @@ def api_request(*args, **kwargs): page_token=page_token, max_results=max_results, extra_params=extra_params, + page_size=page_size, ) def load_table_from_uri( @@ -2175,7 +2257,7 @@ def load_table_from_uri( project: str = None, job_config: LoadJobConfig = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> job.LoadJob: """Starts a job for loading data into a table from CloudStorage. @@ -2259,7 +2341,7 @@ def load_table_from_file( location: str = None, project: str = None, job_config: LoadJobConfig = None, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> job.LoadJob: """Upload the contents of this table from a file-like object. @@ -2362,7 +2444,7 @@ def load_table_from_dataframe( project: str = None, job_config: LoadJobConfig = None, parquet_compression: str = "snappy", - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> job.LoadJob: """Upload the contents of a table from a pandas DataFrame. @@ -2534,6 +2616,15 @@ def load_table_from_dataframe( try: if job_config.source_format == job.SourceFormat.PARQUET: + if _PYARROW_VERSION in _PYARROW_BAD_VERSIONS: + msg = ( + "Loading dataframe data in PARQUET format with pyarrow " + f"{_PYARROW_VERSION} can result in data corruption. It is " + "therefore *strongly* advised to use a different pyarrow " + "version or a different source format. " + "See: https://github.com/googleapis/python-bigquery/issues/781" + ) + warnings.warn(msg, category=RuntimeWarning) if job_config.schema: if parquet_compression == "snappy": # adjust the default value @@ -2588,7 +2679,7 @@ def load_table_from_json( location: str = None, project: str = None, job_config: LoadJobConfig = None, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> job.LoadJob: """Upload the contents of a table from a JSON string or dict. @@ -2672,7 +2763,7 @@ def load_table_from_json( destination = _table_arg_to_table_ref(destination, default_project=self.project) - data_str = "\n".join(json.dumps(item) for item in json_rows) + data_str = "\n".join(json.dumps(item, ensure_ascii=False) for item in json_rows) encoded_str = data_str.encode() data_file = io.BytesIO(encoded_str) return self.load_table_from_file( @@ -2871,7 +2962,7 @@ def copy_table( project: str = None, job_config: CopyJobConfig = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> job.CopyJob: """Copy one or more tables to another table. @@ -2974,7 +3065,7 @@ def extract_table( project: str = None, job_config: ExtractJobConfig = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, source_type: str = "Table", ) -> job.ExtractJob: """Start a job to extract a table into Cloud Storage files. @@ -3072,7 +3163,8 @@ def query( location: str = None, project: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, + job_retry: retries.Retry = DEFAULT_JOB_RETRY, ) -> job.QueryJob: """Run a SQL query. @@ -3102,20 +3194,52 @@ def query( Project ID of the project of where to run the job. Defaults to the client's project. retry (Optional[google.api_core.retry.Retry]): - How to retry the RPC. + How to retry the RPC. This only applies to making RPC + calls. It isn't used to retry failed jobs. This has + a reasonable default that should only be overridden + with care. timeout (Optional[float]): The number of seconds to wait for the underlying HTTP transport before using ``retry``. + job_retry (Optional[google.api_core.retry.Retry]): + How to retry failed jobs. The default retries + rate-limit-exceeded errors. Passing ``None`` disables + job retry. + + Not all jobs can be retried. If ``job_id`` is + provided, then the job returned by the query will not + be retryable, and an exception will be raised if a + non-``None`` (and non-default) value for ``job_retry`` + is also provided. + + Note that errors aren't detected until ``result()`` is + called on the job returned. The ``job_retry`` + specified here becomes the default ``job_retry`` for + ``result()``, where it can also be specified. Returns: google.cloud.bigquery.job.QueryJob: A new query job instance. Raises: TypeError: - If ``job_config`` is not an instance of :class:`~google.cloud.bigquery.job.QueryJobConfig` - class. + If ``job_config`` is not an instance of + :class:`~google.cloud.bigquery.job.QueryJobConfig` + class, or if both ``job_id`` and non-``None`` non-default + ``job_retry`` are provided. """ - job_id = _make_job_id(job_id, job_id_prefix) + job_id_given = job_id is not None + if ( + job_id_given + and job_retry is not None + and job_retry is not DEFAULT_JOB_RETRY + ): + raise TypeError( + "`job_retry` was provided, but the returned job is" + " not retryable, because a custom `job_id` was" + " provided." + ) + + job_id_save = job_id if project is None: project = self.project @@ -3123,8 +3247,6 @@ def query( if location is None: location = self.location - job_config = copy.deepcopy(job_config) - if self._default_query_job_config: if job_config: _verify_job_config_type( @@ -3134,6 +3256,8 @@ def query( # that is in the default, # should be filled in with the default # the incoming therefore has precedence + # + # Note that _fill_from_default doesn't mutate the receiver job_config = job_config._fill_from_default( self._default_query_job_config ) @@ -3142,13 +3266,54 @@ def query( self._default_query_job_config, google.cloud.bigquery.job.QueryJobConfig, ) - job_config = copy.deepcopy(self._default_query_job_config) + job_config = self._default_query_job_config - job_ref = job._JobReference(job_id, project=project, location=location) - query_job = job.QueryJob(job_ref, query, client=self, job_config=job_config) - query_job._begin(retry=retry, timeout=timeout) + # Note that we haven't modified the original job_config (or + # _default_query_job_config) up to this point. + job_config_save = job_config - return query_job + def do_query(): + # Make a copy now, so that original doesn't get changed by the process + # below and to facilitate retry + job_config = copy.deepcopy(job_config_save) + + job_id = _make_job_id(job_id_save, job_id_prefix) + job_ref = job._JobReference(job_id, project=project, location=location) + query_job = job.QueryJob(job_ref, query, client=self, job_config=job_config) + + try: + query_job._begin(retry=retry, timeout=timeout) + except core_exceptions.Conflict as create_exc: + # The thought is if someone is providing their own job IDs and they get + # their job ID generation wrong, this could end up returning results for + # the wrong query. We thus only try to recover if job ID was not given. + if job_id_given: + raise create_exc + + try: + query_job = self.get_job( + job_id, + project=project, + location=location, + retry=retry, + timeout=timeout, + ) + except core_exceptions.GoogleAPIError: # (includes RetryError) + raise create_exc + else: + return query_job + else: + return query_job + + future = do_query() + # The future might be in a failed state now, but if it's + # unrecoverable, we'll find out when we ask for it's result, at which + # point, we may retry. + if not job_id_given: + future._retry_do_query = do_query # in case we have to retry later + future._job_retry = job_retry + + return future def insert_rows( self, @@ -3275,12 +3440,12 @@ def insert_rows_json( self, table: Union[Table, TableReference, str], json_rows: Sequence[Dict], - row_ids: Sequence[str] = None, + row_ids: Union[Iterable[str], AutoRowIDs, None] = AutoRowIDs.GENERATE_UUID, skip_invalid_rows: bool = None, ignore_unknown_values: bool = None, template_suffix: str = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Sequence[dict]: """Insert rows into a table without applying local type conversions. @@ -3297,11 +3462,20 @@ def insert_rows_json( json_rows (Sequence[Dict]): Row data to be inserted. Keys must match the table schema fields and values must be JSON-compatible representations. - row_ids (Optional[Sequence[Optional[str]]]): + row_ids (Union[Iterable[str], AutoRowIDs, None]): Unique IDs, one per row being inserted. An ID can also be ``None``, indicating that an explicit insert ID should **not** be used for that row. If the argument is omitted altogether, unique IDs are created automatically. + + .. versionchanged:: 2.21.0 + Can also be an iterable, not just a sequence, or an + :class:`AutoRowIDs` enum member. + + .. deprecated:: 2.21.0 + Passing ``None`` to explicitly request autogenerating insert IDs is + deprecated, use :attr:`AutoRowIDs.GENERATE_UUID` instead. + skip_invalid_rows (Optional[bool]): Insert all valid rows of a request, even if invalid rows exist. The default value is ``False``, which causes the entire request @@ -3341,12 +3515,37 @@ def insert_rows_json( rows_info = [] data = {"rows": rows_info} - for index, row in enumerate(json_rows): + if row_ids is None: + warnings.warn( + "Passing None for row_ids is deprecated. To explicitly request " + "autogenerated insert IDs, use AutoRowIDs.GENERATE_UUID instead", + category=DeprecationWarning, + ) + row_ids = AutoRowIDs.GENERATE_UUID + + if not isinstance(row_ids, AutoRowIDs): + try: + row_ids_iter = iter(row_ids) + except TypeError: + msg = "row_ids is neither an iterable nor an AutoRowIDs enum member" + raise TypeError(msg) + + for i, row in enumerate(json_rows): info = {"json": row} - if row_ids is not None: - info["insertId"] = row_ids[index] - else: + + if row_ids is AutoRowIDs.GENERATE_UUID: info["insertId"] = str(uuid.uuid4()) + elif row_ids is AutoRowIDs.DISABLED: + info["insertId"] = None + else: + try: + insert_id = next(row_ids_iter) + except StopIteration: + msg = f"row_ids did not generate enough IDs, error at index {i}" + raise ValueError(msg) + else: + info["insertId"] = insert_id + rows_info.append(info) if skip_invalid_rows is not None: @@ -3381,7 +3580,7 @@ def list_partitions( self, table: Union[Table, TableReference, str], retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> Sequence[str]: """List the partitions in a table. @@ -3431,7 +3630,7 @@ def list_rows( start_index: int = None, page_size: int = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> RowIterator: """List the rows of the table. @@ -3543,7 +3742,7 @@ def _list_rows_from_query_results( start_index: int = None, page_size: int = None, retry: retries.Retry = DEFAULT_RETRY, - timeout: float = None, + timeout: float = DEFAULT_TIMEOUT, ) -> RowIterator: """List the rows of a completed query. See diff --git a/google/cloud/bigquery/dbapi/_helpers.py b/google/cloud/bigquery/dbapi/_helpers.py index 3b0d8134c..9c134b47c 100644 --- a/google/cloud/bigquery/dbapi/_helpers.py +++ b/google/cloud/bigquery/dbapi/_helpers.py @@ -18,18 +18,34 @@ import decimal import functools import numbers +import re +import typing from google.cloud import bigquery -from google.cloud.bigquery import table, enums +from google.cloud.bigquery import table, enums, query from google.cloud.bigquery.dbapi import exceptions _NUMERIC_SERVER_MIN = decimal.Decimal("-9.9999999999999999999999999999999999999E+28") _NUMERIC_SERVER_MAX = decimal.Decimal("9.9999999999999999999999999999999999999E+28") +type_parameters_re = re.compile( + r""" + \( + \s*[0-9]+\s* + (, + \s*[0-9]+\s* + )* + \) + """, + re.VERBOSE, +) + def _parameter_type(name, value, query_parameter_type=None, value_doc=""): if query_parameter_type: + # Strip type parameters + query_parameter_type = type_parameters_re.sub("", query_parameter_type) try: parameter_type = getattr( enums.SqlParameterScalarTypes, query_parameter_type.upper() @@ -113,6 +129,197 @@ def array_to_query_parameter(value, name=None, query_parameter_type=None): return bigquery.ArrayQueryParameter(name, array_type, value) +def _parse_struct_fields( + fields, + base, + parse_struct_field=re.compile( + r""" + (?:(\w+)\s+) # field name + ([A-Z0-9<> ,()]+) # Field type + $""", + re.VERBOSE | re.IGNORECASE, + ).match, +): + # Split a string of struct fields. They're defined by commas, but + # we have to avoid splitting on commas internal to fields. For + # example: + # name string, children array> + # + # only has 2 top-level fields. + fields = fields.split(",") + fields = list(reversed(fields)) # in the off chance that there are very many + while fields: + field = fields.pop() + while fields and field.count("<") != field.count(">"): + field += "," + fields.pop() + + m = parse_struct_field(field.strip()) + if not m: + raise exceptions.ProgrammingError( + f"Invalid struct field, {field}, in {base}" + ) + yield m.group(1, 2) + + +SCALAR, ARRAY, STRUCT = "sar" + + +def _parse_type( + type_, + name, + base, + complex_query_parameter_parse=re.compile( + r""" + \s* + (ARRAY|STRUCT|RECORD) # Type + \s* + <([A-Z0-9<> ,()]+)> # Subtype(s) + \s*$ + """, + re.IGNORECASE | re.VERBOSE, + ).match, +): + if "<" not in type_: + # Scalar + + # Strip type parameters + type_ = type_parameters_re.sub("", type_).strip() + try: + type_ = getattr(enums.SqlParameterScalarTypes, type_.upper()) + except AttributeError: + raise exceptions.ProgrammingError( + f"The given parameter type, {type_}," + f"{' for ' + name if name else ''}" + f" is not a valid BigQuery scalar type, in {base}." + ) + if name: + type_ = type_.with_name(name) + return SCALAR, type_ + + m = complex_query_parameter_parse(type_) + if not m: + raise exceptions.ProgrammingError(f"Invalid parameter type, {type_}") + tname, sub = m.group(1, 2) + if tname.upper() == "ARRAY": + sub_type = complex_query_parameter_type(None, sub, base) + if isinstance(sub_type, query.ArrayQueryParameterType): + raise exceptions.ProgrammingError(f"Array can't contain an array in {base}") + sub_type._complex__src = sub + return ARRAY, sub_type + else: + return STRUCT, _parse_struct_fields(sub, base) + + +def complex_query_parameter_type(name: typing.Optional[str], type_: str, base: str): + """Construct a parameter type (`StructQueryParameterType`) for a complex type + + or a non-complex type that's part of a complex type. + + Examples: + + array> + + struct>> + + This is used for computing array types. + """ + + type_type, sub_type = _parse_type(type_, name, base) + if type_type == SCALAR: + type_ = sub_type + elif type_type == ARRAY: + type_ = query.ArrayQueryParameterType(sub_type, name=name) + elif type_type == STRUCT: + fields = [ + complex_query_parameter_type(field_name, field_type, base) + for field_name, field_type in sub_type + ] + type_ = query.StructQueryParameterType(*fields, name=name) + else: # pragma: NO COVER + raise AssertionError("Bad type_type", type_type) # Can't happen :) + + return type_ + + +def complex_query_parameter( + name: typing.Optional[str], value, type_: str, base: typing.Optional[str] = None +): + """ + Construct a query parameter for a complex type (array or struct record) + + or for a subtype, which may not be complex + + Examples: + + array> + + struct>> + + """ + base = base or type_ + + type_type, sub_type = _parse_type(type_, name, base) + + if type_type == SCALAR: + param = query.ScalarQueryParameter(name, sub_type._type, value) + elif type_type == ARRAY: + if not array_like(value): + raise exceptions.ProgrammingError( + f"Array type with non-array-like value" + f" with type {type(value).__name__}" + ) + param = query.ArrayQueryParameter( + name, + sub_type, + value + if isinstance(sub_type, query.ScalarQueryParameterType) + else [ + complex_query_parameter(None, v, sub_type._complex__src, base) + for v in value + ], + ) + elif type_type == STRUCT: + if not isinstance(value, collections_abc.Mapping): + raise exceptions.ProgrammingError(f"Non-mapping value for type {type_}") + value_keys = set(value) + fields = [] + for field_name, field_type in sub_type: + if field_name not in value: + raise exceptions.ProgrammingError( + f"No field value for {field_name} in {type_}" + ) + value_keys.remove(field_name) + fields.append( + complex_query_parameter(field_name, value[field_name], field_type, base) + ) + if value_keys: + raise exceptions.ProgrammingError(f"Extra data keys for {type_}") + + param = query.StructQueryParameter(name, *fields) + else: # pragma: NO COVER + raise AssertionError("Bad type_type", type_type) # Can't happen :) + + return param + + +def _dispatch_parameter(type_, value, name=None): + if type_ is not None and "<" in type_: + param = complex_query_parameter(name, value, type_) + elif isinstance(value, collections_abc.Mapping): + raise NotImplementedError( + f"STRUCT-like parameter values are not supported" + f"{' (parameter ' + name + ')' if name else ''}," + f" unless an explicit type is give in the parameter placeholder" + f" (e.g. '%({name if name else ''}:struct<...>)s')." + ) + elif array_like(value): + param = array_to_query_parameter(value, name, type_) + else: + param = scalar_to_query_parameter(value, name, type_) + + return param + + def to_query_parameters_list(parameters, parameter_types): """Converts a sequence of parameter values into query parameters. @@ -126,19 +333,10 @@ def to_query_parameters_list(parameters, parameter_types): List[google.cloud.bigquery.query._AbstractQueryParameter]: A list of query parameters. """ - result = [] - - for value, type_ in zip(parameters, parameter_types): - if isinstance(value, collections_abc.Mapping): - raise NotImplementedError("STRUCT-like parameter values are not supported.") - elif array_like(value): - param = array_to_query_parameter(value, None, type_) - else: - param = scalar_to_query_parameter(value, None, type_) - - result.append(param) - - return result + return [ + _dispatch_parameter(type_, value) + for value, type_ in zip(parameters, parameter_types) + ] def to_query_parameters_dict(parameters, query_parameter_types): @@ -154,28 +352,10 @@ def to_query_parameters_dict(parameters, query_parameter_types): List[google.cloud.bigquery.query._AbstractQueryParameter]: A list of named query parameters. """ - result = [] - - for name, value in parameters.items(): - if isinstance(value, collections_abc.Mapping): - raise NotImplementedError( - "STRUCT-like parameter values are not supported " - "(parameter {}).".format(name) - ) - else: - query_parameter_type = query_parameter_types.get(name) - if array_like(value): - param = array_to_query_parameter( - value, name=name, query_parameter_type=query_parameter_type - ) - else: - param = scalar_to_query_parameter( - value, name=name, query_parameter_type=query_parameter_type, - ) - - result.append(param) - - return result + return [ + _dispatch_parameter(query_parameter_types.get(name), value, name) + for name, value in parameters.items() + ] def to_query_parameters(parameters, parameter_types): diff --git a/google/cloud/bigquery/dbapi/connection.py b/google/cloud/bigquery/dbapi/connection.py index 459fc82aa..66dee7dfb 100644 --- a/google/cloud/bigquery/dbapi/connection.py +++ b/google/cloud/bigquery/dbapi/connection.py @@ -47,12 +47,14 @@ def __init__(self, client=None, bqstorage_client=None): else: self._owns_client = False + # A warning is already raised by the BQ Storage client factory factory if + # instantiation fails, or if the given BQ Storage client instance is outdated. if bqstorage_client is None: - # A warning is already raised by the factory if instantiation fails. - bqstorage_client = client._create_bqstorage_client() + bqstorage_client = client._ensure_bqstorage_client() self._owns_bqstorage_client = bqstorage_client is not None else: self._owns_bqstorage_client = False + bqstorage_client = client._ensure_bqstorage_client(bqstorage_client) self._client = client self._bqstorage_client = bqstorage_client diff --git a/google/cloud/bigquery/dbapi/cursor.py b/google/cloud/bigquery/dbapi/cursor.py index c8fc49378..587598d5f 100644 --- a/google/cloud/bigquery/dbapi/cursor.py +++ b/google/cloud/bigquery/dbapi/cursor.py @@ -483,7 +483,33 @@ def _format_operation(operation, parameters): def _extract_types( - operation, extra_type_sub=re.compile(r"(%*)%(?:\(([^:)]*)(?::(\w+))?\))?s").sub + operation, + extra_type_sub=re.compile( + r""" + (%*) # Extra %s. We'll deal with these in the replacement code + + % # Beginning of replacement, %s, %(...)s + + (?:\( # Begin of optional name and/or type + ([^:)]*) # name + (?:: # ':' introduces type + ( # start of type group + [a-zA-Z0-9<>, ]+ # First part, no parens + + (?: # start sets of parens + non-paren text + \([0-9 ,]+\) # comma-separated groups of digits in parens + # (e.g. string(10)) + (?=[, >)]) # Must be followed by ,>) or space + [a-zA-Z0-9<>, ]* # Optional non-paren chars + )* # Can be zero or more of parens and following text + ) # end of type group + )? # close type clause ":type" + \))? # End of optional name and/or type + + s # End of replacement + """, + re.VERBOSE, + ).sub, ): """Remove type information from parameter placeholders. diff --git a/google/cloud/bigquery/enums.py b/google/cloud/bigquery/enums.py index 787c2449d..d67cebd4c 100644 --- a/google/cloud/bigquery/enums.py +++ b/google/cloud/bigquery/enums.py @@ -21,6 +21,13 @@ from google.cloud.bigquery.query import ScalarQueryParameterType +class AutoRowIDs(enum.Enum): + """How to handle automatic insert IDs when inserting rows as a stream.""" + + DISABLED = enum.auto() + GENERATE_UUID = enum.auto() + + class Compression(object): """The compression type to use for exported files. The default value is :attr:`NONE`. @@ -42,6 +49,24 @@ class Compression(object): """Specifies no compression.""" +class DecimalTargetType: + """The data types that could be used as a target type when converting decimal values. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#DecimalTargetType + + .. versionadded:: 2.21.0 + """ + + NUMERIC = "NUMERIC" + """Decimal values could be converted to NUMERIC type.""" + + BIGNUMERIC = "BIGNUMERIC" + """Decimal values could be converted to BIGNUMERIC type.""" + + STRING = "STRING" + """Decimal values could be converted to STRING type.""" + + class CreateDisposition(object): """Specifies whether the job is allowed to create new tables. The default value is :attr:`CREATE_IF_NEEDED`. @@ -142,6 +167,19 @@ class SourceFormat(object): """Specifies Orc format.""" +class KeyResultStatementKind: + """Determines which statement in the script represents the "key result". + + The "key result" is used to populate the schema and query results of the script job. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#keyresultstatementkind + """ + + KEY_RESULT_STATEMENT_KIND_UNSPECIFIED = "KEY_RESULT_STATEMENT_KIND_UNSPECIFIED" + LAST = "LAST" + FIRST_SELECT = "FIRST_SELECT" + + _SQL_SCALAR_TYPES = frozenset( ( "INT64", @@ -153,9 +191,11 @@ class SourceFormat(object): "DATE", "TIME", "DATETIME", + "INTERVAL", "GEOGRAPHY", "NUMERIC", "BIGNUMERIC", + "JSON", ) ) @@ -219,23 +259,23 @@ class SqlTypeNames(str, enum.Enum): class SqlParameterScalarTypes: """Supported scalar SQL query parameter types as type objects.""" - STRING = ScalarQueryParameterType("STRING") + BOOL = ScalarQueryParameterType("BOOL") + BOOLEAN = ScalarQueryParameterType("BOOL") + BIGDECIMAL = ScalarQueryParameterType("BIGNUMERIC") + BIGNUMERIC = ScalarQueryParameterType("BIGNUMERIC") BYTES = ScalarQueryParameterType("BYTES") - INTEGER = ScalarQueryParameterType("INT64") - INT64 = ScalarQueryParameterType("INT64") + DATE = ScalarQueryParameterType("DATE") + DATETIME = ScalarQueryParameterType("DATETIME") + DECIMAL = ScalarQueryParameterType("NUMERIC") FLOAT = ScalarQueryParameterType("FLOAT64") FLOAT64 = ScalarQueryParameterType("FLOAT64") - NUMERIC = ScalarQueryParameterType("NUMERIC") - BIGNUMERIC = ScalarQueryParameterType("BIGNUMERIC") - DECIMAL = ScalarQueryParameterType("NUMERIC") - BIGDECIMAL = ScalarQueryParameterType("BIGNUMERIC") - BOOLEAN = ScalarQueryParameterType("BOOL") - BOOL = ScalarQueryParameterType("BOOL") GEOGRAPHY = ScalarQueryParameterType("GEOGRAPHY") - TIMESTAMP = ScalarQueryParameterType("TIMESTAMP") - DATE = ScalarQueryParameterType("DATE") + INT64 = ScalarQueryParameterType("INT64") + INTEGER = ScalarQueryParameterType("INT64") + NUMERIC = ScalarQueryParameterType("NUMERIC") + STRING = ScalarQueryParameterType("STRING") TIME = ScalarQueryParameterType("TIME") - DATETIME = ScalarQueryParameterType("DATETIME") + TIMESTAMP = ScalarQueryParameterType("TIMESTAMP") class WriteDisposition(object): diff --git a/google/cloud/bigquery/exceptions.py b/google/cloud/bigquery/exceptions.py new file mode 100644 index 000000000..6e5c27eb1 --- /dev/null +++ b/google/cloud/bigquery/exceptions.py @@ -0,0 +1,21 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + + +class BigQueryError(Exception): + """Base class for all custom exceptions defined by the BigQuery client.""" + + +class LegacyBigQueryStorageError(BigQueryError): + """Raised when too old a version of BigQuery Storage extra is detected at runtime.""" diff --git a/google/cloud/bigquery/external_config.py b/google/cloud/bigquery/external_config.py index ef4d569fa..f1692ba50 100644 --- a/google/cloud/bigquery/external_config.py +++ b/google/cloud/bigquery/external_config.py @@ -22,11 +22,13 @@ import base64 import copy +from typing import FrozenSet, Iterable, Optional from google.cloud.bigquery._helpers import _to_bytes from google.cloud.bigquery._helpers import _bytes_to_json from google.cloud.bigquery._helpers import _int_or_none from google.cloud.bigquery._helpers import _str_or_none +from google.cloud.bigquery.format_options import ParquetOptions from google.cloud.bigquery.schema import SchemaField @@ -53,6 +55,12 @@ class ExternalSourceFormat(object): DATASTORE_BACKUP = "DATASTORE_BACKUP" """Specifies datastore backup format""" + ORC = "ORC" + """Specifies ORC format.""" + + PARQUET = "PARQUET" + """Specifies Parquet format.""" + BIGTABLE = "BIGTABLE" """Specifies Bigtable format.""" @@ -540,7 +548,7 @@ def from_api_repr(cls, resource: dict) -> "GoogleSheetsOptions": return config -_OPTION_CLASSES = (BigtableOptions, CSVOptions, GoogleSheetsOptions) +_OPTION_CLASSES = (BigtableOptions, CSVOptions, GoogleSheetsOptions, ParquetOptions) class HivePartitioningOptions(object): @@ -686,6 +694,28 @@ def compression(self): def compression(self, value): self._properties["compression"] = value + @property + def decimal_target_types(self) -> Optional[FrozenSet[str]]: + """Possible SQL data types to which the source decimal values are converted. + + See: + https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#ExternalDataConfiguration.FIELDS.decimal_target_types + + .. versionadded:: 2.21.0 + """ + prop = self._properties.get("decimalTargetTypes") + if prop is not None: + prop = frozenset(prop) + return prop + + @decimal_target_types.setter + def decimal_target_types(self, value: Optional[Iterable[str]]): + if value is not None: + self._properties["decimalTargetTypes"] = list(value) + else: + if "decimalTargetTypes" in self._properties: + del self._properties["decimalTargetTypes"] + @property def hive_partitioning(self): """Optional[:class:`~.external_config.HivePartitioningOptions`]: [Beta] When set, \ @@ -784,6 +814,25 @@ def schema(self, value): prop = {"fields": [field.to_api_repr() for field in value]} self._properties["schema"] = prop + @property + def parquet_options(self): + """Optional[google.cloud.bigquery.format_options.ParquetOptions]: Additional + properties to set if ``sourceFormat`` is set to PARQUET. + + See: + https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#ExternalDataConfiguration.FIELDS.parquet_options + """ + if self.source_format != ExternalSourceFormat.PARQUET: + return None + return self._options + + @parquet_options.setter + def parquet_options(self, value): + if self.source_format != ExternalSourceFormat.PARQUET: + msg = f"Cannot set Parquet options, source format is {self.source_format}" + raise TypeError(msg) + self._options = value + def to_api_repr(self) -> dict: """Build an API representation of this object. diff --git a/google/cloud/bigquery/format_options.py b/google/cloud/bigquery/format_options.py new file mode 100644 index 000000000..2c9a2ce20 --- /dev/null +++ b/google/cloud/bigquery/format_options.py @@ -0,0 +1,80 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import copy +from typing import Dict + + +class ParquetOptions: + """Additional options if the PARQUET source format is used.""" + + _SOURCE_FORMAT = "PARQUET" + _RESOURCE_NAME = "parquetOptions" + + def __init__(self): + self._properties = {} + + @property + def enum_as_string(self) -> bool: + """Indicates whether to infer Parquet ENUM logical type as STRING instead of + BYTES by default. + + See + https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#ParquetOptions.FIELDS.enum_as_string + """ + return self._properties.get("enumAsString") + + @enum_as_string.setter + def enum_as_string(self, value: bool) -> None: + self._properties["enumAsString"] = value + + @property + def enable_list_inference(self) -> bool: + """Indicates whether to use schema inference specifically for Parquet LIST + logical type. + + See + https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#ParquetOptions.FIELDS.enable_list_inference + """ + return self._properties.get("enableListInference") + + @enable_list_inference.setter + def enable_list_inference(self, value: bool) -> None: + self._properties["enableListInference"] = value + + @classmethod + def from_api_repr(cls, resource: Dict[str, bool]) -> "ParquetOptions": + """Factory: construct an instance from a resource dict. + + Args: + resource (Dict[str, bool]): + Definition of a :class:`~.format_options.ParquetOptions` instance in + the same representation as is returned from the API. + + Returns: + :class:`~.format_options.ParquetOptions`: + Configuration parsed from ``resource``. + """ + config = cls() + config._properties = copy.deepcopy(resource) + return config + + def to_api_repr(self) -> dict: + """Build an API representation of this object. + + Returns: + Dict[str, bool]: + A dictionary in the format used by the BigQuery API. + """ + return copy.deepcopy(self._properties) diff --git a/google/cloud/bigquery/job/__init__.py b/google/cloud/bigquery/job/__init__.py index 4945841d9..f51311b0b 100644 --- a/google/cloud/bigquery/job/__init__.py +++ b/google/cloud/bigquery/job/__init__.py @@ -22,18 +22,22 @@ from google.cloud.bigquery.job.base import ReservationUsage from google.cloud.bigquery.job.base import ScriptStatistics from google.cloud.bigquery.job.base import ScriptStackFrame +from google.cloud.bigquery.job.base import TransactionInfo from google.cloud.bigquery.job.base import UnknownJob from google.cloud.bigquery.job.copy_ import CopyJob from google.cloud.bigquery.job.copy_ import CopyJobConfig +from google.cloud.bigquery.job.copy_ import OperationType from google.cloud.bigquery.job.extract import ExtractJob from google.cloud.bigquery.job.extract import ExtractJobConfig from google.cloud.bigquery.job.load import LoadJob from google.cloud.bigquery.job.load import LoadJobConfig from google.cloud.bigquery.job.query import _contains_order_by +from google.cloud.bigquery.job.query import DmlStats from google.cloud.bigquery.job.query import QueryJob from google.cloud.bigquery.job.query import QueryJobConfig from google.cloud.bigquery.job.query import QueryPlanEntry from google.cloud.bigquery.job.query import QueryPlanEntryStep +from google.cloud.bigquery.job.query import ScriptOptions from google.cloud.bigquery.job.query import TimelineEntry from google.cloud.bigquery.enums import Compression from google.cloud.bigquery.enums import CreateDisposition @@ -58,15 +62,18 @@ "UnknownJob", "CopyJob", "CopyJobConfig", + "OperationType", "ExtractJob", "ExtractJobConfig", "LoadJob", "LoadJobConfig", "_contains_order_by", + "DmlStats", "QueryJob", "QueryJobConfig", "QueryPlanEntry", "QueryPlanEntryStep", + "ScriptOptions", "TimelineEntry", "Compression", "CreateDisposition", @@ -75,5 +82,6 @@ "QueryPriority", "SchemaUpdateOption", "SourceFormat", + "TransactionInfo", "WriteDisposition", ] diff --git a/google/cloud/bigquery/job/base.py b/google/cloud/bigquery/job/base.py index 20ad81c0b..e5fc592a6 100644 --- a/google/cloud/bigquery/job/base.py +++ b/google/cloud/bigquery/job/base.py @@ -19,6 +19,7 @@ import http import threading import typing +from typing import Dict, Optional from google.api_core import exceptions import google.api_core.future.polling @@ -88,6 +89,22 @@ def _error_result_to_exception(error_result): ) +class TransactionInfo(typing.NamedTuple): + """[Alpha] Information of a multi-statement transaction. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#TransactionInfo + + .. versionadded:: 2.24.0 + """ + + transaction_id: str + """Output only. ID of the transaction.""" + + @classmethod + def from_api_repr(cls, transaction_info: Dict[str, str]) -> "TransactionInfo": + return cls(transaction_info["transactionId"]) + + class _JobReference(object): """A reference to a job. @@ -336,6 +353,18 @@ def reservation_usage(self): for usage in usage_stats_raw ] + @property + def transaction_info(self) -> Optional[TransactionInfo]: + """Information of the multi-statement transaction if this job is part of one. + + .. versionadded:: 2.24.0 + """ + info = self._properties.get("statistics", {}).get("transactionInfo") + if info is None: + return None + else: + return TransactionInfo.from_api_repr(info) + @property def error_result(self): """Error information about the job as a whole. diff --git a/google/cloud/bigquery/job/copy_.py b/google/cloud/bigquery/job/copy_.py index 95f4b613b..c6ee98944 100644 --- a/google/cloud/bigquery/job/copy_.py +++ b/google/cloud/bigquery/job/copy_.py @@ -14,6 +14,8 @@ """Classes for copy jobs.""" +from typing import Optional + from google.cloud.bigquery.encryption_configuration import EncryptionConfiguration from google.cloud.bigquery import _helpers from google.cloud.bigquery.table import TableReference @@ -23,6 +25,25 @@ from google.cloud.bigquery.job.base import _JobReference +class OperationType: + """Different operation types supported in table copy job. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#operationtype + """ + + OPERATION_TYPE_UNSPECIFIED = "OPERATION_TYPE_UNSPECIFIED" + """Unspecified operation type.""" + + COPY = "COPY" + """The source and destination table have the same table type.""" + + SNAPSHOT = "SNAPSHOT" + """The source table type is TABLE and the destination table type is SNAPSHOT.""" + + RESTORE = "RESTORE" + """The source table type is SNAPSHOT and the destination table type is TABLE.""" + + class CopyJobConfig(_JobConfig): """Configuration options for copy jobs. @@ -85,6 +106,23 @@ def destination_encryption_configuration(self, value): api_repr = value.to_api_repr() self._set_sub_prop("destinationEncryptionConfiguration", api_repr) + @property + def operation_type(self) -> str: + """The operation to perform with this copy job. + + See + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationTableCopy.FIELDS.operation_type + """ + return self._get_sub_prop( + "operationType", OperationType.OPERATION_TYPE_UNSPECIFIED + ) + + @operation_type.setter + def operation_type(self, value: Optional[str]): + if value is None: + value = OperationType.OPERATION_TYPE_UNSPECIFIED + self._set_sub_prop("operationType", value) + class CopyJob(_AsyncJob): """Asynchronous job: copy data into a table from other tables. diff --git a/google/cloud/bigquery/job/load.py b/google/cloud/bigquery/job/load.py index b8174af3e..aee055c1c 100644 --- a/google/cloud/bigquery/job/load.py +++ b/google/cloud/bigquery/job/load.py @@ -14,15 +14,17 @@ """Classes for load jobs.""" +from typing import FrozenSet, List, Iterable, Optional + from google.cloud.bigquery.encryption_configuration import EncryptionConfiguration from google.cloud.bigquery.external_config import HivePartitioningOptions +from google.cloud.bigquery.format_options import ParquetOptions from google.cloud.bigquery import _helpers from google.cloud.bigquery.schema import SchemaField from google.cloud.bigquery.schema import _to_schema_fields from google.cloud.bigquery.table import RangePartitioning from google.cloud.bigquery.table import TableReference from google.cloud.bigquery.table import TimePartitioning - from google.cloud.bigquery.job.base import _AsyncJob from google.cloud.bigquery.job.base import _JobConfig from google.cloud.bigquery.job.base import _JobReference @@ -120,6 +122,27 @@ def create_disposition(self): def create_disposition(self, value): self._set_sub_prop("createDisposition", value) + @property + def decimal_target_types(self) -> Optional[FrozenSet[str]]: + """Possible SQL data types to which the source decimal values are converted. + + See: + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.decimal_target_types + + .. versionadded:: 2.21.0 + """ + prop = self._get_sub_prop("decimalTargetTypes") + if prop is not None: + prop = frozenset(prop) + return prop + + @decimal_target_types.setter + def decimal_target_types(self, value: Optional[Iterable[str]]): + if value is not None: + self._set_sub_prop("decimalTargetTypes", list(value)) + else: + self._del_sub_prop("decimalTargetTypes") + @property def destination_encryption_configuration(self): """Optional[google.cloud.bigquery.encryption_configuration.EncryptionConfiguration]: Custom @@ -147,7 +170,7 @@ def destination_encryption_configuration(self, value): @property def destination_table_description(self): - """Optional[str]: Name given to destination table. + """Optional[str]: Description of the destination table. See: https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#DestinationTableProperties.FIELDS.description @@ -276,6 +299,27 @@ def null_marker(self): def null_marker(self, value): self._set_sub_prop("nullMarker", value) + @property + def projection_fields(self) -> Optional[List[str]]: + """Optional[List[str]]: If + :attr:`google.cloud.bigquery.job.LoadJobConfig.source_format` is set to + "DATASTORE_BACKUP", indicates which entity properties to load into + BigQuery from a Cloud Datastore backup. + + Property names are case sensitive and must be top-level properties. If + no properties are specified, BigQuery loads all properties. If any + named property isn't found in the Cloud Datastore backup, an invalid + error is returned in the job result. + + See: + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.projection_fields + """ + return self._get_sub_prop("projectionFields") + + @projection_fields.setter + def projection_fields(self, value: Optional[List[str]]): + self._set_sub_prop("projectionFields", value) + @property def quote_character(self): """Optional[str]: Character used to quote data sections (CSV only). @@ -439,6 +483,26 @@ def write_disposition(self): def write_disposition(self, value): self._set_sub_prop("writeDisposition", value) + @property + def parquet_options(self): + """Optional[google.cloud.bigquery.format_options.ParquetOptions]: Additional + properties to set if ``sourceFormat`` is set to PARQUET. + + See: + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.parquet_options + """ + prop = self._get_sub_prop("parquetOptions") + if prop is not None: + prop = ParquetOptions.from_api_repr(prop) + return prop + + @parquet_options.setter + def parquet_options(self, value): + if value is not None: + self._set_sub_prop("parquetOptions", value.to_api_repr()) + else: + self._del_sub_prop("parquetOptions") + class LoadJob(_AsyncJob): """Asynchronous job for loading data into a table. diff --git a/google/cloud/bigquery/job/query.py b/google/cloud/bigquery/job/query.py index f52f9c621..0cb4798be 100644 --- a/google/cloud/bigquery/job/query.py +++ b/google/cloud/bigquery/job/query.py @@ -18,7 +18,7 @@ import copy import re import typing -from typing import Any, Dict, Union +from typing import Any, Dict, Optional, Union from google.api_core import exceptions from google.api_core.future import polling as polling_future @@ -28,6 +28,7 @@ from google.cloud.bigquery.dataset import DatasetListItem from google.cloud.bigquery.dataset import DatasetReference from google.cloud.bigquery.encryption_configuration import EncryptionConfiguration +from google.cloud.bigquery.enums import KeyResultStatementKind from google.cloud.bigquery.external_config import ExternalConfig from google.cloud.bigquery import _helpers from google.cloud.bigquery.query import _query_param_from_api_repr @@ -35,7 +36,7 @@ from google.cloud.bigquery.query import ScalarQueryParameter from google.cloud.bigquery.query import StructQueryParameter from google.cloud.bigquery.query import UDFResource -from google.cloud.bigquery.retry import DEFAULT_RETRY +from google.cloud.bigquery.retry import DEFAULT_RETRY, DEFAULT_JOB_RETRY from google.cloud.bigquery.routine import RoutineReference from google.cloud.bigquery.table import _EmptyRowIterator from google.cloud.bigquery.table import RangePartitioning @@ -52,6 +53,7 @@ # Assumption: type checks are only used by library developers and CI environments # that have all optional dependencies installed, thus no conditional imports. import pandas + import geopandas import pyarrow from google.api_core import retry as retries from google.cloud import bigquery_storage @@ -113,6 +115,111 @@ def _to_api_repr_table_defs(value): return {k: ExternalConfig.to_api_repr(v) for k, v in value.items()} +class DmlStats(typing.NamedTuple): + """Detailed statistics for DML statements. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/DmlStats + """ + + inserted_row_count: int = 0 + """Number of inserted rows. Populated by DML INSERT and MERGE statements.""" + + deleted_row_count: int = 0 + """Number of deleted rows. populated by DML DELETE, MERGE and TRUNCATE statements. + """ + + updated_row_count: int = 0 + """Number of updated rows. Populated by DML UPDATE and MERGE statements.""" + + @classmethod + def from_api_repr(cls, stats: Dict[str, str]) -> "DmlStats": + # NOTE: The field order here must match the order of fields set at the + # class level. + api_fields = ("insertedRowCount", "deletedRowCount", "updatedRowCount") + + args = ( + int(stats.get(api_field, default_val)) + for api_field, default_val in zip(api_fields, cls.__new__.__defaults__) + ) + return cls(*args) + + +class ScriptOptions: + """Options controlling the execution of scripts. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#ScriptOptions + """ + + def __init__( + self, + statement_timeout_ms: Optional[int] = None, + statement_byte_budget: Optional[int] = None, + key_result_statement: Optional[KeyResultStatementKind] = None, + ): + self._properties = {} + self.statement_timeout_ms = statement_timeout_ms + self.statement_byte_budget = statement_byte_budget + self.key_result_statement = key_result_statement + + @classmethod + def from_api_repr(cls, resource: Dict[str, Any]) -> "ScriptOptions": + """Factory: construct instance from the JSON repr. + + Args: + resource(Dict[str: Any]): + ScriptOptions representation returned from API. + + Returns: + google.cloud.bigquery.ScriptOptions: + ScriptOptions sample parsed from ``resource``. + """ + entry = cls() + entry._properties = copy.deepcopy(resource) + return entry + + def to_api_repr(self) -> Dict[str, Any]: + """Construct the API resource representation.""" + return copy.deepcopy(self._properties) + + @property + def statement_timeout_ms(self) -> Union[int, None]: + """Timeout period for each statement in a script.""" + return _helpers._int_or_none(self._properties.get("statementTimeoutMs")) + + @statement_timeout_ms.setter + def statement_timeout_ms(self, value: Union[int, None]): + if value is not None: + value = str(value) + self._properties["statementTimeoutMs"] = value + + @property + def statement_byte_budget(self) -> Union[int, None]: + """Limit on the number of bytes billed per statement. + + Exceeding this budget results in an error. + """ + return _helpers._int_or_none(self._properties.get("statementByteBudget")) + + @statement_byte_budget.setter + def statement_byte_budget(self, value: Union[int, None]): + if value is not None: + value = str(value) + self._properties["statementByteBudget"] = value + + @property + def key_result_statement(self) -> Union[KeyResultStatementKind, None]: + """Determines which statement in the script represents the "key result". + + This is used to populate the schema and query results of the script job. + Default is ``KeyResultStatementKind.LAST``. + """ + return self._properties.get("keyResultStatement") + + @key_result_statement.setter + def key_result_statement(self, value: Union[KeyResultStatementKind, None]): + self._properties["keyResultStatement"] = value + + class QueryJobConfig(_JobConfig): """Configuration options for query jobs. @@ -502,6 +609,23 @@ def schema_update_options(self): def schema_update_options(self, values): self._set_sub_prop("schemaUpdateOptions", values) + @property + def script_options(self) -> ScriptOptions: + """Connection properties which can modify the query behavior. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#scriptoptions + """ + prop = self._get_sub_prop("scriptOptions") + if prop is not None: + prop = ScriptOptions.from_api_repr(prop) + return prop + + @script_options.setter + def script_options(self, value: Union[ScriptOptions, None]): + if value is not None: + value = value.to_api_repr() + self._set_sub_prop("scriptOptions", value) + def to_api_repr(self) -> dict: """Build an API representation of the query job config. @@ -985,6 +1109,14 @@ def estimated_bytes_processed(self): result = int(result) return result + @property + def dml_stats(self) -> Optional[DmlStats]: + stats = self._job_statistics().get("dmlStats") + if stats is None: + return None + else: + return DmlStats.from_api_repr(stats) + def _blocking_poll(self, timeout=None, **kwargs): self._done_timeout = timeout self._transport_timeout = timeout @@ -1129,6 +1261,7 @@ def result( retry: "retries.Retry" = DEFAULT_RETRY, timeout: float = None, start_index: int = None, + job_retry: "retries.Retry" = DEFAULT_JOB_RETRY, ) -> Union["RowIterator", _EmptyRowIterator]: """Start the job and wait for it to complete and get the result. @@ -1139,9 +1272,13 @@ def result( max_results (Optional[int]): The maximum total number of rows from this request. retry (Optional[google.api_core.retry.Retry]): - How to retry the call that retrieves rows. If the job state is - ``DONE``, retrying is aborted early even if the results are not - available, as this will not change anymore. + How to retry the call that retrieves rows. This only + applies to making RPC calls. It isn't used to retry + failed jobs. This has a reasonable default that + should only be overridden with care. If the job state + is ``DONE``, retrying is aborted early even if the + results are not available, as this will not change + anymore. timeout (Optional[float]): The number of seconds to wait for the underlying HTTP transport before using ``retry``. @@ -1149,6 +1286,16 @@ def result( applies to each individual request. start_index (Optional[int]): The zero-based index of the starting row to read. + job_retry (Optional[google.api_core.retry.Retry]): + How to retry failed jobs. The default retries + rate-limit-exceeded errors. Passing ``None`` disables + job retry. + + Not all jobs can be retried. If ``job_id`` was + provided to the query that created this job, then the + job returned by the query will not be retryable, and + an exception will be raised if non-``None`` + non-default ``job_retry`` is also provided. Returns: google.cloud.bigquery.table.RowIterator: @@ -1164,17 +1311,66 @@ def result( Raises: google.cloud.exceptions.GoogleAPICallError: - If the job failed. + If the job failed and retries aren't successful. concurrent.futures.TimeoutError: If the job did not complete in the given timeout. + TypeError: + If Non-``None`` and non-default ``job_retry`` is + provided and the job is not retryable. """ try: - super(QueryJob, self).result(retry=retry, timeout=timeout) + retry_do_query = getattr(self, "_retry_do_query", None) + if retry_do_query is not None: + if job_retry is DEFAULT_JOB_RETRY: + job_retry = self._job_retry + else: + if job_retry is not None and job_retry is not DEFAULT_JOB_RETRY: + raise TypeError( + "`job_retry` was provided, but this job is" + " not retryable, because a custom `job_id` was" + " provided to the query that created this job." + ) + + first = True + + def do_get_result(): + nonlocal first + + if first: + first = False + else: + # Note that we won't get here if retry_do_query is + # None, because we won't use a retry. + + # The orinal job is failed. Create a new one. + job = retry_do_query() + + # If it's already failed, we might as well stop: + if job.done() and job.exception() is not None: + raise job.exception() + + # Become the new job: + self.__dict__.clear() + self.__dict__.update(job.__dict__) + + # This shouldn't be necessary, because once we have a good + # job, it should stay good,and we shouldn't have to retry. + # But let's be paranoid. :) + self._retry_do_query = retry_do_query + self._job_retry = job_retry + + super(QueryJob, self).result(retry=retry, timeout=timeout) + + # Since the job could already be "done" (e.g. got a finished job + # via client.get_job), the superclass call to done() might not + # set the self._query_results cache. + self._reload_query_results(retry=retry, timeout=timeout) + + if retry_do_query is not None and job_retry is not None: + do_get_result = job_retry(do_get_result) + + do_get_result() - # Since the job could already be "done" (e.g. got a finished job - # via client.get_job), the superclass call to done() might not - # set the self._query_results cache. - self._reload_query_results(retry=retry, timeout=timeout) except exceptions.GoogleAPICallError as exc: exc.message += self._format_for_exception(self.query, self.job_id) exc.query_job = self @@ -1206,12 +1402,14 @@ def result( return rows # If changing the signature of this method, make sure to apply the same - # changes to table.RowIterator.to_arrow() + # changes to table.RowIterator.to_arrow(), except for the max_results parameter + # that should only exist here in the QueryJob method. def to_arrow( self, progress_bar_type: str = None, bqstorage_client: "bigquery_storage.BigQueryReadClient" = None, create_bqstorage_client: bool = True, + max_results: Optional[int] = None, ) -> "pyarrow.Table": """[Beta] Create a class:`pyarrow.Table` by loading all pages of a table or query. @@ -1253,7 +1451,12 @@ def to_arrow( This argument does nothing if ``bqstorage_client`` is supplied. - ..versionadded:: 1.24.0 + .. versionadded:: 1.24.0 + + max_results (Optional[int]): + Maximum number of rows to include in the result. No limit by default. + + .. versionadded:: 2.21.0 Returns: pyarrow.Table @@ -1265,9 +1468,9 @@ def to_arrow( ValueError: If the :mod:`pyarrow` library cannot be imported. - ..versionadded:: 1.17.0 + .. versionadded:: 1.17.0 """ - query_result = wait_for_query(self, progress_bar_type) + query_result = wait_for_query(self, progress_bar_type, max_results=max_results) return query_result.to_arrow( progress_bar_type=progress_bar_type, bqstorage_client=bqstorage_client, @@ -1275,7 +1478,8 @@ def to_arrow( ) # If changing the signature of this method, make sure to apply the same - # changes to table.RowIterator.to_dataframe() + # changes to table.RowIterator.to_dataframe(), except for the max_results parameter + # that should only exist here in the QueryJob method. def to_dataframe( self, bqstorage_client: "bigquery_storage.BigQueryReadClient" = None, @@ -1283,6 +1487,8 @@ def to_dataframe( progress_bar_type: str = None, create_bqstorage_client: bool = True, date_as_object: bool = True, + max_results: Optional[int] = None, + geography_as_object: bool = False, ) -> "pandas.DataFrame": """Return a pandas DataFrame from a QueryJob @@ -1312,7 +1518,7 @@ def to_dataframe( :func:`~google.cloud.bigquery.table.RowIterator.to_dataframe` for details. - ..versionadded:: 1.11.0 + .. versionadded:: 1.11.0 create_bqstorage_client (Optional[bool]): If ``True`` (default), create a BigQuery Storage API client using the default API settings. The BigQuery Storage API @@ -1321,29 +1527,143 @@ def to_dataframe( This argument does nothing if ``bqstorage_client`` is supplied. - ..versionadded:: 1.24.0 + .. versionadded:: 1.24.0 date_as_object (Optional[bool]): If ``True`` (default), cast dates to objects. If ``False``, convert to datetime64[ns] dtype. - ..versionadded:: 1.26.0 + .. versionadded:: 1.26.0 + + max_results (Optional[int]): + Maximum number of rows to include in the result. No limit by default. + + .. versionadded:: 2.21.0 + + geography_as_object (Optional[bool]): + If ``True``, convert GEOGRAPHY data to :mod:`shapely` + geometry objects. If ``False`` (default), don't cast + geography data to :mod:`shapely` geometry objects. + + .. versionadded:: 2.24.0 Returns: - A :class:`~pandas.DataFrame` populated with row data and column - headers from the query results. The column headers are derived - from the destination table's schema. + pandas.DataFrame: + A :class:`~pandas.DataFrame` populated with row data + and column headers from the query results. The column + headers are derived from the destination table's + schema. Raises: - ValueError: If the `pandas` library cannot be imported. + ValueError: + If the :mod:`pandas` library cannot be imported, or + the :mod:`google.cloud.bigquery_storage_v1` module is + required but cannot be imported. Also if + `geography_as_object` is `True`, but the + :mod:`shapely` library cannot be imported. """ - query_result = wait_for_query(self, progress_bar_type) + query_result = wait_for_query(self, progress_bar_type, max_results=max_results) return query_result.to_dataframe( bqstorage_client=bqstorage_client, dtypes=dtypes, progress_bar_type=progress_bar_type, create_bqstorage_client=create_bqstorage_client, date_as_object=date_as_object, + geography_as_object=geography_as_object, + ) + + # If changing the signature of this method, make sure to apply the same + # changes to table.RowIterator.to_dataframe(), except for the max_results parameter + # that should only exist here in the QueryJob method. + def to_geodataframe( + self, + bqstorage_client: "bigquery_storage.BigQueryReadClient" = None, + dtypes: Dict[str, Any] = None, + progress_bar_type: str = None, + create_bqstorage_client: bool = True, + date_as_object: bool = True, + max_results: Optional[int] = None, + geography_column: Optional[str] = None, + ) -> "geopandas.GeoDataFrame": + """Return a GeoPandas GeoDataFrame from a QueryJob + + Args: + bqstorage_client (Optional[google.cloud.bigquery_storage_v1.BigQueryReadClient]): + A BigQuery Storage API client. If supplied, use the faster + BigQuery Storage API to fetch rows from BigQuery. This + API is a billable API. + + This method requires the ``fastavro`` and + ``google-cloud-bigquery-storage`` libraries. + + Reading from a specific partition or snapshot is not + currently supported by this method. + + dtypes (Optional[Map[str, Union[str, pandas.Series.dtype]]]): + A dictionary of column names pandas ``dtype``s. The provided + ``dtype`` is used when constructing the series for the column + specified. Otherwise, the default pandas behavior is used. + + progress_bar_type (Optional[str]): + If set, use the `tqdm `_ library to + display a progress bar while the data downloads. Install the + ``tqdm`` package to use this feature. + + See + :func:`~google.cloud.bigquery.table.RowIterator.to_dataframe` + for details. + + .. versionadded:: 1.11.0 + create_bqstorage_client (Optional[bool]): + If ``True`` (default), create a BigQuery Storage API client + using the default API settings. The BigQuery Storage API + is a faster way to fetch rows from BigQuery. See the + ``bqstorage_client`` parameter for more information. + + This argument does nothing if ``bqstorage_client`` is supplied. + + .. versionadded:: 1.24.0 + + date_as_object (Optional[bool]): + If ``True`` (default), cast dates to objects. If ``False``, convert + to datetime64[ns] dtype. + + .. versionadded:: 1.26.0 + + max_results (Optional[int]): + Maximum number of rows to include in the result. No limit by default. + + .. versionadded:: 2.21.0 + + geography_column (Optional[str]): + If there are more than one GEOGRAPHY column, + identifies which one to use to construct a GeoPandas + GeoDataFrame. This option can be ommitted if there's + only one GEOGRAPHY column. + + Returns: + geopandas.GeoDataFrame: + A :class:`geopandas.GeoDataFrame` populated with row + data and column headers from the query results. The + column headers are derived from the destination + table's schema. + + Raises: + ValueError: + If the :mod:`geopandas` library cannot be imported, or the + :mod:`google.cloud.bigquery_storage_v1` module is + required but cannot be imported. + + .. versionadded:: 2.24.0 + """ + query_result = wait_for_query(self, progress_bar_type, max_results=max_results) + return query_result.to_geodataframe( + bqstorage_client=bqstorage_client, + dtypes=dtypes, + progress_bar_type=progress_bar_type, + create_bqstorage_client=create_bqstorage_client, + date_as_object=date_as_object, + geography_column=geography_column, ) def __iter__(self): diff --git a/google/cloud/bigquery/magics/magics.py b/google/cloud/bigquery/magics/magics.py index 474d9a74a..d368bbeaa 100644 --- a/google/cloud/bigquery/magics/magics.py +++ b/google/cloud/bigquery/magics/magics.py @@ -644,7 +644,7 @@ def _cell_magic(line, query): bqstorage_client_options.api_endpoint = args.bqstorage_api_endpoint bqstorage_client = _make_bqstorage_client( - use_bqstorage_api, context.credentials, bqstorage_client_options, + client, use_bqstorage_api, bqstorage_client_options, ) close_transports = functools.partial(_close_transports, client, bqstorage_client) @@ -671,7 +671,9 @@ def _cell_magic(line, query): _handle_error(ex, args.destination_var) return - result = rows.to_dataframe(bqstorage_client=bqstorage_client) + result = rows.to_dataframe( + bqstorage_client=bqstorage_client, create_bqstorage_client=False, + ) if args.destination_var: IPython.get_ipython().push({args.destination_var: result}) return @@ -728,11 +730,15 @@ def _cell_magic(line, query): if max_results: result = query_job.result(max_results=max_results).to_dataframe( - bqstorage_client=bqstorage_client, progress_bar_type=progress_bar + bqstorage_client=None, + create_bqstorage_client=False, + progress_bar_type=progress_bar, ) else: result = query_job.to_dataframe( - bqstorage_client=bqstorage_client, progress_bar_type=progress_bar + bqstorage_client=bqstorage_client, + create_bqstorage_client=False, + progress_bar_type=progress_bar, ) if args.destination_var: @@ -762,12 +768,12 @@ def _split_args_line(line): return params_option_value, rest_of_args -def _make_bqstorage_client(use_bqstorage_api, credentials, client_options): +def _make_bqstorage_client(client, use_bqstorage_api, client_options): if not use_bqstorage_api: return None try: - from google.cloud import bigquery_storage + from google.cloud import bigquery_storage # noqa: F401 except ImportError as err: customized_error = ImportError( "The default BigQuery Storage API client cannot be used, install " @@ -785,10 +791,9 @@ def _make_bqstorage_client(use_bqstorage_api, credentials, client_options): ) raise customized_error from err - return bigquery_storage.BigQueryReadClient( - credentials=credentials, - client_info=gapic_client_info.ClientInfo(user_agent=IPYTHON_USER_AGENT), + return client._ensure_bqstorage_client( client_options=client_options, + client_info=gapic_client_info.ClientInfo(user_agent=IPYTHON_USER_AGENT), ) diff --git a/google/cloud/bigquery/query.py b/google/cloud/bigquery/query.py index d1e9a45a5..1f449f189 100644 --- a/google/cloud/bigquery/query.py +++ b/google/cloud/bigquery/query.py @@ -16,7 +16,9 @@ from collections import OrderedDict import copy -from typing import Union +import datetime +import decimal +from typing import Optional, Union from google.cloud.bigquery.table import _parse_schema_resource from google.cloud.bigquery._helpers import _rows_from_json @@ -24,6 +26,11 @@ from google.cloud.bigquery._helpers import _SCALAR_VALUE_TO_JSON_PARAM +_SCALAR_VALUE_TYPE = Optional[ + Union[str, int, float, decimal.Decimal, bool, datetime.datetime, datetime.date] +] + + class UDFResource(object): """Describe a single user-defined function (UDF) resource. @@ -325,35 +332,46 @@ class ScalarQueryParameter(_AbstractQueryParameter): """Named / positional query parameters for scalar values. Args: - name (Optional[str]): + name: Parameter name, used via ``@foo`` syntax. If None, the parameter can only be addressed via position (``?``). - type_ (str): - Name of parameter type. One of 'STRING', 'INT64', - 'FLOAT64', 'NUMERIC', 'BIGNUMERIC', 'BOOL', 'TIMESTAMP', 'DATETIME', or - 'DATE'. + type_: + Name of parameter type. See + :class:`google.cloud.bigquery.enums.SqlTypeNames` and + :class:`google.cloud.bigquery.enums.SqlParameterScalarTypes` for + supported types. - value (Union[str, int, float, decimal.Decimal, bool, datetime.datetime, datetime.date]): + value: The scalar parameter value. """ - def __init__(self, name, type_, value): + def __init__( + self, + name: Optional[str], + type_: Optional[Union[str, ScalarQueryParameterType]], + value: _SCALAR_VALUE_TYPE, + ): self.name = name - self.type_ = type_ + if isinstance(type_, ScalarQueryParameterType): + self.type_ = type_._type + else: + self.type_ = type_ self.value = value @classmethod - def positional(cls, type_: str, value) -> "ScalarQueryParameter": + def positional( + cls, type_: Union[str, ScalarQueryParameterType], value: _SCALAR_VALUE_TYPE + ) -> "ScalarQueryParameter": """Factory for positional paramater. Args: - type_ (str): + type_: Name of parameter type. One of 'STRING', 'INT64', 'FLOAT64', 'NUMERIC', 'BIGNUMERIC', 'BOOL', 'TIMESTAMP', 'DATETIME', or 'DATE'. - value (Union[str, int, float, decimal.Decimal, bool, datetime.datetime, datetime.date]): + value: The scalar parameter value. Returns: diff --git a/google/cloud/bigquery/retry.py b/google/cloud/bigquery/retry.py index 5e9075fe1..830582322 100644 --- a/google/cloud/bigquery/retry.py +++ b/google/cloud/bigquery/retry.py @@ -27,10 +27,14 @@ exceptions.TooManyRequests, exceptions.InternalServerError, exceptions.BadGateway, + requests.exceptions.ChunkedEncodingError, requests.exceptions.ConnectionError, + requests.exceptions.Timeout, auth_exceptions.TransportError, ) +_DEFAULT_JOB_DEADLINE = 60.0 * 10.0 # seconds + def _should_retry(exc): """Predicate for determining when to retry. @@ -46,7 +50,7 @@ def _should_retry(exc): return reason in _RETRYABLE_REASONS -DEFAULT_RETRY = retry.Retry(predicate=_should_retry) +DEFAULT_RETRY = retry.Retry(predicate=_should_retry, deadline=600.0) """The default retry object. Any method with a ``retry`` parameter will be retried automatically, @@ -55,3 +59,28 @@ def _should_retry(exc): on ``DEFAULT_RETRY``. For example, to change the deadline to 30 seconds, pass ``retry=bigquery.DEFAULT_RETRY.with_deadline(30)``. """ + +DEFAULT_TIMEOUT = 5.0 * 60.0 +"""The default API timeout. + +This is the time to wait per request. To adjust the total wait time, set a +deadline on the retry object. +""" + +job_retry_reasons = "rateLimitExceeded", "backendError" + + +def _job_should_retry(exc): + if not hasattr(exc, "errors") or len(exc.errors) == 0: + return False + + reason = exc.errors[0]["reason"] + return reason in job_retry_reasons + + +DEFAULT_JOB_RETRY = retry.Retry( + predicate=_job_should_retry, deadline=_DEFAULT_JOB_DEADLINE +) +""" +The default job retry object. +""" diff --git a/google/cloud/bigquery/routine/__init__.py b/google/cloud/bigquery/routine/__init__.py index d1c79b05e..7353073c8 100644 --- a/google/cloud/bigquery/routine/__init__.py +++ b/google/cloud/bigquery/routine/__init__.py @@ -19,6 +19,7 @@ from google.cloud.bigquery.routine.routine import Routine from google.cloud.bigquery.routine.routine import RoutineArgument from google.cloud.bigquery.routine.routine import RoutineReference +from google.cloud.bigquery.routine.routine import RoutineType __all__ = ( @@ -26,4 +27,5 @@ "Routine", "RoutineArgument", "RoutineReference", + "RoutineType", ) diff --git a/google/cloud/bigquery/routine/routine.py b/google/cloud/bigquery/routine/routine.py index bbc0a7693..a776212c3 100644 --- a/google/cloud/bigquery/routine/routine.py +++ b/google/cloud/bigquery/routine/routine.py @@ -21,6 +21,21 @@ import google.cloud._helpers from google.cloud.bigquery import _helpers import google.cloud.bigquery_v2.types +from google.cloud.bigquery_v2.types import StandardSqlTableType + + +class RoutineType: + """The fine-grained type of the routine. + + https://cloud.google.com/bigquery/docs/reference/rest/v2/routines#routinetype + + .. versionadded:: 2.22.0 + """ + + ROUTINE_TYPE_UNSPECIFIED = "ROUTINE_TYPE_UNSPECIFIED" + SCALAR_FUNCTION = "SCALAR_FUNCTION" + PROCEDURE = "PROCEDURE" + TABLE_VALUED_FUNCTION = "TABLE_VALUED_FUNCTION" class Routine(object): @@ -48,6 +63,7 @@ class Routine(object): "modified": "lastModifiedTime", "reference": "routineReference", "return_type": "returnType", + "return_table_type": "returnTableType", "type_": "routineType", "description": "description", "determinism_level": "determinismLevel", @@ -204,6 +220,35 @@ def return_type(self, value): resource = None self._properties[self._PROPERTY_TO_API_FIELD["return_type"]] = resource + @property + def return_table_type(self) -> StandardSqlTableType: + """The return type of a Table Valued Function (TVF) routine. + + .. versionadded:: 2.22.0 + """ + resource = self._properties.get( + self._PROPERTY_TO_API_FIELD["return_table_type"] + ) + if not resource: + return resource + + output = google.cloud.bigquery_v2.types.StandardSqlTableType() + raw_protobuf = json_format.ParseDict( + resource, output._pb, ignore_unknown_fields=True + ) + return type(output).wrap(raw_protobuf) + + @return_table_type.setter + def return_table_type(self, value): + if not value: + resource = None + else: + resource = { + "columns": [json_format.MessageToDict(col._pb) for col in value.columns] + } + + self._properties[self._PROPERTY_TO_API_FIELD["return_table_type"]] = resource + @property def imported_libraries(self): """List[str]: The path of the imported JavaScript libraries. diff --git a/google/cloud/bigquery/schema.py b/google/cloud/bigquery/schema.py index cb221d6de..157db7ce6 100644 --- a/google/cloud/bigquery/schema.py +++ b/google/cloud/bigquery/schema.py @@ -15,6 +15,7 @@ """Schemas for BigQuery tables / queries.""" import collections +from typing import Optional from google.cloud.bigquery_v2 import types @@ -67,6 +68,15 @@ class SchemaField(object): policy_tags (Optional[PolicyTagList]): The policy tag list for the field. + precision (Optional[int]): + Precison (number of digits) of fields with NUMERIC or BIGNUMERIC type. + + scale (Optional[int]): + Scale (digits after decimal) of fields with NUMERIC or BIGNUMERIC type. + + max_length (Optional[int]): + Maximim length of fields with STRING or BYTES type. + """ def __init__( @@ -77,6 +87,9 @@ def __init__( description=_DEFAULT_VALUE, fields=(), policy_tags=None, + precision=_DEFAULT_VALUE, + scale=_DEFAULT_VALUE, + max_length=_DEFAULT_VALUE, ): self._properties = { "name": name, @@ -86,8 +99,40 @@ def __init__( self._properties["mode"] = mode.upper() if description is not _DEFAULT_VALUE: self._properties["description"] = description + if precision is not _DEFAULT_VALUE: + self._properties["precision"] = precision + if scale is not _DEFAULT_VALUE: + self._properties["scale"] = scale + if max_length is not _DEFAULT_VALUE: + self._properties["maxLength"] = max_length self._fields = tuple(fields) - self._policy_tags = policy_tags + + self._policy_tags = self._determine_policy_tags(field_type, policy_tags) + + @staticmethod + def _determine_policy_tags( + field_type: str, given_policy_tags: Optional["PolicyTagList"] + ) -> Optional["PolicyTagList"]: + """Return the given policy tags, or their suitable representation if `None`. + + Args: + field_type: The type of the schema field. + given_policy_tags: The policy tags to maybe ajdust. + """ + if given_policy_tags is not None: + return given_policy_tags + + if field_type is not None and field_type.upper() in _STRUCT_TYPES: + return None + + return PolicyTagList() + + @staticmethod + def __get_int(api_repr, name): + v = api_repr.get(name, _DEFAULT_VALUE) + if v is not _DEFAULT_VALUE: + v = int(v) + return v @classmethod def from_api_repr(cls, api_repr: dict) -> "SchemaField": @@ -101,18 +146,27 @@ def from_api_repr(cls, api_repr: dict) -> "SchemaField": Returns: google.cloud.biquery.schema.SchemaField: The ``SchemaField`` object. """ + field_type = api_repr["type"].upper() + # Handle optional properties with default values mode = api_repr.get("mode", "NULLABLE") description = api_repr.get("description", _DEFAULT_VALUE) fields = api_repr.get("fields", ()) + policy_tags = cls._determine_policy_tags( + field_type, PolicyTagList.from_api_repr(api_repr.get("policyTags")) + ) + return cls( - field_type=api_repr["type"].upper(), + field_type=field_type, fields=[cls.from_api_repr(f) for f in fields], mode=mode.upper(), description=description, name=api_repr["name"], - policy_tags=PolicyTagList.from_api_repr(api_repr.get("policyTags")), + policy_tags=policy_tags, + precision=cls.__get_int(api_repr, "precision"), + scale=cls.__get_int(api_repr, "scale"), + max_length=cls.__get_int(api_repr, "maxLength"), ) @property @@ -148,6 +202,21 @@ def description(self): """Optional[str]: description for the field.""" return self._properties.get("description") + @property + def precision(self): + """Optional[int]: Precision (number of digits) for the NUMERIC field.""" + return self._properties.get("precision") + + @property + def scale(self): + """Optional[int]: Scale (digits after decimal) for the NUMERIC field.""" + return self._properties.get("scale") + + @property + def max_length(self): + """Optional[int]: Maximum length for the STRING or BYTES field.""" + return self._properties.get("maxLength") + @property def fields(self): """Optional[tuple]: Subfields contained in this field. @@ -175,9 +244,9 @@ def to_api_repr(self) -> dict: # add this to the serialized representation. if self.field_type.upper() in _STRUCT_TYPES: answer["fields"] = [f.to_api_repr() for f in self.fields] - - # If this contains a policy tag definition, include that as well: - if self.policy_tags is not None: + else: + # Explicitly include policy tag definition (we must not do it for RECORD + # fields, because those are not leaf fields). answer["policyTags"] = self.policy_tags.to_api_repr() # Done; return the serialized dictionary. @@ -191,14 +260,29 @@ def _key(self): Returns: Tuple: The contents of this :class:`~google.cloud.bigquery.schema.SchemaField`. """ + field_type = self.field_type.upper() + if field_type == "STRING" or field_type == "BYTES": + if self.max_length is not None: + field_type = f"{field_type}({self.max_length})" + elif field_type.endswith("NUMERIC"): + if self.precision is not None: + if self.scale is not None: + field_type = f"{field_type}({self.precision}, {self.scale})" + else: + field_type = f"{field_type}({self.precision})" + + policy_tags = ( + () if self._policy_tags is None else tuple(sorted(self._policy_tags.names)) + ) + return ( self.name, - self.field_type.upper(), + field_type, # Mode is always str, if not given it defaults to a str value self.mode.upper(), # pytype: disable=attribute-error self.description, self._fields, - self._policy_tags, + policy_tags, ) def to_standard_sql(self) -> types.StandardSqlField: @@ -269,21 +353,7 @@ def _parse_schema_resource(info): Optional[Sequence[google.cloud.bigquery.schema.SchemaField`]: A list of parsed fields, or ``None`` if no "fields" key found. """ - if "fields" not in info: - return () - - schema = [] - for r_field in info["fields"]: - name = r_field["name"] - field_type = r_field["type"] - mode = r_field.get("mode", "NULLABLE") - description = r_field.get("description") - sub_fields = _parse_schema_resource(r_field) - policy_tags = PolicyTagList.from_api_repr(r_field.get("policyTags")) - schema.append( - SchemaField(name, field_type, mode, description, sub_fields, policy_tags) - ) - return schema + return [SchemaField.from_api_repr(f) for f in info.get("fields", ())] def _build_schema_resource(fields): diff --git a/google/cloud/bigquery/table.py b/google/cloud/bigquery/table.py index b91c91a39..609c0b57e 100644 --- a/google/cloud/bigquery/table.py +++ b/google/cloud/bigquery/table.py @@ -20,9 +20,8 @@ import datetime import functools import operator -import pytz import typing -from typing import Any, Dict, Iterable, Tuple +from typing import Any, Dict, Iterable, Iterator, Optional, Tuple import warnings try: @@ -30,6 +29,20 @@ except ImportError: # pragma: NO COVER pandas = None +try: + import geopandas +except ImportError: + geopandas = None +else: + _COORDINATE_REFERENCE_SYSTEM = "EPSG:4326" + +try: + import shapely.geos +except ImportError: + shapely = None +else: + _read_wkt = shapely.geos.WKTReader(shapely.geos.lgeos).read + try: import pyarrow except ImportError: # pragma: NO COVER @@ -41,6 +54,7 @@ import google.cloud._helpers from google.cloud.bigquery import _helpers from google.cloud.bigquery import _pandas_helpers +from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError from google.cloud.bigquery.schema import _build_schema_resource from google.cloud.bigquery.schema import _parse_schema_resource from google.cloud.bigquery.schema import _to_schema_fields @@ -52,6 +66,7 @@ # Unconditionally import optional dependencies again to tell pytype that # they are not None, avoiding false "no attribute" errors. import pandas + import geopandas import pyarrow from google.cloud import bigquery_storage @@ -60,6 +75,14 @@ "The pandas library is not installed, please install " "pandas to use the to_dataframe() function." ) +_NO_GEOPANDAS_ERROR = ( + "The geopandas library is not installed, please install " + "geopandas to use the to_geodataframe() function." +) +_NO_SHAPELY_ERROR = ( + "The shapely library is not installed, please install " + "shapely to use the geography_as_object option." +) _NO_PYARROW_ERROR = ( "The pyarrow library is not installed, please install " "pyarrow to use the to_arrow() function." @@ -254,9 +277,16 @@ def _key(self): return (self._project, self._dataset_id, self._table_id) def __eq__(self, other): - if not isinstance(other, TableReference): + if isinstance(other, (Table, TableListItem)): + return ( + self.project == other.project + and self.dataset_id == other.dataset_id + and self.table_id == other.table_id + ) + elif isinstance(other, TableReference): + return self._key() == other._key() + else: return NotImplemented - return self._key() == other._key() def __ne__(self, other): return not self == other @@ -320,6 +350,7 @@ class Table(object): "range_partitioning": "rangePartitioning", "time_partitioning": "timePartitioning", "schema": "schema", + "snapshot_definition": "snapshotDefinition", "streaming_buffer": "streamingBuffer", "self_link": "selfLink", "table_id": ["tableReference", "tableId"], @@ -909,6 +940,19 @@ def external_data_configuration(self, value): self._PROPERTY_TO_API_FIELD["external_data_configuration"] ] = api_repr + @property + def snapshot_definition(self) -> Optional["SnapshotDefinition"]: + """Information about the snapshot. This value is set via snapshot creation. + + See: https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#Table.FIELDS.snapshot_definition + """ + snapshot_info = self._properties.get( + self._PROPERTY_TO_API_FIELD["snapshot_definition"] + ) + if snapshot_info is not None: + snapshot_info = SnapshotDefinition(snapshot_info) + return snapshot_info + @classmethod def from_string(cls, full_table_id: str) -> "Table": """Construct a table from fully-qualified table ID. @@ -996,6 +1040,24 @@ def _build_resource(self, filter_fields): """Generate a resource for ``update``.""" return _helpers._build_resource_from_properties(self, filter_fields) + def __eq__(self, other): + if isinstance(other, Table): + return ( + self._properties["tableReference"] + == other._properties["tableReference"] + ) + elif isinstance(other, (TableReference, TableListItem)): + return ( + self.project == other.project + and self.dataset_id == other.dataset_id + and self.table_id == other.table_id + ) + else: + return NotImplemented + + def __hash__(self): + return hash((self.project, self.dataset_id, self.table_id)) + def __repr__(self): return "Table({})".format(repr(self.reference)) @@ -1214,6 +1276,19 @@ def to_api_repr(self) -> dict: """ return copy.deepcopy(self._properties) + def __eq__(self, other): + if isinstance(other, (Table, TableReference, TableListItem)): + return ( + self.project == other.project + and self.dataset_id == other.dataset_id + and self.table_id == other.table_id + ) + else: + return NotImplemented + + def __hash__(self): + return hash((self.project, self.dataset_id, self.table_id)) + def _row_from_mapping(mapping, schema): """Convert a mapping to a row tuple using the schema. @@ -1273,6 +1348,29 @@ def __init__(self, resource): ) +class SnapshotDefinition: + """Information about base table and snapshot time of the snapshot. + + See https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#snapshotdefinition + + Args: + resource: Snapshot definition representation returned from the API. + """ + + def __init__(self, resource: Dict[str, Any]): + self.base_table_reference = None + if "baseTableReference" in resource: + self.base_table_reference = TableReference.from_api_repr( + resource["baseTableReference"] + ) + + self.snapshot_time = None + if "snapshotTime" in resource: + self.snapshot_time = google.cloud._helpers._rfc3339_to_datetime( + resource["snapshotTime"] + ) + + class Row(object): """A BigQuery row. @@ -1414,7 +1512,9 @@ class RowIterator(HTTPIterator): """A class for iterating through HTTP/JSON API row list responses. Args: - client (google.cloud.bigquery.Client): The API client. + client (Optional[google.cloud.bigquery.Client]): + The API client instance. This should always be non-`None`, except for + subclasses that do not use it, namely the ``_EmptyRowIterator``. api_request (Callable[google.cloud._http.JSONConnection.api_request]): The function to use to make API requests. path (str): The method path to query for the list of items. @@ -1479,7 +1579,7 @@ def __init__( self._field_to_index = _helpers._field_to_index_mapping(schema) self._page_size = page_size self._preserve_order = False - self._project = client.project + self._project = client.project if client is not None else None self._schema = schema self._selected_fields = selected_fields self._table = table @@ -1512,11 +1612,17 @@ def _validate_bqstorage(self, bqstorage_client, create_bqstorage_client): return False if self.max_results is not None: - warnings.warn( - "Cannot use bqstorage_client if max_results is set, " - "reverting to fetching data with the REST endpoint.", - stacklevel=2, - ) + return False + + try: + from google.cloud import bigquery_storage # noqa: F401 + except ImportError: + return False + + try: + _helpers.BQ_STORAGE_VERSIONS.verify_version() + except LegacyBigQueryStorageError as exc: + warnings.warn(str(exc)) return False return True @@ -1553,6 +1659,25 @@ def total_rows(self): """int: The total number of rows in the table.""" return self._total_rows + def _maybe_warn_max_results( + self, bqstorage_client: Optional["bigquery_storage.BigQueryReadClient"], + ): + """Issue a warning if BQ Storage client is not ``None`` with ``max_results`` set. + + This helper method should be used directly in the relevant top-level public + methods, so that the warning is issued for the correct line in user code. + + Args: + bqstorage_client: + The BigQuery Storage client intended to use for downloading result rows. + """ + if bqstorage_client is not None and self.max_results is not None: + warnings.warn( + "Cannot use bqstorage_client if max_results is set, " + "reverting to fetching data with the REST endpoint.", + stacklevel=3, + ) + def _to_page_iterable( self, bqstorage_download, tabledata_list_download, bqstorage_client=None ): @@ -1633,7 +1758,7 @@ def to_arrow( This argument does nothing if ``bqstorage_client`` is supplied. - ..versionadded:: 1.24.0 + .. versionadded:: 1.24.0 Returns: pyarrow.Table @@ -1644,18 +1769,20 @@ def to_arrow( Raises: ValueError: If the :mod:`pyarrow` library cannot be imported. - ..versionadded:: 1.17.0 + .. versionadded:: 1.17.0 """ if pyarrow is None: raise ValueError(_NO_PYARROW_ERROR) + self._maybe_warn_max_results(bqstorage_client) + if not self._validate_bqstorage(bqstorage_client, create_bqstorage_client): create_bqstorage_client = False bqstorage_client = None owns_bqstorage_client = False if not bqstorage_client and create_bqstorage_client: - bqstorage_client = self.client._create_bqstorage_client() + bqstorage_client = self.client._ensure_bqstorage_client() owns_bqstorage_client = bqstorage_client is not None try: @@ -1724,7 +1851,7 @@ def to_dataframe_iterable( created by the server. If ``max_queue_size`` is :data:`None`, the queue size is infinite. - ..versionadded:: 2.14.0 + .. versionadded:: 2.14.0 Returns: pandas.DataFrame: @@ -1739,6 +1866,8 @@ def to_dataframe_iterable( if dtypes is None: dtypes = {} + self._maybe_warn_max_results(bqstorage_client) + column_names = [field.name for field in self._schema] bqstorage_download = functools.partial( _pandas_helpers.download_dataframe_bqstorage, @@ -1772,6 +1901,7 @@ def to_dataframe( progress_bar_type: str = None, create_bqstorage_client: bool = True, date_as_object: bool = True, + geography_as_object: bool = False, ) -> "pandas.DataFrame": """Create a pandas DataFrame by loading all pages of a query. @@ -1810,7 +1940,7 @@ def to_dataframe( Use the :func:`tqdm.tqdm_gui` function to display a progress bar as a graphical dialog box. - ..versionadded:: 1.11.0 + .. versionadded:: 1.11.0 create_bqstorage_client (Optional[bool]): If ``True`` (default), create a BigQuery Storage API client using the default API settings. The BigQuery Storage API @@ -1819,13 +1949,20 @@ def to_dataframe( This argument does nothing if ``bqstorage_client`` is supplied. - ..versionadded:: 1.24.0 + .. versionadded:: 1.24.0 date_as_object (Optional[bool]): If ``True`` (default), cast dates to objects. If ``False``, convert to datetime64[ns] dtype. - ..versionadded:: 1.26.0 + .. versionadded:: 1.26.0 + + geography_as_object (Optional[bool]): + If ``True``, convert GEOGRAPHY data to :mod:`shapely` + geometry objects. If ``False`` (default), don't cast + geography data to :mod:`shapely` geometry objects. + + .. versionadded:: 2.24.0 Returns: pandas.DataFrame: @@ -1835,16 +1972,23 @@ def to_dataframe( Raises: ValueError: - If the :mod:`pandas` library cannot be imported, or the - :mod:`google.cloud.bigquery_storage_v1` module is - required but cannot be imported. + If the :mod:`pandas` library cannot be imported, or + the :mod:`google.cloud.bigquery_storage_v1` module is + required but cannot be imported. Also if + `geography_as_object` is `True`, but the + :mod:`shapely` library cannot be imported. """ if pandas is None: raise ValueError(_NO_PANDAS_ERROR) + if geography_as_object and shapely is None: + raise ValueError(_NO_SHAPELY_ERROR) + if dtypes is None: dtypes = {} + self._maybe_warn_max_results(bqstorage_client) + if not self._validate_bqstorage(bqstorage_client, create_bqstorage_client): create_bqstorage_client = False bqstorage_client = None @@ -1860,7 +2004,7 @@ def to_dataframe( # Pandas, we set the timestamp_as_object parameter to True, if necessary. types_to_check = { pyarrow.timestamp("us"), - pyarrow.timestamp("us", tz=pytz.UTC), + pyarrow.timestamp("us", tz=datetime.timezone.utc), } for column in record_batch: @@ -1880,10 +2024,138 @@ def to_dataframe( for column in dtypes: df[column] = pandas.Series(df[column], dtype=dtypes[column]) + if geography_as_object: + for field in self.schema: + if field.field_type.upper() == "GEOGRAPHY": + df[field.name] = df[field.name].dropna().apply(_read_wkt) + return df + # If changing the signature of this method, make sure to apply the same + # changes to job.QueryJob.to_geodataframe() + def to_geodataframe( + self, + bqstorage_client: "bigquery_storage.BigQueryReadClient" = None, + dtypes: Dict[str, Any] = None, + progress_bar_type: str = None, + create_bqstorage_client: bool = True, + date_as_object: bool = True, + geography_column: Optional[str] = None, + ) -> "geopandas.GeoDataFrame": + """Create a GeoPandas GeoDataFrame by loading all pages of a query. + + Args: + bqstorage_client (Optional[google.cloud.bigquery_storage_v1.BigQueryReadClient]): + A BigQuery Storage API client. If supplied, use the faster + BigQuery Storage API to fetch rows from BigQuery. + + This method requires the ``pyarrow`` and + ``google-cloud-bigquery-storage`` libraries. -class _EmptyRowIterator(object): + This method only exposes a subset of the capabilities of the + BigQuery Storage API. For full access to all features + (projections, filters, snapshots) use the Storage API directly. + + dtypes (Optional[Map[str, Union[str, pandas.Series.dtype]]]): + A dictionary of column names pandas ``dtype``s. The provided + ``dtype`` is used when constructing the series for the column + specified. Otherwise, the default pandas behavior is used. + progress_bar_type (Optional[str]): + If set, use the `tqdm `_ library to + display a progress bar while the data downloads. Install the + ``tqdm`` package to use this feature. + + Possible values of ``progress_bar_type`` include: + + ``None`` + No progress bar. + ``'tqdm'`` + Use the :func:`tqdm.tqdm` function to print a progress bar + to :data:`sys.stderr`. + ``'tqdm_notebook'`` + Use the :func:`tqdm.tqdm_notebook` function to display a + progress bar as a Jupyter notebook widget. + ``'tqdm_gui'`` + Use the :func:`tqdm.tqdm_gui` function to display a + progress bar as a graphical dialog box. + + create_bqstorage_client (Optional[bool]): + If ``True`` (default), create a BigQuery Storage API client + using the default API settings. The BigQuery Storage API + is a faster way to fetch rows from BigQuery. See the + ``bqstorage_client`` parameter for more information. + + This argument does nothing if ``bqstorage_client`` is supplied. + + date_as_object (Optional[bool]): + If ``True`` (default), cast dates to objects. If ``False``, convert + to datetime64[ns] dtype. + + geography_column (Optional[str]): + If there are more than one GEOGRAPHY column, + identifies which one to use to construct a geopandas + GeoDataFrame. This option can be ommitted if there's + only one GEOGRAPHY column. + + Returns: + geopandas.GeoDataFrame: + A :class:`geopandas.GeoDataFrame` populated with row + data and column headers from the query results. The + column headers are derived from the destination + table's schema. + + Raises: + ValueError: + If the :mod:`geopandas` library cannot be imported, or the + :mod:`google.cloud.bigquery_storage_v1` module is + required but cannot be imported. + + .. versionadded:: 2.24.0 + """ + if geopandas is None: + raise ValueError(_NO_GEOPANDAS_ERROR) + + geography_columns = set( + field.name + for field in self.schema + if field.field_type.upper() == "GEOGRAPHY" + ) + if not geography_columns: + raise TypeError( + "There must be at least one GEOGRAPHY column" + " to create a GeoDataFrame" + ) + + if geography_column: + if geography_column not in geography_columns: + raise ValueError( + f"The given geography column, {geography_column}, doesn't name" + f" a GEOGRAPHY column in the result." + ) + elif len(geography_columns) == 1: + [geography_column] = geography_columns + else: + raise ValueError( + "There is more than one GEOGRAPHY column in the result. " + "The geography_column argument must be used to specify which " + "one to use to create a GeoDataFrame" + ) + + df = self.to_dataframe( + bqstorage_client, + dtypes, + progress_bar_type, + create_bqstorage_client, + date_as_object, + geography_as_object=True, + ) + + return geopandas.GeoDataFrame( + df, crs=_COORDINATE_REFERENCE_SYSTEM, geometry=geography_column + ) + + +class _EmptyRowIterator(RowIterator): """An empty row iterator. This class prevents API requests when there are no rows to fetch or rows @@ -1895,6 +2167,18 @@ class _EmptyRowIterator(object): pages = () total_rows = 0 + def __init__( + self, client=None, api_request=None, path=None, schema=(), *args, **kwargs + ): + super().__init__( + client=client, + api_request=api_request, + path=path, + schema=schema, + *args, + **kwargs, + ) + def to_arrow( self, progress_bar_type=None, @@ -1922,6 +2206,7 @@ def to_dataframe( progress_bar_type=None, create_bqstorage_client=True, date_as_object=True, + geography_as_object=False, ) -> "pandas.DataFrame": """Create an empty dataframe. @@ -1939,6 +2224,62 @@ def to_dataframe( raise ValueError(_NO_PANDAS_ERROR) return pandas.DataFrame() + def to_geodataframe( + self, + bqstorage_client=None, + dtypes=None, + progress_bar_type=None, + create_bqstorage_client=True, + date_as_object=True, + geography_column: Optional[str] = None, + ) -> "pandas.DataFrame": + """Create an empty dataframe. + + Args: + bqstorage_client (Any): Ignored. Added for compatibility with RowIterator. + dtypes (Any): Ignored. Added for compatibility with RowIterator. + progress_bar_type (Any): Ignored. Added for compatibility with RowIterator. + create_bqstorage_client (bool): Ignored. Added for compatibility with RowIterator. + date_as_object (bool): Ignored. Added for compatibility with RowIterator. + + Returns: + pandas.DataFrame: An empty :class:`~pandas.DataFrame`. + """ + if geopandas is None: + raise ValueError(_NO_GEOPANDAS_ERROR) + return geopandas.GeoDataFrame(crs=_COORDINATE_REFERENCE_SYSTEM) + + def to_dataframe_iterable( + self, + bqstorage_client: Optional["bigquery_storage.BigQueryReadClient"] = None, + dtypes: Optional[Dict[str, Any]] = None, + max_queue_size: Optional[int] = None, + ) -> Iterator["pandas.DataFrame"]: + """Create an iterable of pandas DataFrames, to process the table as a stream. + + .. versionadded:: 2.21.0 + + Args: + bqstorage_client: + Ignored. Added for compatibility with RowIterator. + + dtypes (Optional[Map[str, Union[str, pandas.Series.dtype]]]): + Ignored. Added for compatibility with RowIterator. + + max_queue_size: + Ignored. Added for compatibility with RowIterator. + + Returns: + An iterator yielding a single empty :class:`~pandas.DataFrame`. + + Raises: + ValueError: + If the :mod:`pandas` library cannot be imported. + """ + if pandas is None: + raise ValueError(_NO_PANDAS_ERROR) + return iter((pandas.DataFrame(),)) + def __iter__(self): return iter(()) diff --git a/google/cloud/bigquery/version.py b/google/cloud/bigquery/version.py index 61e0c0a83..21cbec9fe 100644 --- a/google/cloud/bigquery/version.py +++ b/google/cloud/bigquery/version.py @@ -12,4 +12,4 @@ # See the License for the specific language governing permissions and # limitations under the License. -__version__ = "2.16.1" +__version__ = "2.25.1" diff --git a/google/cloud/bigquery_v2/__init__.py b/google/cloud/bigquery_v2/__init__.py index ebcc26bef..f9957efa9 100644 --- a/google/cloud/bigquery_v2/__init__.py +++ b/google/cloud/bigquery_v2/__init__.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -27,9 +26,9 @@ from .types.standard_sql import StandardSqlDataType from .types.standard_sql import StandardSqlField from .types.standard_sql import StandardSqlStructType +from .types.standard_sql import StandardSqlTableType from .types.table_reference import TableReference - __all__ = ( "DeleteModelRequest", "EncryptionConfiguration", @@ -42,5 +41,6 @@ "StandardSqlDataType", "StandardSqlField", "StandardSqlStructType", + "StandardSqlTableType", "TableReference", ) diff --git a/google/cloud/bigquery_v2/gapic_metadata.json b/google/cloud/bigquery_v2/gapic_metadata.json new file mode 100644 index 000000000..3251a2630 --- /dev/null +++ b/google/cloud/bigquery_v2/gapic_metadata.json @@ -0,0 +1,63 @@ + { + "comment": "This file maps proto services/RPCs to the corresponding library clients/methods", + "language": "python", + "libraryPackage": "google.cloud.bigquery_v2", + "protoPackage": "google.cloud.bigquery.v2", + "schema": "1.0", + "services": { + "ModelService": { + "clients": { + "grpc": { + "libraryClient": "ModelServiceClient", + "rpcs": { + "DeleteModel": { + "methods": [ + "delete_model" + ] + }, + "GetModel": { + "methods": [ + "get_model" + ] + }, + "ListModels": { + "methods": [ + "list_models" + ] + }, + "PatchModel": { + "methods": [ + "patch_model" + ] + } + } + }, + "grpc-async": { + "libraryClient": "ModelServiceAsyncClient", + "rpcs": { + "DeleteModel": { + "methods": [ + "delete_model" + ] + }, + "GetModel": { + "methods": [ + "get_model" + ] + }, + "ListModels": { + "methods": [ + "list_models" + ] + }, + "PatchModel": { + "methods": [ + "patch_model" + ] + } + } + } + } + } + } +} diff --git a/google/cloud/bigquery_v2/proto/encryption_config.proto b/google/cloud/bigquery_v2/proto/encryption_config.proto deleted file mode 100644 index 1c0512a17..000000000 --- a/google/cloud/bigquery_v2/proto/encryption_config.proto +++ /dev/null @@ -1,32 +0,0 @@ -// Copyright 2020 Google LLC -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -syntax = "proto3"; - -package google.cloud.bigquery.v2; - -import "google/api/field_behavior.proto"; -import "google/protobuf/wrappers.proto"; -import "google/api/annotations.proto"; - -option go_package = "google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery"; -option java_outer_classname = "EncryptionConfigProto"; -option java_package = "com.google.cloud.bigquery.v2"; - -message EncryptionConfiguration { - // Optional. Describes the Cloud KMS encryption key that will be used to - // protect destination BigQuery table. The BigQuery Service Account associated - // with your project requires access to this encryption key. - google.protobuf.StringValue kms_key_name = 1 [(google.api.field_behavior) = OPTIONAL]; -} diff --git a/google/cloud/bigquery_v2/proto/encryption_config_pb2.py b/google/cloud/bigquery_v2/proto/encryption_config_pb2.py deleted file mode 100644 index 5ae21ea6f..000000000 --- a/google/cloud/bigquery_v2/proto/encryption_config_pb2.py +++ /dev/null @@ -1,104 +0,0 @@ -# -*- coding: utf-8 -*- -# Generated by the protocol buffer compiler. DO NOT EDIT! -# source: google/cloud/bigquery_v2/proto/encryption_config.proto -"""Generated protocol buffer code.""" -from google.protobuf import descriptor as _descriptor -from google.protobuf import message as _message -from google.protobuf import reflection as _reflection -from google.protobuf import symbol_database as _symbol_database - -# @@protoc_insertion_point(imports) - -_sym_db = _symbol_database.Default() - - -from google.api import field_behavior_pb2 as google_dot_api_dot_field__behavior__pb2 -from google.protobuf import wrappers_pb2 as google_dot_protobuf_dot_wrappers__pb2 -from google.api import annotations_pb2 as google_dot_api_dot_annotations__pb2 - - -DESCRIPTOR = _descriptor.FileDescriptor( - name="google/cloud/bigquery_v2/proto/encryption_config.proto", - package="google.cloud.bigquery.v2", - syntax="proto3", - serialized_options=b"\n\034com.google.cloud.bigquery.v2B\025EncryptionConfigProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery", - create_key=_descriptor._internal_create_key, - serialized_pb=b'\n6google/cloud/bigquery_v2/proto/encryption_config.proto\x12\x18google.cloud.bigquery.v2\x1a\x1fgoogle/api/field_behavior.proto\x1a\x1egoogle/protobuf/wrappers.proto\x1a\x1cgoogle/api/annotations.proto"R\n\x17\x45ncryptionConfiguration\x12\x37\n\x0ckms_key_name\x18\x01 \x01(\x0b\x32\x1c.google.protobuf.StringValueB\x03\xe0\x41\x01\x42w\n\x1c\x63om.google.cloud.bigquery.v2B\x15\x45ncryptionConfigProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigqueryb\x06proto3', - dependencies=[ - google_dot_api_dot_field__behavior__pb2.DESCRIPTOR, - google_dot_protobuf_dot_wrappers__pb2.DESCRIPTOR, - google_dot_api_dot_annotations__pb2.DESCRIPTOR, - ], -) - - -_ENCRYPTIONCONFIGURATION = _descriptor.Descriptor( - name="EncryptionConfiguration", - full_name="google.cloud.bigquery.v2.EncryptionConfiguration", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="kms_key_name", - full_name="google.cloud.bigquery.v2.EncryptionConfiguration.kms_key_name", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\001", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=179, - serialized_end=261, -) - -_ENCRYPTIONCONFIGURATION.fields_by_name[ - "kms_key_name" -].message_type = google_dot_protobuf_dot_wrappers__pb2._STRINGVALUE -DESCRIPTOR.message_types_by_name["EncryptionConfiguration"] = _ENCRYPTIONCONFIGURATION -_sym_db.RegisterFileDescriptor(DESCRIPTOR) - -EncryptionConfiguration = _reflection.GeneratedProtocolMessageType( - "EncryptionConfiguration", - (_message.Message,), - { - "DESCRIPTOR": _ENCRYPTIONCONFIGURATION, - "__module__": "google.cloud.bigquery_v2.proto.encryption_config_pb2", - "__doc__": """Encryption configuration. - - Attributes: - kms_key_name: - Optional. Describes the Cloud KMS encryption key that will be - used to protect destination BigQuery table. The BigQuery - Service Account associated with your project requires access - to this encryption key. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.EncryptionConfiguration) - }, -) -_sym_db.RegisterMessage(EncryptionConfiguration) - - -DESCRIPTOR._options = None -_ENCRYPTIONCONFIGURATION.fields_by_name["kms_key_name"]._options = None -# @@protoc_insertion_point(module_scope) diff --git a/google/cloud/bigquery_v2/proto/location_metadata.proto b/google/cloud/bigquery_v2/proto/location_metadata.proto deleted file mode 100644 index 95a3133c5..000000000 --- a/google/cloud/bigquery_v2/proto/location_metadata.proto +++ /dev/null @@ -1,34 +0,0 @@ -// Copyright 2019 Google LLC. -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. -// - -syntax = "proto3"; - -package google.cloud.bigquery.v2; - -import "google/api/annotations.proto"; - -option go_package = "google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery"; -option java_outer_classname = "LocationMetadataProto"; -option java_package = "com.google.cloud.bigquery.v2"; - - -// BigQuery-specific metadata about a location. This will be set on -// google.cloud.location.Location.metadata in Cloud Location API -// responses. -message LocationMetadata { - // The legacy BigQuery location ID, e.g. “EU” for the “europe” location. - // This is for any API consumers that need the legacy “US” and “EU” locations. - string legacy_location_id = 1; -} diff --git a/google/cloud/bigquery_v2/proto/model.proto b/google/cloud/bigquery_v2/proto/model.proto deleted file mode 100644 index 2d400dddd..000000000 --- a/google/cloud/bigquery_v2/proto/model.proto +++ /dev/null @@ -1,1208 +0,0 @@ -// Copyright 2020 Google LLC -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -syntax = "proto3"; - -package google.cloud.bigquery.v2; - -import "google/api/client.proto"; -import "google/api/field_behavior.proto"; -import "google/cloud/bigquery/v2/encryption_config.proto"; -import "google/cloud/bigquery/v2/model_reference.proto"; -import "google/cloud/bigquery/v2/standard_sql.proto"; -import "google/cloud/bigquery/v2/table_reference.proto"; -import "google/protobuf/empty.proto"; -import "google/protobuf/timestamp.proto"; -import "google/protobuf/wrappers.proto"; -import "google/api/annotations.proto"; - -option go_package = "google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery"; -option java_outer_classname = "ModelProto"; -option java_package = "com.google.cloud.bigquery.v2"; - -service ModelService { - option (google.api.default_host) = "bigquery.googleapis.com"; - option (google.api.oauth_scopes) = - "https://www.googleapis.com/auth/bigquery," - "https://www.googleapis.com/auth/bigquery.readonly," - "https://www.googleapis.com/auth/cloud-platform," - "https://www.googleapis.com/auth/cloud-platform.read-only"; - - // Gets the specified model resource by model ID. - rpc GetModel(GetModelRequest) returns (Model) { - option (google.api.method_signature) = "project_id,dataset_id,model_id"; - } - - // Lists all models in the specified dataset. Requires the READER dataset - // role. - rpc ListModels(ListModelsRequest) returns (ListModelsResponse) { - option (google.api.method_signature) = "project_id,dataset_id,max_results"; - } - - // Patch specific fields in the specified model. - rpc PatchModel(PatchModelRequest) returns (Model) { - option (google.api.method_signature) = "project_id,dataset_id,model_id,model"; - } - - // Deletes the model specified by modelId from the dataset. - rpc DeleteModel(DeleteModelRequest) returns (google.protobuf.Empty) { - option (google.api.method_signature) = "project_id,dataset_id,model_id"; - } -} - -message Model { - message SeasonalPeriod { - enum SeasonalPeriodType { - SEASONAL_PERIOD_TYPE_UNSPECIFIED = 0; - - // No seasonality - NO_SEASONALITY = 1; - - // Daily period, 24 hours. - DAILY = 2; - - // Weekly period, 7 days. - WEEKLY = 3; - - // Monthly period, 30 days or irregular. - MONTHLY = 4; - - // Quarterly period, 90 days or irregular. - QUARTERLY = 5; - - // Yearly period, 365 days or irregular. - YEARLY = 6; - } - - - } - - message KmeansEnums { - // Indicates the method used to initialize the centroids for KMeans - // clustering algorithm. - enum KmeansInitializationMethod { - KMEANS_INITIALIZATION_METHOD_UNSPECIFIED = 0; - - // Initializes the centroids randomly. - RANDOM = 1; - - // Initializes the centroids using data specified in - // kmeans_initialization_column. - CUSTOM = 2; - - // Initializes with kmeans++. - KMEANS_PLUS_PLUS = 3; - } - - - } - - // Evaluation metrics for regression and explicit feedback type matrix - // factorization models. - message RegressionMetrics { - // Mean absolute error. - google.protobuf.DoubleValue mean_absolute_error = 1; - - // Mean squared error. - google.protobuf.DoubleValue mean_squared_error = 2; - - // Mean squared log error. - google.protobuf.DoubleValue mean_squared_log_error = 3; - - // Median absolute error. - google.protobuf.DoubleValue median_absolute_error = 4; - - // R^2 score. - google.protobuf.DoubleValue r_squared = 5; - } - - // Aggregate metrics for classification/classifier models. For multi-class - // models, the metrics are either macro-averaged or micro-averaged. When - // macro-averaged, the metrics are calculated for each label and then an - // unweighted average is taken of those values. When micro-averaged, the - // metric is calculated globally by counting the total number of correctly - // predicted rows. - message AggregateClassificationMetrics { - // Precision is the fraction of actual positive predictions that had - // positive actual labels. For multiclass this is a macro-averaged - // metric treating each class as a binary classifier. - google.protobuf.DoubleValue precision = 1; - - // Recall is the fraction of actual positive labels that were given a - // positive prediction. For multiclass this is a macro-averaged metric. - google.protobuf.DoubleValue recall = 2; - - // Accuracy is the fraction of predictions given the correct label. For - // multiclass this is a micro-averaged metric. - google.protobuf.DoubleValue accuracy = 3; - - // Threshold at which the metrics are computed. For binary - // classification models this is the positive class threshold. - // For multi-class classfication models this is the confidence - // threshold. - google.protobuf.DoubleValue threshold = 4; - - // The F1 score is an average of recall and precision. For multiclass - // this is a macro-averaged metric. - google.protobuf.DoubleValue f1_score = 5; - - // Logarithmic Loss. For multiclass this is a macro-averaged metric. - google.protobuf.DoubleValue log_loss = 6; - - // Area Under a ROC Curve. For multiclass this is a macro-averaged - // metric. - google.protobuf.DoubleValue roc_auc = 7; - } - - // Evaluation metrics for binary classification/classifier models. - message BinaryClassificationMetrics { - // Confusion matrix for binary classification models. - message BinaryConfusionMatrix { - // Threshold value used when computing each of the following metric. - google.protobuf.DoubleValue positive_class_threshold = 1; - - // Number of true samples predicted as true. - google.protobuf.Int64Value true_positives = 2; - - // Number of false samples predicted as true. - google.protobuf.Int64Value false_positives = 3; - - // Number of true samples predicted as false. - google.protobuf.Int64Value true_negatives = 4; - - // Number of false samples predicted as false. - google.protobuf.Int64Value false_negatives = 5; - - // The fraction of actual positive predictions that had positive actual - // labels. - google.protobuf.DoubleValue precision = 6; - - // The fraction of actual positive labels that were given a positive - // prediction. - google.protobuf.DoubleValue recall = 7; - - // The equally weighted average of recall and precision. - google.protobuf.DoubleValue f1_score = 8; - - // The fraction of predictions given the correct label. - google.protobuf.DoubleValue accuracy = 9; - } - - // Aggregate classification metrics. - AggregateClassificationMetrics aggregate_classification_metrics = 1; - - // Binary confusion matrix at multiple thresholds. - repeated BinaryConfusionMatrix binary_confusion_matrix_list = 2; - - // Label representing the positive class. - string positive_label = 3; - - // Label representing the negative class. - string negative_label = 4; - } - - // Evaluation metrics for multi-class classification/classifier models. - message MultiClassClassificationMetrics { - // Confusion matrix for multi-class classification models. - message ConfusionMatrix { - // A single entry in the confusion matrix. - message Entry { - // The predicted label. For confidence_threshold > 0, we will - // also add an entry indicating the number of items under the - // confidence threshold. - string predicted_label = 1; - - // Number of items being predicted as this label. - google.protobuf.Int64Value item_count = 2; - } - - // A single row in the confusion matrix. - message Row { - // The original label of this row. - string actual_label = 1; - - // Info describing predicted label distribution. - repeated Entry entries = 2; - } - - // Confidence threshold used when computing the entries of the - // confusion matrix. - google.protobuf.DoubleValue confidence_threshold = 1; - - // One row per actual label. - repeated Row rows = 2; - } - - // Aggregate classification metrics. - AggregateClassificationMetrics aggregate_classification_metrics = 1; - - // Confusion matrix at different thresholds. - repeated ConfusionMatrix confusion_matrix_list = 2; - } - - // Evaluation metrics for clustering models. - message ClusteringMetrics { - // Message containing the information about one cluster. - message Cluster { - // Representative value of a single feature within the cluster. - message FeatureValue { - // Representative value of a categorical feature. - message CategoricalValue { - // Represents the count of a single category within the cluster. - message CategoryCount { - // The name of category. - string category = 1; - - // The count of training samples matching the category within the - // cluster. - google.protobuf.Int64Value count = 2; - } - - // Counts of all categories for the categorical feature. If there are - // more than ten categories, we return top ten (by count) and return - // one more CategoryCount with category "_OTHER_" and count as - // aggregate counts of remaining categories. - repeated CategoryCount category_counts = 1; - } - - // The feature column name. - string feature_column = 1; - - oneof value { - // The numerical feature value. This is the centroid value for this - // feature. - google.protobuf.DoubleValue numerical_value = 2; - - // The categorical feature value. - CategoricalValue categorical_value = 3; - } - } - - // Centroid id. - int64 centroid_id = 1; - - // Values of highly variant features for this cluster. - repeated FeatureValue feature_values = 2; - - // Count of training data rows that were assigned to this cluster. - google.protobuf.Int64Value count = 3; - } - - // Davies-Bouldin index. - google.protobuf.DoubleValue davies_bouldin_index = 1; - - // Mean of squared distances between each sample to its cluster centroid. - google.protobuf.DoubleValue mean_squared_distance = 2; - - // [Beta] Information for all clusters. - repeated Cluster clusters = 3; - } - - // Evaluation metrics used by weighted-ALS models specified by - // feedback_type=implicit. - message RankingMetrics { - // Calculates a precision per user for all the items by ranking them and - // then averages all the precisions across all the users. - google.protobuf.DoubleValue mean_average_precision = 1; - - // Similar to the mean squared error computed in regression and explicit - // recommendation models except instead of computing the rating directly, - // the output from evaluate is computed against a preference which is 1 or 0 - // depending on if the rating exists or not. - google.protobuf.DoubleValue mean_squared_error = 2; - - // A metric to determine the goodness of a ranking calculated from the - // predicted confidence by comparing it to an ideal rank measured by the - // original ratings. - google.protobuf.DoubleValue normalized_discounted_cumulative_gain = 3; - - // Determines the goodness of a ranking by computing the percentile rank - // from the predicted confidence and dividing it by the original rank. - google.protobuf.DoubleValue average_rank = 4; - } - - // Model evaluation metrics for ARIMA forecasting models. - message ArimaForecastingMetrics { - // Model evaluation metrics for a single ARIMA forecasting model. - message ArimaSingleModelForecastingMetrics { - // Non-seasonal order. - ArimaOrder non_seasonal_order = 1; - - // Arima fitting metrics. - ArimaFittingMetrics arima_fitting_metrics = 2; - - // Is arima model fitted with drift or not. It is always false when d - // is not 1. - bool has_drift = 3; - - // The id to indicate different time series. - string time_series_id = 4; - - // Seasonal periods. Repeated because multiple periods are supported - // for one time series. - repeated SeasonalPeriod.SeasonalPeriodType seasonal_periods = 5; - } - - // Non-seasonal order. - repeated ArimaOrder non_seasonal_order = 1; - - // Arima model fitting metrics. - repeated ArimaFittingMetrics arima_fitting_metrics = 2; - - // Seasonal periods. Repeated because multiple periods are supported for one - // time series. - repeated SeasonalPeriod.SeasonalPeriodType seasonal_periods = 3; - - // Whether Arima model fitted with drift or not. It is always false when d - // is not 1. - repeated bool has_drift = 4; - - // Id to differentiate different time series for the large-scale case. - repeated string time_series_id = 5; - - // Repeated as there can be many metric sets (one for each model) in - // auto-arima and the large-scale case. - repeated ArimaSingleModelForecastingMetrics arima_single_model_forecasting_metrics = 6; - } - - // Evaluation metrics of a model. These are either computed on all training - // data or just the eval data based on whether eval data was used during - // training. These are not present for imported models. - message EvaluationMetrics { - oneof metrics { - // Populated for regression models and explicit feedback type matrix - // factorization models. - RegressionMetrics regression_metrics = 1; - - // Populated for binary classification/classifier models. - BinaryClassificationMetrics binary_classification_metrics = 2; - - // Populated for multi-class classification/classifier models. - MultiClassClassificationMetrics multi_class_classification_metrics = 3; - - // Populated for clustering models. - ClusteringMetrics clustering_metrics = 4; - - // Populated for implicit feedback type matrix factorization models. - RankingMetrics ranking_metrics = 5; - - // Populated for ARIMA models. - ArimaForecastingMetrics arima_forecasting_metrics = 6; - } - } - - // Data split result. This contains references to the training and evaluation - // data tables that were used to train the model. - message DataSplitResult { - // Table reference of the training data after split. - TableReference training_table = 1; - - // Table reference of the evaluation data after split. - TableReference evaluation_table = 2; - } - - // Arima order, can be used for both non-seasonal and seasonal parts. - message ArimaOrder { - // Order of the autoregressive part. - int64 p = 1; - - // Order of the differencing part. - int64 d = 2; - - // Order of the moving-average part. - int64 q = 3; - } - - // ARIMA model fitting metrics. - message ArimaFittingMetrics { - // Log-likelihood. - double log_likelihood = 1; - - // AIC. - double aic = 2; - - // Variance. - double variance = 3; - } - - // Global explanations containing the top most important features - // after training. - message GlobalExplanation { - // Explanation for a single feature. - message Explanation { - // Full name of the feature. For non-numerical features, will be - // formatted like .. Overall size of - // feature name will always be truncated to first 120 characters. - string feature_name = 1; - - // Attribution of feature. - google.protobuf.DoubleValue attribution = 2; - } - - // A list of the top global explanations. Sorted by absolute value of - // attribution in descending order. - repeated Explanation explanations = 1; - - // Class label for this set of global explanations. Will be empty/null for - // binary logistic and linear regression models. Sorted alphabetically in - // descending order. - string class_label = 2; - } - - // Information about a single training query run for the model. - message TrainingRun { - message TrainingOptions { - // The maximum number of iterations in training. Used only for iterative - // training algorithms. - int64 max_iterations = 1; - - // Type of loss function used during training run. - LossType loss_type = 2; - - // Learning rate in training. Used only for iterative training algorithms. - double learn_rate = 3; - - // L1 regularization coefficient. - google.protobuf.DoubleValue l1_regularization = 4; - - // L2 regularization coefficient. - google.protobuf.DoubleValue l2_regularization = 5; - - // When early_stop is true, stops training when accuracy improvement is - // less than 'min_relative_progress'. Used only for iterative training - // algorithms. - google.protobuf.DoubleValue min_relative_progress = 6; - - // Whether to train a model from the last checkpoint. - google.protobuf.BoolValue warm_start = 7; - - // Whether to stop early when the loss doesn't improve significantly - // any more (compared to min_relative_progress). Used only for iterative - // training algorithms. - google.protobuf.BoolValue early_stop = 8; - - // Name of input label columns in training data. - repeated string input_label_columns = 9; - - // The data split type for training and evaluation, e.g. RANDOM. - DataSplitMethod data_split_method = 10; - - // The fraction of evaluation data over the whole input data. The rest - // of data will be used as training data. The format should be double. - // Accurate to two decimal places. - // Default value is 0.2. - double data_split_eval_fraction = 11; - - // The column to split data with. This column won't be used as a - // feature. - // 1. When data_split_method is CUSTOM, the corresponding column should - // be boolean. The rows with true value tag are eval data, and the false - // are training data. - // 2. When data_split_method is SEQ, the first DATA_SPLIT_EVAL_FRACTION - // rows (from smallest to largest) in the corresponding column are used - // as training data, and the rest are eval data. It respects the order - // in Orderable data types: - // https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#data-type-properties - string data_split_column = 12; - - // The strategy to determine learn rate for the current iteration. - LearnRateStrategy learn_rate_strategy = 13; - - // Specifies the initial learning rate for the line search learn rate - // strategy. - double initial_learn_rate = 16; - - // Weights associated with each label class, for rebalancing the - // training data. Only applicable for classification models. - map label_class_weights = 17; - - // User column specified for matrix factorization models. - string user_column = 18; - - // Item column specified for matrix factorization models. - string item_column = 19; - - // Distance type for clustering models. - DistanceType distance_type = 20; - - // Number of clusters for clustering models. - int64 num_clusters = 21; - - // [Beta] Google Cloud Storage URI from which the model was imported. Only - // applicable for imported models. - string model_uri = 22; - - // Optimization strategy for training linear regression models. - OptimizationStrategy optimization_strategy = 23; - - // Hidden units for dnn models. - repeated int64 hidden_units = 24; - - // Batch size for dnn models. - int64 batch_size = 25; - - // Dropout probability for dnn models. - google.protobuf.DoubleValue dropout = 26; - - // Maximum depth of a tree for boosted tree models. - int64 max_tree_depth = 27; - - // Subsample fraction of the training data to grow tree to prevent - // overfitting for boosted tree models. - double subsample = 28; - - // Minimum split loss for boosted tree models. - google.protobuf.DoubleValue min_split_loss = 29; - - // Num factors specified for matrix factorization models. - int64 num_factors = 30; - - // Feedback type that specifies which algorithm to run for matrix - // factorization. - FeedbackType feedback_type = 31; - - // Hyperparameter for matrix factoration when implicit feedback type is - // specified. - google.protobuf.DoubleValue wals_alpha = 32; - - // The method used to initialize the centroids for kmeans algorithm. - KmeansEnums.KmeansInitializationMethod kmeans_initialization_method = 33; - - // The column used to provide the initial centroids for kmeans algorithm - // when kmeans_initialization_method is CUSTOM. - string kmeans_initialization_column = 34; - - // Column to be designated as time series timestamp for ARIMA model. - string time_series_timestamp_column = 35; - - // Column to be designated as time series data for ARIMA model. - string time_series_data_column = 36; - - // Whether to enable auto ARIMA or not. - bool auto_arima = 37; - - // A specification of the non-seasonal part of the ARIMA model: the three - // components (p, d, q) are the AR order, the degree of differencing, and - // the MA order. - ArimaOrder non_seasonal_order = 38; - - // The data frequency of a time series. - DataFrequency data_frequency = 39; - - // Include drift when fitting an ARIMA model. - bool include_drift = 41; - - // The geographical region based on which the holidays are considered in - // time series modeling. If a valid value is specified, then holiday - // effects modeling is enabled. - HolidayRegion holiday_region = 42; - - // The id column that will be used to indicate different time series to - // forecast in parallel. - string time_series_id_column = 43; - - // The number of periods ahead that need to be forecasted. - int64 horizon = 44; - - // Whether to preserve the input structs in output feature names. - // Suppose there is a struct A with field b. - // When false (default), the output feature name is A_b. - // When true, the output feature name is A.b. - bool preserve_input_structs = 45; - - // The max value of non-seasonal p and q. - int64 auto_arima_max_order = 46; - } - - // Information about a single iteration of the training run. - message IterationResult { - // Information about a single cluster for clustering model. - message ClusterInfo { - // Centroid id. - int64 centroid_id = 1; - - // Cluster radius, the average distance from centroid - // to each point assigned to the cluster. - google.protobuf.DoubleValue cluster_radius = 2; - - // Cluster size, the total number of points assigned to the cluster. - google.protobuf.Int64Value cluster_size = 3; - } - - // (Auto-)arima fitting result. Wrap everything in ArimaResult for easier - // refactoring if we want to use model-specific iteration results. - message ArimaResult { - // Arima coefficients. - message ArimaCoefficients { - // Auto-regressive coefficients, an array of double. - repeated double auto_regressive_coefficients = 1; - - // Moving-average coefficients, an array of double. - repeated double moving_average_coefficients = 2; - - // Intercept coefficient, just a double not an array. - double intercept_coefficient = 3; - } - - // Arima model information. - message ArimaModelInfo { - // Non-seasonal order. - ArimaOrder non_seasonal_order = 1; - - // Arima coefficients. - ArimaCoefficients arima_coefficients = 2; - - // Arima fitting metrics. - ArimaFittingMetrics arima_fitting_metrics = 3; - - // Whether Arima model fitted with drift or not. It is always false - // when d is not 1. - bool has_drift = 4; - - // The id to indicate different time series. - string time_series_id = 5; - - // Seasonal periods. Repeated because multiple periods are supported - // for one time series. - repeated SeasonalPeriod.SeasonalPeriodType seasonal_periods = 6; - } - - // This message is repeated because there are multiple arima models - // fitted in auto-arima. For non-auto-arima model, its size is one. - repeated ArimaModelInfo arima_model_info = 1; - - // Seasonal periods. Repeated because multiple periods are supported for - // one time series. - repeated SeasonalPeriod.SeasonalPeriodType seasonal_periods = 2; - } - - // Index of the iteration, 0 based. - google.protobuf.Int32Value index = 1; - - // Time taken to run the iteration in milliseconds. - google.protobuf.Int64Value duration_ms = 4; - - // Loss computed on the training data at the end of iteration. - google.protobuf.DoubleValue training_loss = 5; - - // Loss computed on the eval data at the end of iteration. - google.protobuf.DoubleValue eval_loss = 6; - - // Learn rate used for this iteration. - double learn_rate = 7; - - // Information about top clusters for clustering models. - repeated ClusterInfo cluster_infos = 8; - - ArimaResult arima_result = 9; - } - - // Options that were used for this training run, includes - // user specified and default options that were used. - TrainingOptions training_options = 1; - - // The start time of this training run. - google.protobuf.Timestamp start_time = 8; - - // Output of each iteration run, results.size() <= max_iterations. - repeated IterationResult results = 6; - - // The evaluation metrics over training/eval data that were computed at the - // end of training. - EvaluationMetrics evaluation_metrics = 7; - - // Data split result of the training run. Only set when the input data is - // actually split. - DataSplitResult data_split_result = 9; - - // Global explanations for important features of the model. For multi-class - // models, there is one entry for each label class. For other models, there - // is only one entry in the list. - repeated GlobalExplanation global_explanations = 10; - } - - // Indicates the type of the Model. - enum ModelType { - MODEL_TYPE_UNSPECIFIED = 0; - - // Linear regression model. - LINEAR_REGRESSION = 1; - - // Logistic regression based classification model. - LOGISTIC_REGRESSION = 2; - - // K-means clustering model. - KMEANS = 3; - - // Matrix factorization model. - MATRIX_FACTORIZATION = 4; - - // [Beta] DNN classifier model. - DNN_CLASSIFIER = 5; - - // [Beta] An imported TensorFlow model. - TENSORFLOW = 6; - - // [Beta] DNN regressor model. - DNN_REGRESSOR = 7; - - // [Beta] Boosted tree regressor model. - BOOSTED_TREE_REGRESSOR = 9; - - // [Beta] Boosted tree classifier model. - BOOSTED_TREE_CLASSIFIER = 10; - - // [Beta] ARIMA model. - ARIMA = 11; - - // [Beta] AutoML Tables regression model. - AUTOML_REGRESSOR = 12; - - // [Beta] AutoML Tables classification model. - AUTOML_CLASSIFIER = 13; - } - - // Loss metric to evaluate model training performance. - enum LossType { - LOSS_TYPE_UNSPECIFIED = 0; - - // Mean squared loss, used for linear regression. - MEAN_SQUARED_LOSS = 1; - - // Mean log loss, used for logistic regression. - MEAN_LOG_LOSS = 2; - } - - // Distance metric used to compute the distance between two points. - enum DistanceType { - DISTANCE_TYPE_UNSPECIFIED = 0; - - // Eculidean distance. - EUCLIDEAN = 1; - - // Cosine distance. - COSINE = 2; - } - - // Indicates the method to split input data into multiple tables. - enum DataSplitMethod { - DATA_SPLIT_METHOD_UNSPECIFIED = 0; - - // Splits data randomly. - RANDOM = 1; - - // Splits data with the user provided tags. - CUSTOM = 2; - - // Splits data sequentially. - SEQUENTIAL = 3; - - // Data split will be skipped. - NO_SPLIT = 4; - - // Splits data automatically: Uses NO_SPLIT if the data size is small. - // Otherwise uses RANDOM. - AUTO_SPLIT = 5; - } - - // Type of supported data frequency for time series forecasting models. - enum DataFrequency { - DATA_FREQUENCY_UNSPECIFIED = 0; - - // Automatically inferred from timestamps. - AUTO_FREQUENCY = 1; - - // Yearly data. - YEARLY = 2; - - // Quarterly data. - QUARTERLY = 3; - - // Monthly data. - MONTHLY = 4; - - // Weekly data. - WEEKLY = 5; - - // Daily data. - DAILY = 6; - - // Hourly data. - HOURLY = 7; - } - - // Type of supported holiday regions for time series forecasting models. - enum HolidayRegion { - // Holiday region unspecified. - HOLIDAY_REGION_UNSPECIFIED = 0; - - // Global. - GLOBAL = 1; - - // North America. - NA = 2; - - // Japan and Asia Pacific: Korea, Greater China, India, Australia, and New - // Zealand. - JAPAC = 3; - - // Europe, the Middle East and Africa. - EMEA = 4; - - // Latin America and the Caribbean. - LAC = 5; - - // United Arab Emirates - AE = 6; - - // Argentina - AR = 7; - - // Austria - AT = 8; - - // Australia - AU = 9; - - // Belgium - BE = 10; - - // Brazil - BR = 11; - - // Canada - CA = 12; - - // Switzerland - CH = 13; - - // Chile - CL = 14; - - // China - CN = 15; - - // Colombia - CO = 16; - - // Czechoslovakia - CS = 17; - - // Czech Republic - CZ = 18; - - // Germany - DE = 19; - - // Denmark - DK = 20; - - // Algeria - DZ = 21; - - // Ecuador - EC = 22; - - // Estonia - EE = 23; - - // Egypt - EG = 24; - - // Spain - ES = 25; - - // Finland - FI = 26; - - // France - FR = 27; - - // Great Britain (United Kingdom) - GB = 28; - - // Greece - GR = 29; - - // Hong Kong - HK = 30; - - // Hungary - HU = 31; - - // Indonesia - ID = 32; - - // Ireland - IE = 33; - - // Israel - IL = 34; - - // India - IN = 35; - - // Iran - IR = 36; - - // Italy - IT = 37; - - // Japan - JP = 38; - - // Korea (South) - KR = 39; - - // Latvia - LV = 40; - - // Morocco - MA = 41; - - // Mexico - MX = 42; - - // Malaysia - MY = 43; - - // Nigeria - NG = 44; - - // Netherlands - NL = 45; - - // Norway - NO = 46; - - // New Zealand - NZ = 47; - - // Peru - PE = 48; - - // Philippines - PH = 49; - - // Pakistan - PK = 50; - - // Poland - PL = 51; - - // Portugal - PT = 52; - - // Romania - RO = 53; - - // Serbia - RS = 54; - - // Russian Federation - RU = 55; - - // Saudi Arabia - SA = 56; - - // Sweden - SE = 57; - - // Singapore - SG = 58; - - // Slovenia - SI = 59; - - // Slovakia - SK = 60; - - // Thailand - TH = 61; - - // Turkey - TR = 62; - - // Taiwan - TW = 63; - - // Ukraine - UA = 64; - - // United States - US = 65; - - // Venezuela - VE = 66; - - // Viet Nam - VN = 67; - - // South Africa - ZA = 68; - } - - // Indicates the learning rate optimization strategy to use. - enum LearnRateStrategy { - LEARN_RATE_STRATEGY_UNSPECIFIED = 0; - - // Use line search to determine learning rate. - LINE_SEARCH = 1; - - // Use a constant learning rate. - CONSTANT = 2; - } - - // Indicates the optimization strategy used for training. - enum OptimizationStrategy { - OPTIMIZATION_STRATEGY_UNSPECIFIED = 0; - - // Uses an iterative batch gradient descent algorithm. - BATCH_GRADIENT_DESCENT = 1; - - // Uses a normal equation to solve linear regression problem. - NORMAL_EQUATION = 2; - } - - // Indicates the training algorithm to use for matrix factorization models. - enum FeedbackType { - FEEDBACK_TYPE_UNSPECIFIED = 0; - - // Use weighted-als for implicit feedback problems. - IMPLICIT = 1; - - // Use nonweighted-als for explicit feedback problems. - EXPLICIT = 2; - } - - // Output only. A hash of this resource. - string etag = 1 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Required. Unique identifier for this model. - ModelReference model_reference = 2 [(google.api.field_behavior) = REQUIRED]; - - // Output only. The time when this model was created, in millisecs since the epoch. - int64 creation_time = 5 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Output only. The time when this model was last modified, in millisecs since the epoch. - int64 last_modified_time = 6 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Optional. A user-friendly description of this model. - string description = 12 [(google.api.field_behavior) = OPTIONAL]; - - // Optional. A descriptive name for this model. - string friendly_name = 14 [(google.api.field_behavior) = OPTIONAL]; - - // The labels associated with this model. You can use these to organize - // and group your models. Label keys and values can be no longer - // than 63 characters, can only contain lowercase letters, numeric - // characters, underscores and dashes. International characters are allowed. - // Label values are optional. Label keys must start with a letter and each - // label in the list must have a different key. - map labels = 15; - - // Optional. The time when this model expires, in milliseconds since the epoch. - // If not present, the model will persist indefinitely. Expired models - // will be deleted and their storage reclaimed. The defaultTableExpirationMs - // property of the encapsulating dataset can be used to set a default - // expirationTime on newly created models. - int64 expiration_time = 16 [(google.api.field_behavior) = OPTIONAL]; - - // Output only. The geographic location where the model resides. This value - // is inherited from the dataset. - string location = 13 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Custom encryption configuration (e.g., Cloud KMS keys). This shows the - // encryption configuration of the model data while stored in BigQuery - // storage. This field can be used with PatchModel to update encryption key - // for an already encrypted model. - EncryptionConfiguration encryption_configuration = 17; - - // Output only. Type of the model resource. - ModelType model_type = 7 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Output only. Information for all training runs in increasing order of start_time. - repeated TrainingRun training_runs = 9 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Output only. Input feature columns that were used to train this model. - repeated StandardSqlField feature_columns = 10 [(google.api.field_behavior) = OUTPUT_ONLY]; - - // Output only. Label columns that were used to train this model. - // The output of the model will have a "predicted_" prefix to these columns. - repeated StandardSqlField label_columns = 11 [(google.api.field_behavior) = OUTPUT_ONLY]; -} - -message GetModelRequest { - // Required. Project ID of the requested model. - string project_id = 1 [(google.api.field_behavior) = REQUIRED]; - - // Required. Dataset ID of the requested model. - string dataset_id = 2 [(google.api.field_behavior) = REQUIRED]; - - // Required. Model ID of the requested model. - string model_id = 3 [(google.api.field_behavior) = REQUIRED]; -} - -message PatchModelRequest { - // Required. Project ID of the model to patch. - string project_id = 1 [(google.api.field_behavior) = REQUIRED]; - - // Required. Dataset ID of the model to patch. - string dataset_id = 2 [(google.api.field_behavior) = REQUIRED]; - - // Required. Model ID of the model to patch. - string model_id = 3 [(google.api.field_behavior) = REQUIRED]; - - // Required. Patched model. - // Follows RFC5789 patch semantics. Missing fields are not updated. - // To clear a field, explicitly set to default value. - Model model = 4 [(google.api.field_behavior) = REQUIRED]; -} - -message DeleteModelRequest { - // Required. Project ID of the model to delete. - string project_id = 1 [(google.api.field_behavior) = REQUIRED]; - - // Required. Dataset ID of the model to delete. - string dataset_id = 2 [(google.api.field_behavior) = REQUIRED]; - - // Required. Model ID of the model to delete. - string model_id = 3 [(google.api.field_behavior) = REQUIRED]; -} - -message ListModelsRequest { - // Required. Project ID of the models to list. - string project_id = 1 [(google.api.field_behavior) = REQUIRED]; - - // Required. Dataset ID of the models to list. - string dataset_id = 2 [(google.api.field_behavior) = REQUIRED]; - - // The maximum number of results to return in a single response page. - // Leverage the page tokens to iterate through the entire collection. - google.protobuf.UInt32Value max_results = 3; - - // Page token, returned by a previous call to request the next page of - // results - string page_token = 4; -} - -message ListModelsResponse { - // Models in the requested dataset. Only the following fields are populated: - // model_reference, model_type, creation_time, last_modified_time and - // labels. - repeated Model models = 1; - - // A token to request the next page of results. - string next_page_token = 2; -} diff --git a/google/cloud/bigquery_v2/proto/model_pb2.py b/google/cloud/bigquery_v2/proto/model_pb2.py deleted file mode 100644 index 7b66be8f7..000000000 --- a/google/cloud/bigquery_v2/proto/model_pb2.py +++ /dev/null @@ -1,4298 +0,0 @@ -# -*- coding: utf-8 -*- -# Generated by the protocol buffer compiler. DO NOT EDIT! -# source: google/cloud/bigquery_v2/proto/model.proto -"""Generated protocol buffer code.""" -from google.protobuf import descriptor as _descriptor -from google.protobuf import message as _message -from google.protobuf import reflection as _reflection -from google.protobuf import symbol_database as _symbol_database - -# @@protoc_insertion_point(imports) - -_sym_db = _symbol_database.Default() - - -from google.api import client_pb2 as google_dot_api_dot_client__pb2 -from google.api import field_behavior_pb2 as google_dot_api_dot_field__behavior__pb2 -from google.cloud.bigquery_v2.proto import ( - encryption_config_pb2 as google_dot_cloud_dot_bigquery__v2_dot_proto_dot_encryption__config__pb2, -) -from google.cloud.bigquery_v2.proto import ( - model_reference_pb2 as google_dot_cloud_dot_bigquery__v2_dot_proto_dot_model__reference__pb2, -) -from google.cloud.bigquery_v2.proto import ( - standard_sql_pb2 as google_dot_cloud_dot_bigquery__v2_dot_proto_dot_standard__sql__pb2, -) -from google.protobuf import empty_pb2 as google_dot_protobuf_dot_empty__pb2 -from google.protobuf import timestamp_pb2 as google_dot_protobuf_dot_timestamp__pb2 -from google.protobuf import wrappers_pb2 as google_dot_protobuf_dot_wrappers__pb2 -from google.api import annotations_pb2 as google_dot_api_dot_annotations__pb2 - - -DESCRIPTOR = _descriptor.FileDescriptor( - name="google/cloud/bigquery_v2/proto/model.proto", - package="google.cloud.bigquery.v2", - syntax="proto3", - serialized_options=b"\n\034com.google.cloud.bigquery.v2B\nModelProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery", - create_key=_descriptor._internal_create_key, - serialized_pb=b'\n*google/cloud/bigquery_v2/proto/model.proto\x12\x18google.cloud.bigquery.v2\x1a\x17google/api/client.proto\x1a\x1fgoogle/api/field_behavior.proto\x1a\x36google/cloud/bigquery_v2/proto/encryption_config.proto\x1a\x34google/cloud/bigquery_v2/proto/model_reference.proto\x1a\x31google/cloud/bigquery_v2/proto/standard_sql.proto\x1a\x1bgoogle/protobuf/empty.proto\x1a\x1fgoogle/protobuf/timestamp.proto\x1a\x1egoogle/protobuf/wrappers.proto\x1a\x1cgoogle/api/annotations.proto"\x9b\x35\n\x05Model\x12\x11\n\x04\x65tag\x18\x01 \x01(\tB\x03\xe0\x41\x03\x12\x46\n\x0fmodel_reference\x18\x02 \x01(\x0b\x32(.google.cloud.bigquery.v2.ModelReferenceB\x03\xe0\x41\x02\x12\x1a\n\rcreation_time\x18\x05 \x01(\x03\x42\x03\xe0\x41\x03\x12\x1f\n\x12last_modified_time\x18\x06 \x01(\x03\x42\x03\xe0\x41\x03\x12\x18\n\x0b\x64\x65scription\x18\x0c \x01(\tB\x03\xe0\x41\x01\x12\x1a\n\rfriendly_name\x18\x0e \x01(\tB\x03\xe0\x41\x01\x12;\n\x06labels\x18\x0f \x03(\x0b\x32+.google.cloud.bigquery.v2.Model.LabelsEntry\x12\x1c\n\x0f\x65xpiration_time\x18\x10 \x01(\x03\x42\x03\xe0\x41\x01\x12\x15\n\x08location\x18\r \x01(\tB\x03\xe0\x41\x03\x12S\n\x18\x65ncryption_configuration\x18\x11 \x01(\x0b\x32\x31.google.cloud.bigquery.v2.EncryptionConfiguration\x12\x42\n\nmodel_type\x18\x07 \x01(\x0e\x32).google.cloud.bigquery.v2.Model.ModelTypeB\x03\xe0\x41\x03\x12G\n\rtraining_runs\x18\t \x03(\x0b\x32+.google.cloud.bigquery.v2.Model.TrainingRunB\x03\xe0\x41\x03\x12H\n\x0f\x66\x65\x61ture_columns\x18\n \x03(\x0b\x32*.google.cloud.bigquery.v2.StandardSqlFieldB\x03\xe0\x41\x03\x12\x46\n\rlabel_columns\x18\x0b \x03(\x0b\x32*.google.cloud.bigquery.v2.StandardSqlFieldB\x03\xe0\x41\x03\x1aq\n\x0bKmeansEnums"b\n\x1aKmeansInitializationMethod\x12,\n(KMEANS_INITIALIZATION_METHOD_UNSPECIFIED\x10\x00\x12\n\n\x06RANDOM\x10\x01\x12\n\n\x06\x43USTOM\x10\x02\x1a\xb4\x02\n\x11RegressionMetrics\x12\x39\n\x13mean_absolute_error\x18\x01 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12\x38\n\x12mean_squared_error\x18\x02 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12<\n\x16mean_squared_log_error\x18\x03 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12;\n\x15median_absolute_error\x18\x04 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12/\n\tr_squared\x18\x05 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x1a\xef\x02\n\x1e\x41ggregateClassificationMetrics\x12/\n\tprecision\x18\x01 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12,\n\x06recall\x18\x02 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12.\n\x08\x61\x63\x63uracy\x18\x03 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12/\n\tthreshold\x18\x04 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12.\n\x08\x66\x31_score\x18\x05 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12.\n\x08log_loss\x18\x06 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12-\n\x07roc_auc\x18\x07 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x1a\x9f\x06\n\x1b\x42inaryClassificationMetrics\x12h\n aggregate_classification_metrics\x18\x01 \x01(\x0b\x32>.google.cloud.bigquery.v2.Model.AggregateClassificationMetrics\x12w\n\x1c\x62inary_confusion_matrix_list\x18\x02 \x03(\x0b\x32Q.google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix\x12\x16\n\x0epositive_label\x18\x03 \x01(\t\x12\x16\n\x0enegative_label\x18\x04 \x01(\t\x1a\xec\x03\n\x15\x42inaryConfusionMatrix\x12>\n\x18positive_class_threshold\x18\x01 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12\x33\n\x0etrue_positives\x18\x02 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x12\x34\n\x0f\x66\x61lse_positives\x18\x03 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x12\x33\n\x0etrue_negatives\x18\x04 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x12\x34\n\x0f\x66\x61lse_negatives\x18\x05 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x12/\n\tprecision\x18\x06 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12,\n\x06recall\x18\x07 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12.\n\x08\x66\x31_score\x18\x08 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12.\n\x08\x61\x63\x63uracy\x18\t \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x1a\x87\x05\n\x1fMultiClassClassificationMetrics\x12h\n aggregate_classification_metrics\x18\x01 \x01(\x0b\x32>.google.cloud.bigquery.v2.Model.AggregateClassificationMetrics\x12n\n\x15\x63onfusion_matrix_list\x18\x02 \x03(\x0b\x32O.google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix\x1a\x89\x03\n\x0f\x43onfusionMatrix\x12:\n\x14\x63onfidence_threshold\x18\x01 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12\x61\n\x04rows\x18\x02 \x03(\x0b\x32S.google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Row\x1aQ\n\x05\x45ntry\x12\x17\n\x0fpredicted_label\x18\x01 \x01(\t\x12/\n\nitem_count\x18\x02 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x1a\x83\x01\n\x03Row\x12\x14\n\x0c\x61\x63tual_label\x18\x01 \x01(\t\x12\x66\n\x07\x65ntries\x18\x02 \x03(\x0b\x32U.google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Entry\x1a\xcb\x06\n\x11\x43lusteringMetrics\x12:\n\x14\x64\x61vies_bouldin_index\x18\x01 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12;\n\x15mean_squared_distance\x18\x02 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12K\n\x08\x63lusters\x18\x03 \x03(\x0b\x32\x39.google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster\x1a\xef\x04\n\x07\x43luster\x12\x13\n\x0b\x63\x65ntroid_id\x18\x01 \x01(\x03\x12^\n\x0e\x66\x65\x61ture_values\x18\x02 \x03(\x0b\x32\x46.google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue\x12*\n\x05\x63ount\x18\x03 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x1a\xc2\x03\n\x0c\x46\x65\x61tureValue\x12\x16\n\x0e\x66\x65\x61ture_column\x18\x01 \x01(\t\x12\x37\n\x0fnumerical_value\x18\x02 \x01(\x0b\x32\x1c.google.protobuf.DoubleValueH\x00\x12t\n\x11\x63\x61tegorical_value\x18\x03 \x01(\x0b\x32W.google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValueH\x00\x1a\xe1\x01\n\x10\x43\x61tegoricalValue\x12~\n\x0f\x63\x61tegory_counts\x18\x01 \x03(\x0b\x32\x65.google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount\x1aM\n\rCategoryCount\x12\x10\n\x08\x63\x61tegory\x18\x01 \x01(\t\x12*\n\x05\x63ount\x18\x02 \x01(\x0b\x32\x1b.google.protobuf.Int64ValueB\x07\n\x05value\x1a\x95\x03\n\x11\x45valuationMetrics\x12O\n\x12regression_metrics\x18\x01 \x01(\x0b\x32\x31.google.cloud.bigquery.v2.Model.RegressionMetricsH\x00\x12\x64\n\x1d\x62inary_classification_metrics\x18\x02 \x01(\x0b\x32;.google.cloud.bigquery.v2.Model.BinaryClassificationMetricsH\x00\x12m\n"multi_class_classification_metrics\x18\x03 \x01(\x0b\x32?.google.cloud.bigquery.v2.Model.MultiClassClassificationMetricsH\x00\x12O\n\x12\x63lustering_metrics\x18\x04 \x01(\x0b\x32\x31.google.cloud.bigquery.v2.Model.ClusteringMetricsH\x00\x42\t\n\x07metrics\x1a\xab\x0f\n\x0bTrainingRun\x12U\n\x10training_options\x18\x01 \x01(\x0b\x32;.google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions\x12.\n\nstart_time\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.Timestamp\x12L\n\x07results\x18\x06 \x03(\x0b\x32;.google.cloud.bigquery.v2.Model.TrainingRun.IterationResult\x12M\n\x12\x65valuation_metrics\x18\x07 \x01(\x0b\x32\x31.google.cloud.bigquery.v2.Model.EvaluationMetrics\x1a\x9d\t\n\x0fTrainingOptions\x12\x16\n\x0emax_iterations\x18\x01 \x01(\x03\x12;\n\tloss_type\x18\x02 \x01(\x0e\x32(.google.cloud.bigquery.v2.Model.LossType\x12\x12\n\nlearn_rate\x18\x03 \x01(\x01\x12\x37\n\x11l1_regularization\x18\x04 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12\x37\n\x11l2_regularization\x18\x05 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12;\n\x15min_relative_progress\x18\x06 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12.\n\nwarm_start\x18\x07 \x01(\x0b\x32\x1a.google.protobuf.BoolValue\x12.\n\nearly_stop\x18\x08 \x01(\x0b\x32\x1a.google.protobuf.BoolValue\x12\x1b\n\x13input_label_columns\x18\t \x03(\t\x12J\n\x11\x64\x61ta_split_method\x18\n \x01(\x0e\x32/.google.cloud.bigquery.v2.Model.DataSplitMethod\x12 \n\x18\x64\x61ta_split_eval_fraction\x18\x0b \x01(\x01\x12\x19\n\x11\x64\x61ta_split_column\x18\x0c \x01(\t\x12N\n\x13learn_rate_strategy\x18\r \x01(\x0e\x32\x31.google.cloud.bigquery.v2.Model.LearnRateStrategy\x12\x1a\n\x12initial_learn_rate\x18\x10 \x01(\x01\x12o\n\x13label_class_weights\x18\x11 \x03(\x0b\x32R.google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.LabelClassWeightsEntry\x12\x43\n\rdistance_type\x18\x14 \x01(\x0e\x32,.google.cloud.bigquery.v2.Model.DistanceType\x12\x14\n\x0cnum_clusters\x18\x15 \x01(\x03\x12\x11\n\tmodel_uri\x18\x16 \x01(\t\x12S\n\x15optimization_strategy\x18\x17 \x01(\x0e\x32\x34.google.cloud.bigquery.v2.Model.OptimizationStrategy\x12l\n\x1ckmeans_initialization_method\x18! \x01(\x0e\x32\x46.google.cloud.bigquery.v2.Model.KmeansEnums.KmeansInitializationMethod\x12$\n\x1ckmeans_initialization_column\x18" \x01(\t\x1a\x38\n\x16LabelClassWeightsEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\x01:\x02\x38\x01\x1a\xd7\x03\n\x0fIterationResult\x12*\n\x05index\x18\x01 \x01(\x0b\x32\x1b.google.protobuf.Int32Value\x12\x30\n\x0b\x64uration_ms\x18\x04 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x12\x33\n\rtraining_loss\x18\x05 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12/\n\teval_loss\x18\x06 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12\x12\n\nlearn_rate\x18\x07 \x01(\x01\x12^\n\rcluster_infos\x18\x08 \x03(\x0b\x32G.google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.ClusterInfo\x1a\x8b\x01\n\x0b\x43lusterInfo\x12\x13\n\x0b\x63\x65ntroid_id\x18\x01 \x01(\x03\x12\x34\n\x0e\x63luster_radius\x18\x02 \x01(\x0b\x32\x1c.google.protobuf.DoubleValue\x12\x31\n\x0c\x63luster_size\x18\x03 \x01(\x0b\x32\x1b.google.protobuf.Int64Value\x1a-\n\x0bLabelsEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\t:\x02\x38\x01"s\n\tModelType\x12\x1a\n\x16MODEL_TYPE_UNSPECIFIED\x10\x00\x12\x15\n\x11LINEAR_REGRESSION\x10\x01\x12\x17\n\x13LOGISTIC_REGRESSION\x10\x02\x12\n\n\x06KMEANS\x10\x03\x12\x0e\n\nTENSORFLOW\x10\x06"O\n\x08LossType\x12\x19\n\x15LOSS_TYPE_UNSPECIFIED\x10\x00\x12\x15\n\x11MEAN_SQUARED_LOSS\x10\x01\x12\x11\n\rMEAN_LOG_LOSS\x10\x02"H\n\x0c\x44istanceType\x12\x1d\n\x19\x44ISTANCE_TYPE_UNSPECIFIED\x10\x00\x12\r\n\tEUCLIDEAN\x10\x01\x12\n\n\x06\x43OSINE\x10\x02"z\n\x0f\x44\x61taSplitMethod\x12!\n\x1d\x44\x41TA_SPLIT_METHOD_UNSPECIFIED\x10\x00\x12\n\n\x06RANDOM\x10\x01\x12\n\n\x06\x43USTOM\x10\x02\x12\x0e\n\nSEQUENTIAL\x10\x03\x12\x0c\n\x08NO_SPLIT\x10\x04\x12\x0e\n\nAUTO_SPLIT\x10\x05"W\n\x11LearnRateStrategy\x12#\n\x1fLEARN_RATE_STRATEGY_UNSPECIFIED\x10\x00\x12\x0f\n\x0bLINE_SEARCH\x10\x01\x12\x0c\n\x08\x43ONSTANT\x10\x02"n\n\x14OptimizationStrategy\x12%\n!OPTIMIZATION_STRATEGY_UNSPECIFIED\x10\x00\x12\x1a\n\x16\x42\x41TCH_GRADIENT_DESCENT\x10\x01\x12\x13\n\x0fNORMAL_EQUATION\x10\x02"Z\n\x0fGetModelRequest\x12\x17\n\nproject_id\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x17\n\ndataset_id\x18\x02 \x01(\tB\x03\xe0\x41\x02\x12\x15\n\x08model_id\x18\x03 \x01(\tB\x03\xe0\x41\x02"\x91\x01\n\x11PatchModelRequest\x12\x17\n\nproject_id\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x17\n\ndataset_id\x18\x02 \x01(\tB\x03\xe0\x41\x02\x12\x15\n\x08model_id\x18\x03 \x01(\tB\x03\xe0\x41\x02\x12\x33\n\x05model\x18\x04 \x01(\x0b\x32\x1f.google.cloud.bigquery.v2.ModelB\x03\xe0\x41\x02"]\n\x12\x44\x65leteModelRequest\x12\x17\n\nproject_id\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x17\n\ndataset_id\x18\x02 \x01(\tB\x03\xe0\x41\x02\x12\x15\n\x08model_id\x18\x03 \x01(\tB\x03\xe0\x41\x02"\x8c\x01\n\x11ListModelsRequest\x12\x17\n\nproject_id\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x17\n\ndataset_id\x18\x02 \x01(\tB\x03\xe0\x41\x02\x12\x31\n\x0bmax_results\x18\x03 \x01(\x0b\x32\x1c.google.protobuf.UInt32Value\x12\x12\n\npage_token\x18\x04 \x01(\t"^\n\x12ListModelsResponse\x12/\n\x06models\x18\x01 \x03(\x0b\x32\x1f.google.cloud.bigquery.v2.Model\x12\x17\n\x0fnext_page_token\x18\x02 \x01(\t2\xfa\x05\n\x0cModelService\x12y\n\x08GetModel\x12).google.cloud.bigquery.v2.GetModelRequest\x1a\x1f.google.cloud.bigquery.v2.Model"!\xda\x41\x1eproject_id,dataset_id,model_id\x12\x8d\x01\n\nListModels\x12+.google.cloud.bigquery.v2.ListModelsRequest\x1a,.google.cloud.bigquery.v2.ListModelsResponse"$\xda\x41!project_id,dataset_id,max_results\x12\x83\x01\n\nPatchModel\x12+.google.cloud.bigquery.v2.PatchModelRequest\x1a\x1f.google.cloud.bigquery.v2.Model"\'\xda\x41$project_id,dataset_id,model_id,model\x12v\n\x0b\x44\x65leteModel\x12,.google.cloud.bigquery.v2.DeleteModelRequest\x1a\x16.google.protobuf.Empty"!\xda\x41\x1eproject_id,dataset_id,model_id\x1a\xe0\x01\xca\x41\x17\x62igquery.googleapis.com\xd2\x41\xc2\x01https://www.googleapis.com/auth/bigquery,https://www.googleapis.com/auth/bigquery.readonly,https://www.googleapis.com/auth/cloud-platform,https://www.googleapis.com/auth/cloud-platform.read-onlyBl\n\x1c\x63om.google.cloud.bigquery.v2B\nModelProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigqueryb\x06proto3', - dependencies=[ - google_dot_api_dot_client__pb2.DESCRIPTOR, - google_dot_api_dot_field__behavior__pb2.DESCRIPTOR, - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_encryption__config__pb2.DESCRIPTOR, - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_model__reference__pb2.DESCRIPTOR, - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_standard__sql__pb2.DESCRIPTOR, - google_dot_protobuf_dot_empty__pb2.DESCRIPTOR, - google_dot_protobuf_dot_timestamp__pb2.DESCRIPTOR, - google_dot_protobuf_dot_wrappers__pb2.DESCRIPTOR, - google_dot_api_dot_annotations__pb2.DESCRIPTOR, - ], -) - - -_MODEL_KMEANSENUMS_KMEANSINITIALIZATIONMETHOD = _descriptor.EnumDescriptor( - name="KmeansInitializationMethod", - full_name="google.cloud.bigquery.v2.Model.KmeansEnums.KmeansInitializationMethod", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="KMEANS_INITIALIZATION_METHOD_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="RANDOM", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="CUSTOM", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=1132, - serialized_end=1230, -) -_sym_db.RegisterEnumDescriptor(_MODEL_KMEANSENUMS_KMEANSINITIALIZATIONMETHOD) - -_MODEL_MODELTYPE = _descriptor.EnumDescriptor( - name="ModelType", - full_name="google.cloud.bigquery.v2.Model.ModelType", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="MODEL_TYPE_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="LINEAR_REGRESSION", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="LOGISTIC_REGRESSION", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="KMEANS", - index=3, - number=3, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="TENSORFLOW", - index=4, - number=6, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=6632, - serialized_end=6747, -) -_sym_db.RegisterEnumDescriptor(_MODEL_MODELTYPE) - -_MODEL_LOSSTYPE = _descriptor.EnumDescriptor( - name="LossType", - full_name="google.cloud.bigquery.v2.Model.LossType", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="LOSS_TYPE_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="MEAN_SQUARED_LOSS", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="MEAN_LOG_LOSS", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=6749, - serialized_end=6828, -) -_sym_db.RegisterEnumDescriptor(_MODEL_LOSSTYPE) - -_MODEL_DISTANCETYPE = _descriptor.EnumDescriptor( - name="DistanceType", - full_name="google.cloud.bigquery.v2.Model.DistanceType", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="DISTANCE_TYPE_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="EUCLIDEAN", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="COSINE", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=6830, - serialized_end=6902, -) -_sym_db.RegisterEnumDescriptor(_MODEL_DISTANCETYPE) - -_MODEL_DATASPLITMETHOD = _descriptor.EnumDescriptor( - name="DataSplitMethod", - full_name="google.cloud.bigquery.v2.Model.DataSplitMethod", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="DATA_SPLIT_METHOD_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="RANDOM", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="CUSTOM", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="SEQUENTIAL", - index=3, - number=3, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="NO_SPLIT", - index=4, - number=4, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="AUTO_SPLIT", - index=5, - number=5, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=6904, - serialized_end=7026, -) -_sym_db.RegisterEnumDescriptor(_MODEL_DATASPLITMETHOD) - -_MODEL_LEARNRATESTRATEGY = _descriptor.EnumDescriptor( - name="LearnRateStrategy", - full_name="google.cloud.bigquery.v2.Model.LearnRateStrategy", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="LEARN_RATE_STRATEGY_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="LINE_SEARCH", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="CONSTANT", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=7028, - serialized_end=7115, -) -_sym_db.RegisterEnumDescriptor(_MODEL_LEARNRATESTRATEGY) - -_MODEL_OPTIMIZATIONSTRATEGY = _descriptor.EnumDescriptor( - name="OptimizationStrategy", - full_name="google.cloud.bigquery.v2.Model.OptimizationStrategy", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="OPTIMIZATION_STRATEGY_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="BATCH_GRADIENT_DESCENT", - index=1, - number=1, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="NORMAL_EQUATION", - index=2, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=7117, - serialized_end=7227, -) -_sym_db.RegisterEnumDescriptor(_MODEL_OPTIMIZATIONSTRATEGY) - - -_MODEL_KMEANSENUMS = _descriptor.Descriptor( - name="KmeansEnums", - full_name="google.cloud.bigquery.v2.Model.KmeansEnums", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[], - extensions=[], - nested_types=[], - enum_types=[_MODEL_KMEANSENUMS_KMEANSINITIALIZATIONMETHOD,], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=1117, - serialized_end=1230, -) - -_MODEL_REGRESSIONMETRICS = _descriptor.Descriptor( - name="RegressionMetrics", - full_name="google.cloud.bigquery.v2.Model.RegressionMetrics", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="mean_absolute_error", - full_name="google.cloud.bigquery.v2.Model.RegressionMetrics.mean_absolute_error", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="mean_squared_error", - full_name="google.cloud.bigquery.v2.Model.RegressionMetrics.mean_squared_error", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="mean_squared_log_error", - full_name="google.cloud.bigquery.v2.Model.RegressionMetrics.mean_squared_log_error", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="median_absolute_error", - full_name="google.cloud.bigquery.v2.Model.RegressionMetrics.median_absolute_error", - index=3, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="r_squared", - full_name="google.cloud.bigquery.v2.Model.RegressionMetrics.r_squared", - index=4, - number=5, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=1233, - serialized_end=1541, -) - -_MODEL_AGGREGATECLASSIFICATIONMETRICS = _descriptor.Descriptor( - name="AggregateClassificationMetrics", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="precision", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.precision", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="recall", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.recall", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="accuracy", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.accuracy", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="threshold", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.threshold", - index=3, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="f1_score", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.f1_score", - index=4, - number=5, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="log_loss", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.log_loss", - index=5, - number=6, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="roc_auc", - full_name="google.cloud.bigquery.v2.Model.AggregateClassificationMetrics.roc_auc", - index=6, - number=7, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=1544, - serialized_end=1911, -) - -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX = _descriptor.Descriptor( - name="BinaryConfusionMatrix", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="positive_class_threshold", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.positive_class_threshold", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="true_positives", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.true_positives", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="false_positives", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.false_positives", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="true_negatives", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.true_negatives", - index=3, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="false_negatives", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.false_negatives", - index=4, - number=5, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="precision", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.precision", - index=5, - number=6, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="recall", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.recall", - index=6, - number=7, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="f1_score", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.f1_score", - index=7, - number=8, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="accuracy", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix.accuracy", - index=8, - number=9, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=2221, - serialized_end=2713, -) - -_MODEL_BINARYCLASSIFICATIONMETRICS = _descriptor.Descriptor( - name="BinaryClassificationMetrics", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="aggregate_classification_metrics", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.aggregate_classification_metrics", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="binary_confusion_matrix_list", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.binary_confusion_matrix_list", - index=1, - number=2, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="positive_label", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.positive_label", - index=2, - number=3, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="negative_label", - full_name="google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.negative_label", - index=3, - number=4, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=1914, - serialized_end=2713, -) - -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ENTRY = _descriptor.Descriptor( - name="Entry", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Entry", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="predicted_label", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Entry.predicted_label", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="item_count", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Entry.item_count", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=3148, - serialized_end=3229, -) - -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ROW = _descriptor.Descriptor( - name="Row", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Row", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="actual_label", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Row.actual_label", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="entries", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Row.entries", - index=1, - number=2, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=3232, - serialized_end=3363, -) - -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX = _descriptor.Descriptor( - name="ConfusionMatrix", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="confidence_threshold", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.confidence_threshold", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="rows", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.rows", - index=1, - number=2, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[ - _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ENTRY, - _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ROW, - ], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=2970, - serialized_end=3363, -) - -_MODEL_MULTICLASSCLASSIFICATIONMETRICS = _descriptor.Descriptor( - name="MultiClassClassificationMetrics", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="aggregate_classification_metrics", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.aggregate_classification_metrics", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="confusion_matrix_list", - full_name="google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.confusion_matrix_list", - index=1, - number=2, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=2716, - serialized_end=3363, -) - -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE_CATEGORYCOUNT = _descriptor.Descriptor( - name="CategoryCount", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="category", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount.category", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="count", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount.count", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=4123, - serialized_end=4200, -) - -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE = _descriptor.Descriptor( - name="CategoricalValue", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="category_counts", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.category_counts", - index=0, - number=1, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[ - _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE_CATEGORYCOUNT, - ], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=3975, - serialized_end=4200, -) - -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE = _descriptor.Descriptor( - name="FeatureValue", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="feature_column", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.feature_column", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="numerical_value", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.numerical_value", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="categorical_value", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.categorical_value", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[ - _descriptor.OneofDescriptor( - name="value", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.value", - index=0, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[], - ), - ], - serialized_start=3759, - serialized_end=4209, -) - -_MODEL_CLUSTERINGMETRICS_CLUSTER = _descriptor.Descriptor( - name="Cluster", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="centroid_id", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.centroid_id", - index=0, - number=1, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="feature_values", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.feature_values", - index=1, - number=2, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="count", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.count", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=3586, - serialized_end=4209, -) - -_MODEL_CLUSTERINGMETRICS = _descriptor.Descriptor( - name="ClusteringMetrics", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="davies_bouldin_index", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.davies_bouldin_index", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="mean_squared_distance", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.mean_squared_distance", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="clusters", - full_name="google.cloud.bigquery.v2.Model.ClusteringMetrics.clusters", - index=2, - number=3, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_CLUSTERINGMETRICS_CLUSTER,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=3366, - serialized_end=4209, -) - -_MODEL_EVALUATIONMETRICS = _descriptor.Descriptor( - name="EvaluationMetrics", - full_name="google.cloud.bigquery.v2.Model.EvaluationMetrics", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="regression_metrics", - full_name="google.cloud.bigquery.v2.Model.EvaluationMetrics.regression_metrics", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="binary_classification_metrics", - full_name="google.cloud.bigquery.v2.Model.EvaluationMetrics.binary_classification_metrics", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="multi_class_classification_metrics", - full_name="google.cloud.bigquery.v2.Model.EvaluationMetrics.multi_class_classification_metrics", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="clustering_metrics", - full_name="google.cloud.bigquery.v2.Model.EvaluationMetrics.clustering_metrics", - index=3, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[ - _descriptor.OneofDescriptor( - name="metrics", - full_name="google.cloud.bigquery.v2.Model.EvaluationMetrics.metrics", - index=0, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[], - ), - ], - serialized_start=4212, - serialized_end=4617, -) - -_MODEL_TRAININGRUN_TRAININGOPTIONS_LABELCLASSWEIGHTSENTRY = _descriptor.Descriptor( - name="LabelClassWeightsEntry", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.LabelClassWeightsEntry", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="key", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.LabelClassWeightsEntry.key", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="value", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.LabelClassWeightsEntry.value", - index=1, - number=2, - type=1, - cpp_type=5, - label=1, - has_default_value=False, - default_value=float(0), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=b"8\001", - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=6053, - serialized_end=6109, -) - -_MODEL_TRAININGRUN_TRAININGOPTIONS = _descriptor.Descriptor( - name="TrainingOptions", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="max_iterations", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.max_iterations", - index=0, - number=1, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="loss_type", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.loss_type", - index=1, - number=2, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="learn_rate", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.learn_rate", - index=2, - number=3, - type=1, - cpp_type=5, - label=1, - has_default_value=False, - default_value=float(0), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="l1_regularization", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.l1_regularization", - index=3, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="l2_regularization", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.l2_regularization", - index=4, - number=5, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="min_relative_progress", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.min_relative_progress", - index=5, - number=6, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="warm_start", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.warm_start", - index=6, - number=7, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="early_stop", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.early_stop", - index=7, - number=8, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="input_label_columns", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.input_label_columns", - index=8, - number=9, - type=9, - cpp_type=9, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="data_split_method", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.data_split_method", - index=9, - number=10, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="data_split_eval_fraction", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.data_split_eval_fraction", - index=10, - number=11, - type=1, - cpp_type=5, - label=1, - has_default_value=False, - default_value=float(0), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="data_split_column", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.data_split_column", - index=11, - number=12, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="learn_rate_strategy", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.learn_rate_strategy", - index=12, - number=13, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="initial_learn_rate", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.initial_learn_rate", - index=13, - number=16, - type=1, - cpp_type=5, - label=1, - has_default_value=False, - default_value=float(0), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="label_class_weights", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.label_class_weights", - index=14, - number=17, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="distance_type", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.distance_type", - index=15, - number=20, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="num_clusters", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.num_clusters", - index=16, - number=21, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_uri", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.model_uri", - index=17, - number=22, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="optimization_strategy", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.optimization_strategy", - index=18, - number=23, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="kmeans_initialization_method", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.kmeans_initialization_method", - index=19, - number=33, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="kmeans_initialization_column", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.kmeans_initialization_column", - index=20, - number=34, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_TRAININGRUN_TRAININGOPTIONS_LABELCLASSWEIGHTSENTRY,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=4928, - serialized_end=6109, -) - -_MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO = _descriptor.Descriptor( - name="ClusterInfo", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.ClusterInfo", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="centroid_id", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.ClusterInfo.centroid_id", - index=0, - number=1, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="cluster_radius", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.ClusterInfo.cluster_radius", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="cluster_size", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.ClusterInfo.cluster_size", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=6444, - serialized_end=6583, -) - -_MODEL_TRAININGRUN_ITERATIONRESULT = _descriptor.Descriptor( - name="IterationResult", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="index", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.index", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="duration_ms", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.duration_ms", - index=1, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="training_loss", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.training_loss", - index=2, - number=5, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="eval_loss", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.eval_loss", - index=3, - number=6, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="learn_rate", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.learn_rate", - index=4, - number=7, - type=1, - cpp_type=5, - label=1, - has_default_value=False, - default_value=float(0), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="cluster_infos", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.cluster_infos", - index=5, - number=8, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[_MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO,], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=6112, - serialized_end=6583, -) - -_MODEL_TRAININGRUN = _descriptor.Descriptor( - name="TrainingRun", - full_name="google.cloud.bigquery.v2.Model.TrainingRun", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="training_options", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.training_options", - index=0, - number=1, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="start_time", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.start_time", - index=1, - number=8, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="results", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.results", - index=2, - number=6, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="evaluation_metrics", - full_name="google.cloud.bigquery.v2.Model.TrainingRun.evaluation_metrics", - index=3, - number=7, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[ - _MODEL_TRAININGRUN_TRAININGOPTIONS, - _MODEL_TRAININGRUN_ITERATIONRESULT, - ], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=4620, - serialized_end=6583, -) - -_MODEL_LABELSENTRY = _descriptor.Descriptor( - name="LabelsEntry", - full_name="google.cloud.bigquery.v2.Model.LabelsEntry", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="key", - full_name="google.cloud.bigquery.v2.Model.LabelsEntry.key", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="value", - full_name="google.cloud.bigquery.v2.Model.LabelsEntry.value", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=b"8\001", - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=6585, - serialized_end=6630, -) - -_MODEL = _descriptor.Descriptor( - name="Model", - full_name="google.cloud.bigquery.v2.Model", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="etag", - full_name="google.cloud.bigquery.v2.Model.etag", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_reference", - full_name="google.cloud.bigquery.v2.Model.model_reference", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="creation_time", - full_name="google.cloud.bigquery.v2.Model.creation_time", - index=2, - number=5, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="last_modified_time", - full_name="google.cloud.bigquery.v2.Model.last_modified_time", - index=3, - number=6, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="description", - full_name="google.cloud.bigquery.v2.Model.description", - index=4, - number=12, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\001", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="friendly_name", - full_name="google.cloud.bigquery.v2.Model.friendly_name", - index=5, - number=14, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\001", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="labels", - full_name="google.cloud.bigquery.v2.Model.labels", - index=6, - number=15, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="expiration_time", - full_name="google.cloud.bigquery.v2.Model.expiration_time", - index=7, - number=16, - type=3, - cpp_type=2, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\001", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="location", - full_name="google.cloud.bigquery.v2.Model.location", - index=8, - number=13, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="encryption_configuration", - full_name="google.cloud.bigquery.v2.Model.encryption_configuration", - index=9, - number=17, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_type", - full_name="google.cloud.bigquery.v2.Model.model_type", - index=10, - number=7, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="training_runs", - full_name="google.cloud.bigquery.v2.Model.training_runs", - index=11, - number=9, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="feature_columns", - full_name="google.cloud.bigquery.v2.Model.feature_columns", - index=12, - number=10, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="label_columns", - full_name="google.cloud.bigquery.v2.Model.label_columns", - index=13, - number=11, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\003", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[ - _MODEL_KMEANSENUMS, - _MODEL_REGRESSIONMETRICS, - _MODEL_AGGREGATECLASSIFICATIONMETRICS, - _MODEL_BINARYCLASSIFICATIONMETRICS, - _MODEL_MULTICLASSCLASSIFICATIONMETRICS, - _MODEL_CLUSTERINGMETRICS, - _MODEL_EVALUATIONMETRICS, - _MODEL_TRAININGRUN, - _MODEL_LABELSENTRY, - ], - enum_types=[ - _MODEL_MODELTYPE, - _MODEL_LOSSTYPE, - _MODEL_DISTANCETYPE, - _MODEL_DATASPLITMETHOD, - _MODEL_LEARNRATESTRATEGY, - _MODEL_OPTIMIZATIONSTRATEGY, - ], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=416, - serialized_end=7227, -) - - -_GETMODELREQUEST = _descriptor.Descriptor( - name="GetModelRequest", - full_name="google.cloud.bigquery.v2.GetModelRequest", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="project_id", - full_name="google.cloud.bigquery.v2.GetModelRequest.project_id", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="dataset_id", - full_name="google.cloud.bigquery.v2.GetModelRequest.dataset_id", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_id", - full_name="google.cloud.bigquery.v2.GetModelRequest.model_id", - index=2, - number=3, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=7229, - serialized_end=7319, -) - - -_PATCHMODELREQUEST = _descriptor.Descriptor( - name="PatchModelRequest", - full_name="google.cloud.bigquery.v2.PatchModelRequest", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="project_id", - full_name="google.cloud.bigquery.v2.PatchModelRequest.project_id", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="dataset_id", - full_name="google.cloud.bigquery.v2.PatchModelRequest.dataset_id", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_id", - full_name="google.cloud.bigquery.v2.PatchModelRequest.model_id", - index=2, - number=3, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model", - full_name="google.cloud.bigquery.v2.PatchModelRequest.model", - index=3, - number=4, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=7322, - serialized_end=7467, -) - - -_DELETEMODELREQUEST = _descriptor.Descriptor( - name="DeleteModelRequest", - full_name="google.cloud.bigquery.v2.DeleteModelRequest", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="project_id", - full_name="google.cloud.bigquery.v2.DeleteModelRequest.project_id", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="dataset_id", - full_name="google.cloud.bigquery.v2.DeleteModelRequest.dataset_id", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_id", - full_name="google.cloud.bigquery.v2.DeleteModelRequest.model_id", - index=2, - number=3, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=7469, - serialized_end=7562, -) - - -_LISTMODELSREQUEST = _descriptor.Descriptor( - name="ListModelsRequest", - full_name="google.cloud.bigquery.v2.ListModelsRequest", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="project_id", - full_name="google.cloud.bigquery.v2.ListModelsRequest.project_id", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="dataset_id", - full_name="google.cloud.bigquery.v2.ListModelsRequest.dataset_id", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="max_results", - full_name="google.cloud.bigquery.v2.ListModelsRequest.max_results", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="page_token", - full_name="google.cloud.bigquery.v2.ListModelsRequest.page_token", - index=3, - number=4, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=7565, - serialized_end=7705, -) - - -_LISTMODELSRESPONSE = _descriptor.Descriptor( - name="ListModelsResponse", - full_name="google.cloud.bigquery.v2.ListModelsResponse", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="models", - full_name="google.cloud.bigquery.v2.ListModelsResponse.models", - index=0, - number=1, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="next_page_token", - full_name="google.cloud.bigquery.v2.ListModelsResponse.next_page_token", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=7707, - serialized_end=7801, -) - -_MODEL_KMEANSENUMS.containing_type = _MODEL -_MODEL_KMEANSENUMS_KMEANSINITIALIZATIONMETHOD.containing_type = _MODEL_KMEANSENUMS -_MODEL_REGRESSIONMETRICS.fields_by_name[ - "mean_absolute_error" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_REGRESSIONMETRICS.fields_by_name[ - "mean_squared_error" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_REGRESSIONMETRICS.fields_by_name[ - "mean_squared_log_error" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_REGRESSIONMETRICS.fields_by_name[ - "median_absolute_error" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_REGRESSIONMETRICS.fields_by_name[ - "r_squared" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_REGRESSIONMETRICS.containing_type = _MODEL -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "precision" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "recall" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "accuracy" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "threshold" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "f1_score" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "log_loss" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.fields_by_name[ - "roc_auc" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_AGGREGATECLASSIFICATIONMETRICS.containing_type = _MODEL -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "positive_class_threshold" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "true_positives" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "false_positives" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "true_negatives" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "false_negatives" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "precision" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "recall" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "f1_score" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.fields_by_name[ - "accuracy" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX.containing_type = ( - _MODEL_BINARYCLASSIFICATIONMETRICS -) -_MODEL_BINARYCLASSIFICATIONMETRICS.fields_by_name[ - "aggregate_classification_metrics" -].message_type = _MODEL_AGGREGATECLASSIFICATIONMETRICS -_MODEL_BINARYCLASSIFICATIONMETRICS.fields_by_name[ - "binary_confusion_matrix_list" -].message_type = _MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX -_MODEL_BINARYCLASSIFICATIONMETRICS.containing_type = _MODEL -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ENTRY.fields_by_name[ - "item_count" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ENTRY.containing_type = ( - _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX -) -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ROW.fields_by_name[ - "entries" -].message_type = _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ENTRY -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ROW.containing_type = ( - _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX -) -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX.fields_by_name[ - "confidence_threshold" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX.fields_by_name[ - "rows" -].message_type = _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ROW -_MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX.containing_type = ( - _MODEL_MULTICLASSCLASSIFICATIONMETRICS -) -_MODEL_MULTICLASSCLASSIFICATIONMETRICS.fields_by_name[ - "aggregate_classification_metrics" -].message_type = _MODEL_AGGREGATECLASSIFICATIONMETRICS -_MODEL_MULTICLASSCLASSIFICATIONMETRICS.fields_by_name[ - "confusion_matrix_list" -].message_type = _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX -_MODEL_MULTICLASSCLASSIFICATIONMETRICS.containing_type = _MODEL -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE_CATEGORYCOUNT.fields_by_name[ - "count" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE_CATEGORYCOUNT.containing_type = ( - _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE -) -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE.fields_by_name[ - "category_counts" -].message_type = ( - _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE_CATEGORYCOUNT -) -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE.containing_type = ( - _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE -) -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.fields_by_name[ - "numerical_value" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.fields_by_name[ - "categorical_value" -].message_type = _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.containing_type = ( - _MODEL_CLUSTERINGMETRICS_CLUSTER -) -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.oneofs_by_name["value"].fields.append( - _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.fields_by_name["numerical_value"] -) -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.fields_by_name[ - "numerical_value" -].containing_oneof = _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.oneofs_by_name[ - "value" -] -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.oneofs_by_name["value"].fields.append( - _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.fields_by_name["categorical_value"] -) -_MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.fields_by_name[ - "categorical_value" -].containing_oneof = _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE.oneofs_by_name[ - "value" -] -_MODEL_CLUSTERINGMETRICS_CLUSTER.fields_by_name[ - "feature_values" -].message_type = _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE -_MODEL_CLUSTERINGMETRICS_CLUSTER.fields_by_name[ - "count" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_CLUSTERINGMETRICS_CLUSTER.containing_type = _MODEL_CLUSTERINGMETRICS -_MODEL_CLUSTERINGMETRICS.fields_by_name[ - "davies_bouldin_index" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_CLUSTERINGMETRICS.fields_by_name[ - "mean_squared_distance" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_CLUSTERINGMETRICS.fields_by_name[ - "clusters" -].message_type = _MODEL_CLUSTERINGMETRICS_CLUSTER -_MODEL_CLUSTERINGMETRICS.containing_type = _MODEL -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "regression_metrics" -].message_type = _MODEL_REGRESSIONMETRICS -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "binary_classification_metrics" -].message_type = _MODEL_BINARYCLASSIFICATIONMETRICS -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "multi_class_classification_metrics" -].message_type = _MODEL_MULTICLASSCLASSIFICATIONMETRICS -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "clustering_metrics" -].message_type = _MODEL_CLUSTERINGMETRICS -_MODEL_EVALUATIONMETRICS.containing_type = _MODEL -_MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"].fields.append( - _MODEL_EVALUATIONMETRICS.fields_by_name["regression_metrics"] -) -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "regression_metrics" -].containing_oneof = _MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"] -_MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"].fields.append( - _MODEL_EVALUATIONMETRICS.fields_by_name["binary_classification_metrics"] -) -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "binary_classification_metrics" -].containing_oneof = _MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"] -_MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"].fields.append( - _MODEL_EVALUATIONMETRICS.fields_by_name["multi_class_classification_metrics"] -) -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "multi_class_classification_metrics" -].containing_oneof = _MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"] -_MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"].fields.append( - _MODEL_EVALUATIONMETRICS.fields_by_name["clustering_metrics"] -) -_MODEL_EVALUATIONMETRICS.fields_by_name[ - "clustering_metrics" -].containing_oneof = _MODEL_EVALUATIONMETRICS.oneofs_by_name["metrics"] -_MODEL_TRAININGRUN_TRAININGOPTIONS_LABELCLASSWEIGHTSENTRY.containing_type = ( - _MODEL_TRAININGRUN_TRAININGOPTIONS -) -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "loss_type" -].enum_type = _MODEL_LOSSTYPE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "l1_regularization" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "l2_regularization" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "min_relative_progress" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "warm_start" -].message_type = google_dot_protobuf_dot_wrappers__pb2._BOOLVALUE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "early_stop" -].message_type = google_dot_protobuf_dot_wrappers__pb2._BOOLVALUE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "data_split_method" -].enum_type = _MODEL_DATASPLITMETHOD -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "learn_rate_strategy" -].enum_type = _MODEL_LEARNRATESTRATEGY -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "label_class_weights" -].message_type = _MODEL_TRAININGRUN_TRAININGOPTIONS_LABELCLASSWEIGHTSENTRY -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "distance_type" -].enum_type = _MODEL_DISTANCETYPE -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "optimization_strategy" -].enum_type = _MODEL_OPTIMIZATIONSTRATEGY -_MODEL_TRAININGRUN_TRAININGOPTIONS.fields_by_name[ - "kmeans_initialization_method" -].enum_type = _MODEL_KMEANSENUMS_KMEANSINITIALIZATIONMETHOD -_MODEL_TRAININGRUN_TRAININGOPTIONS.containing_type = _MODEL_TRAININGRUN -_MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO.fields_by_name[ - "cluster_radius" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO.fields_by_name[ - "cluster_size" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO.containing_type = ( - _MODEL_TRAININGRUN_ITERATIONRESULT -) -_MODEL_TRAININGRUN_ITERATIONRESULT.fields_by_name[ - "index" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT32VALUE -_MODEL_TRAININGRUN_ITERATIONRESULT.fields_by_name[ - "duration_ms" -].message_type = google_dot_protobuf_dot_wrappers__pb2._INT64VALUE -_MODEL_TRAININGRUN_ITERATIONRESULT.fields_by_name[ - "training_loss" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_TRAININGRUN_ITERATIONRESULT.fields_by_name[ - "eval_loss" -].message_type = google_dot_protobuf_dot_wrappers__pb2._DOUBLEVALUE -_MODEL_TRAININGRUN_ITERATIONRESULT.fields_by_name[ - "cluster_infos" -].message_type = _MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO -_MODEL_TRAININGRUN_ITERATIONRESULT.containing_type = _MODEL_TRAININGRUN -_MODEL_TRAININGRUN.fields_by_name[ - "training_options" -].message_type = _MODEL_TRAININGRUN_TRAININGOPTIONS -_MODEL_TRAININGRUN.fields_by_name[ - "start_time" -].message_type = google_dot_protobuf_dot_timestamp__pb2._TIMESTAMP -_MODEL_TRAININGRUN.fields_by_name[ - "results" -].message_type = _MODEL_TRAININGRUN_ITERATIONRESULT -_MODEL_TRAININGRUN.fields_by_name[ - "evaluation_metrics" -].message_type = _MODEL_EVALUATIONMETRICS -_MODEL_TRAININGRUN.containing_type = _MODEL -_MODEL_LABELSENTRY.containing_type = _MODEL -_MODEL.fields_by_name[ - "model_reference" -].message_type = ( - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_model__reference__pb2._MODELREFERENCE -) -_MODEL.fields_by_name["labels"].message_type = _MODEL_LABELSENTRY -_MODEL.fields_by_name[ - "encryption_configuration" -].message_type = ( - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_encryption__config__pb2._ENCRYPTIONCONFIGURATION -) -_MODEL.fields_by_name["model_type"].enum_type = _MODEL_MODELTYPE -_MODEL.fields_by_name["training_runs"].message_type = _MODEL_TRAININGRUN -_MODEL.fields_by_name[ - "feature_columns" -].message_type = ( - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_standard__sql__pb2._STANDARDSQLFIELD -) -_MODEL.fields_by_name[ - "label_columns" -].message_type = ( - google_dot_cloud_dot_bigquery__v2_dot_proto_dot_standard__sql__pb2._STANDARDSQLFIELD -) -_MODEL_MODELTYPE.containing_type = _MODEL -_MODEL_LOSSTYPE.containing_type = _MODEL -_MODEL_DISTANCETYPE.containing_type = _MODEL -_MODEL_DATASPLITMETHOD.containing_type = _MODEL -_MODEL_LEARNRATESTRATEGY.containing_type = _MODEL -_MODEL_OPTIMIZATIONSTRATEGY.containing_type = _MODEL -_PATCHMODELREQUEST.fields_by_name["model"].message_type = _MODEL -_LISTMODELSREQUEST.fields_by_name[ - "max_results" -].message_type = google_dot_protobuf_dot_wrappers__pb2._UINT32VALUE -_LISTMODELSRESPONSE.fields_by_name["models"].message_type = _MODEL -DESCRIPTOR.message_types_by_name["Model"] = _MODEL -DESCRIPTOR.message_types_by_name["GetModelRequest"] = _GETMODELREQUEST -DESCRIPTOR.message_types_by_name["PatchModelRequest"] = _PATCHMODELREQUEST -DESCRIPTOR.message_types_by_name["DeleteModelRequest"] = _DELETEMODELREQUEST -DESCRIPTOR.message_types_by_name["ListModelsRequest"] = _LISTMODELSREQUEST -DESCRIPTOR.message_types_by_name["ListModelsResponse"] = _LISTMODELSRESPONSE -_sym_db.RegisterFileDescriptor(DESCRIPTOR) - -Model = _reflection.GeneratedProtocolMessageType( - "Model", - (_message.Message,), - { - "KmeansEnums": _reflection.GeneratedProtocolMessageType( - "KmeansEnums", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_KMEANSENUMS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2" - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.KmeansEnums) - }, - ), - "RegressionMetrics": _reflection.GeneratedProtocolMessageType( - "RegressionMetrics", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_REGRESSIONMETRICS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Evaluation metrics for regression and explicit feedback type matrix - factorization models. - - Attributes: - mean_absolute_error: - Mean absolute error. - mean_squared_error: - Mean squared error. - mean_squared_log_error: - Mean squared log error. - median_absolute_error: - Median absolute error. - r_squared: - R^2 score. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.RegressionMetrics) - }, - ), - "AggregateClassificationMetrics": _reflection.GeneratedProtocolMessageType( - "AggregateClassificationMetrics", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_AGGREGATECLASSIFICATIONMETRICS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Aggregate metrics for classification/classifier models. For multi- - class models, the metrics are either macro-averaged or micro-averaged. - When macro-averaged, the metrics are calculated for each label and - then an unweighted average is taken of those values. When micro- - averaged, the metric is calculated globally by counting the total - number of correctly predicted rows. - - Attributes: - precision: - Precision is the fraction of actual positive predictions that - had positive actual labels. For multiclass this is a macro- - averaged metric treating each class as a binary classifier. - recall: - Recall is the fraction of actual positive labels that were - given a positive prediction. For multiclass this is a macro- - averaged metric. - accuracy: - Accuracy is the fraction of predictions given the correct - label. For multiclass this is a micro-averaged metric. - threshold: - Threshold at which the metrics are computed. For binary - classification models this is the positive class threshold. - For multi-class classfication models this is the confidence - threshold. - f1_score: - The F1 score is an average of recall and precision. For - multiclass this is a macro-averaged metric. - log_loss: - Logarithmic Loss. For multiclass this is a macro-averaged - metric. - roc_auc: - Area Under a ROC Curve. For multiclass this is a macro- - averaged metric. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.AggregateClassificationMetrics) - }, - ), - "BinaryClassificationMetrics": _reflection.GeneratedProtocolMessageType( - "BinaryClassificationMetrics", - (_message.Message,), - { - "BinaryConfusionMatrix": _reflection.GeneratedProtocolMessageType( - "BinaryConfusionMatrix", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_BINARYCLASSIFICATIONMETRICS_BINARYCONFUSIONMATRIX, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Confusion matrix for binary classification models. - - Attributes: - positive_class_threshold: - Threshold value used when computing each of the following - metric. - true_positives: - Number of true samples predicted as true. - false_positives: - Number of false samples predicted as true. - true_negatives: - Number of true samples predicted as false. - false_negatives: - Number of false samples predicted as false. - precision: - The fraction of actual positive predictions that had positive - actual labels. - recall: - The fraction of actual positive labels that were given a - positive prediction. - f1_score: - The equally weighted average of recall and precision. - accuracy: - The fraction of predictions given the correct label. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.BinaryClassificationMetrics.BinaryConfusionMatrix) - }, - ), - "DESCRIPTOR": _MODEL_BINARYCLASSIFICATIONMETRICS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Evaluation metrics for binary classification/classifier models. - - Attributes: - aggregate_classification_metrics: - Aggregate classification metrics. - binary_confusion_matrix_list: - Binary confusion matrix at multiple thresholds. - positive_label: - Label representing the positive class. - negative_label: - Label representing the negative class. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.BinaryClassificationMetrics) - }, - ), - "MultiClassClassificationMetrics": _reflection.GeneratedProtocolMessageType( - "MultiClassClassificationMetrics", - (_message.Message,), - { - "ConfusionMatrix": _reflection.GeneratedProtocolMessageType( - "ConfusionMatrix", - (_message.Message,), - { - "Entry": _reflection.GeneratedProtocolMessageType( - "Entry", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ENTRY, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """A single entry in the confusion matrix. - - Attributes: - predicted_label: - The predicted label. For confidence_threshold > 0, we will - also add an entry indicating the number of items under the - confidence threshold. - item_count: - Number of items being predicted as this label. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Entry) - }, - ), - "Row": _reflection.GeneratedProtocolMessageType( - "Row", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX_ROW, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """A single row in the confusion matrix. - - Attributes: - actual_label: - The original label of this row. - entries: - Info describing predicted label distribution. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix.Row) - }, - ), - "DESCRIPTOR": _MODEL_MULTICLASSCLASSIFICATIONMETRICS_CONFUSIONMATRIX, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Confusion matrix for multi-class classification models. - - Attributes: - confidence_threshold: - Confidence threshold used when computing the entries of the - confusion matrix. - rows: - One row per actual label. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics.ConfusionMatrix) - }, - ), - "DESCRIPTOR": _MODEL_MULTICLASSCLASSIFICATIONMETRICS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Evaluation metrics for multi-class classification/classifier models. - - Attributes: - aggregate_classification_metrics: - Aggregate classification metrics. - confusion_matrix_list: - Confusion matrix at different thresholds. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.MultiClassClassificationMetrics) - }, - ), - "ClusteringMetrics": _reflection.GeneratedProtocolMessageType( - "ClusteringMetrics", - (_message.Message,), - { - "Cluster": _reflection.GeneratedProtocolMessageType( - "Cluster", - (_message.Message,), - { - "FeatureValue": _reflection.GeneratedProtocolMessageType( - "FeatureValue", - (_message.Message,), - { - "CategoricalValue": _reflection.GeneratedProtocolMessageType( - "CategoricalValue", - (_message.Message,), - { - "CategoryCount": _reflection.GeneratedProtocolMessageType( - "CategoryCount", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE_CATEGORYCOUNT, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Represents the count of a single category within the cluster. - - Attributes: - category: - The name of category. - count: - The count of training samples matching the category within the - cluster. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount) - }, - ), - "DESCRIPTOR": _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE_CATEGORICALVALUE, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Representative value of a categorical feature. - - Attributes: - category_counts: - Counts of all categories for the categorical feature. If there - are more than ten categories, we return top ten (by count) and - return one more CategoryCount with category ``*OTHER*`` and - count as aggregate counts of remaining categories. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue) - }, - ), - "DESCRIPTOR": _MODEL_CLUSTERINGMETRICS_CLUSTER_FEATUREVALUE, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Representative value of a single feature within the cluster. - - Attributes: - feature_column: - The feature column name. - numerical_value: - The numerical feature value. This is the centroid value for - this feature. - categorical_value: - The categorical feature value. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster.FeatureValue) - }, - ), - "DESCRIPTOR": _MODEL_CLUSTERINGMETRICS_CLUSTER, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Message containing the information about one cluster. - - Attributes: - centroid_id: - Centroid id. - feature_values: - Values of highly variant features for this cluster. - count: - Count of training data rows that were assigned to this - cluster. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.ClusteringMetrics.Cluster) - }, - ), - "DESCRIPTOR": _MODEL_CLUSTERINGMETRICS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Evaluation metrics for clustering models. - - Attributes: - davies_bouldin_index: - Davies-Bouldin index. - mean_squared_distance: - Mean of squared distances between each sample to its cluster - centroid. - clusters: - [Beta] Information for all clusters. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.ClusteringMetrics) - }, - ), - "EvaluationMetrics": _reflection.GeneratedProtocolMessageType( - "EvaluationMetrics", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_EVALUATIONMETRICS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Evaluation metrics of a model. These are either computed on all - training data or just the eval data based on whether eval data was - used during training. These are not present for imported models. - - Attributes: - regression_metrics: - Populated for regression models and explicit feedback type - matrix factorization models. - binary_classification_metrics: - Populated for binary classification/classifier models. - multi_class_classification_metrics: - Populated for multi-class classification/classifier models. - clustering_metrics: - Populated for clustering models. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.EvaluationMetrics) - }, - ), - "TrainingRun": _reflection.GeneratedProtocolMessageType( - "TrainingRun", - (_message.Message,), - { - "TrainingOptions": _reflection.GeneratedProtocolMessageType( - "TrainingOptions", - (_message.Message,), - { - "LabelClassWeightsEntry": _reflection.GeneratedProtocolMessageType( - "LabelClassWeightsEntry", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_TRAININGRUN_TRAININGOPTIONS_LABELCLASSWEIGHTSENTRY, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2" - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions.LabelClassWeightsEntry) - }, - ), - "DESCRIPTOR": _MODEL_TRAININGRUN_TRAININGOPTIONS, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - max_iterations: - The maximum number of iterations in training. Used only for - iterative training algorithms. - loss_type: - Type of loss function used during training run. - learn_rate: - Learning rate in training. Used only for iterative training - algorithms. - l1_regularization: - L1 regularization coefficient. - l2_regularization: - L2 regularization coefficient. - min_relative_progress: - When early_stop is true, stops training when accuracy - improvement is less than ‘min_relative_progress’. Used only - for iterative training algorithms. - warm_start: - Whether to train a model from the last checkpoint. - early_stop: - Whether to stop early when the loss doesn’t improve - significantly any more (compared to min_relative_progress). - Used only for iterative training algorithms. - input_label_columns: - Name of input label columns in training data. - data_split_method: - The data split type for training and evaluation, e.g. RANDOM. - data_split_eval_fraction: - The fraction of evaluation data over the whole input data. The - rest of data will be used as training data. The format should - be double. Accurate to two decimal places. Default value is - 0.2. - data_split_column: - The column to split data with. This column won’t be used as a - feature. 1. When data_split_method is CUSTOM, the - corresponding column should be boolean. The rows with true - value tag are eval data, and the false are training data. 2. - When data_split_method is SEQ, the first - DATA_SPLIT_EVAL_FRACTION rows (from smallest to largest) in - the corresponding column are used as training data, and the - rest are eval data. It respects the order in Orderable data - types: - https://cloud.google.com/bigquery/docs/reference/standard- - sql/data-types#data-type-properties - learn_rate_strategy: - The strategy to determine learn rate for the current - iteration. - initial_learn_rate: - Specifies the initial learning rate for the line search learn - rate strategy. - label_class_weights: - Weights associated with each label class, for rebalancing the - training data. Only applicable for classification models. - distance_type: - Distance type for clustering models. - num_clusters: - Number of clusters for clustering models. - model_uri: - [Beta] Google Cloud Storage URI from which the model was - imported. Only applicable for imported models. - optimization_strategy: - Optimization strategy for training linear regression models. - kmeans_initialization_method: - The method used to initialize the centroids for kmeans - algorithm. - kmeans_initialization_column: - The column used to provide the initial centroids for kmeans - algorithm when kmeans_initialization_method is CUSTOM. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.TrainingRun.TrainingOptions) - }, - ), - "IterationResult": _reflection.GeneratedProtocolMessageType( - "IterationResult", - (_message.Message,), - { - "ClusterInfo": _reflection.GeneratedProtocolMessageType( - "ClusterInfo", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_TRAININGRUN_ITERATIONRESULT_CLUSTERINFO, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Information about a single cluster for clustering model. - - Attributes: - centroid_id: - Centroid id. - cluster_radius: - Cluster radius, the average distance from centroid to each - point assigned to the cluster. - cluster_size: - Cluster size, the total number of points assigned to the - cluster. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.TrainingRun.IterationResult.ClusterInfo) - }, - ), - "DESCRIPTOR": _MODEL_TRAININGRUN_ITERATIONRESULT, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Information about a single iteration of the training run. - - Attributes: - index: - Index of the iteration, 0 based. - duration_ms: - Time taken to run the iteration in milliseconds. - training_loss: - Loss computed on the training data at the end of iteration. - eval_loss: - Loss computed on the eval data at the end of iteration. - learn_rate: - Learn rate used for this iteration. - cluster_infos: - Information about top clusters for clustering models. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.TrainingRun.IterationResult) - }, - ), - "DESCRIPTOR": _MODEL_TRAININGRUN, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Information about a single training query run for the model. - - Attributes: - training_options: - Options that were used for this training run, includes user - specified and default options that were used. - start_time: - The start time of this training run. - results: - Output of each iteration run, results.size() <= - max_iterations. - evaluation_metrics: - The evaluation metrics over training/eval data that were - computed at the end of training. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.TrainingRun) - }, - ), - "LabelsEntry": _reflection.GeneratedProtocolMessageType( - "LabelsEntry", - (_message.Message,), - { - "DESCRIPTOR": _MODEL_LABELSENTRY, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2" - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model.LabelsEntry) - }, - ), - "DESCRIPTOR": _MODEL, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - etag: - Output only. A hash of this resource. - model_reference: - Required. Unique identifier for this model. - creation_time: - Output only. The time when this model was created, in - millisecs since the epoch. - last_modified_time: - Output only. The time when this model was last modified, in - millisecs since the epoch. - description: - Optional. A user-friendly description of this model. - friendly_name: - Optional. A descriptive name for this model. - labels: - The labels associated with this model. You can use these to - organize and group your models. Label keys and values can be - no longer than 63 characters, can only contain lowercase - letters, numeric characters, underscores and dashes. - International characters are allowed. Label values are - optional. Label keys must start with a letter and each label - in the list must have a different key. - expiration_time: - Optional. The time when this model expires, in milliseconds - since the epoch. If not present, the model will persist - indefinitely. Expired models will be deleted and their storage - reclaimed. The defaultTableExpirationMs property of the - encapsulating dataset can be used to set a default - expirationTime on newly created models. - location: - Output only. The geographic location where the model resides. - This value is inherited from the dataset. - encryption_configuration: - Custom encryption configuration (e.g., Cloud KMS keys). This - shows the encryption configuration of the model data while - stored in BigQuery storage. - model_type: - Output only. Type of the model resource. - training_runs: - Output only. Information for all training runs in increasing - order of start_time. - feature_columns: - Output only. Input feature columns that were used to train - this model. - label_columns: - Output only. Label columns that were used to train this model. - The output of the model will have a ``predicted\_`` prefix to - these columns. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.Model) - }, -) -_sym_db.RegisterMessage(Model) -_sym_db.RegisterMessage(Model.KmeansEnums) -_sym_db.RegisterMessage(Model.RegressionMetrics) -_sym_db.RegisterMessage(Model.AggregateClassificationMetrics) -_sym_db.RegisterMessage(Model.BinaryClassificationMetrics) -_sym_db.RegisterMessage(Model.BinaryClassificationMetrics.BinaryConfusionMatrix) -_sym_db.RegisterMessage(Model.MultiClassClassificationMetrics) -_sym_db.RegisterMessage(Model.MultiClassClassificationMetrics.ConfusionMatrix) -_sym_db.RegisterMessage(Model.MultiClassClassificationMetrics.ConfusionMatrix.Entry) -_sym_db.RegisterMessage(Model.MultiClassClassificationMetrics.ConfusionMatrix.Row) -_sym_db.RegisterMessage(Model.ClusteringMetrics) -_sym_db.RegisterMessage(Model.ClusteringMetrics.Cluster) -_sym_db.RegisterMessage(Model.ClusteringMetrics.Cluster.FeatureValue) -_sym_db.RegisterMessage(Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue) -_sym_db.RegisterMessage( - Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount -) -_sym_db.RegisterMessage(Model.EvaluationMetrics) -_sym_db.RegisterMessage(Model.TrainingRun) -_sym_db.RegisterMessage(Model.TrainingRun.TrainingOptions) -_sym_db.RegisterMessage(Model.TrainingRun.TrainingOptions.LabelClassWeightsEntry) -_sym_db.RegisterMessage(Model.TrainingRun.IterationResult) -_sym_db.RegisterMessage(Model.TrainingRun.IterationResult.ClusterInfo) -_sym_db.RegisterMessage(Model.LabelsEntry) - -GetModelRequest = _reflection.GeneratedProtocolMessageType( - "GetModelRequest", - (_message.Message,), - { - "DESCRIPTOR": _GETMODELREQUEST, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - project_id: - Required. Project ID of the requested model. - dataset_id: - Required. Dataset ID of the requested model. - model_id: - Required. Model ID of the requested model. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.GetModelRequest) - }, -) -_sym_db.RegisterMessage(GetModelRequest) - -PatchModelRequest = _reflection.GeneratedProtocolMessageType( - "PatchModelRequest", - (_message.Message,), - { - "DESCRIPTOR": _PATCHMODELREQUEST, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - project_id: - Required. Project ID of the model to patch. - dataset_id: - Required. Dataset ID of the model to patch. - model_id: - Required. Model ID of the model to patch. - model: - Required. Patched model. Follows RFC5789 patch semantics. - Missing fields are not updated. To clear a field, explicitly - set to default value. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.PatchModelRequest) - }, -) -_sym_db.RegisterMessage(PatchModelRequest) - -DeleteModelRequest = _reflection.GeneratedProtocolMessageType( - "DeleteModelRequest", - (_message.Message,), - { - "DESCRIPTOR": _DELETEMODELREQUEST, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - project_id: - Required. Project ID of the model to delete. - dataset_id: - Required. Dataset ID of the model to delete. - model_id: - Required. Model ID of the model to delete. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.DeleteModelRequest) - }, -) -_sym_db.RegisterMessage(DeleteModelRequest) - -ListModelsRequest = _reflection.GeneratedProtocolMessageType( - "ListModelsRequest", - (_message.Message,), - { - "DESCRIPTOR": _LISTMODELSREQUEST, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - project_id: - Required. Project ID of the models to list. - dataset_id: - Required. Dataset ID of the models to list. - max_results: - The maximum number of results to return in a single response - page. Leverage the page tokens to iterate through the entire - collection. - page_token: - Page token, returned by a previous call to request the next - page of results - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.ListModelsRequest) - }, -) -_sym_db.RegisterMessage(ListModelsRequest) - -ListModelsResponse = _reflection.GeneratedProtocolMessageType( - "ListModelsResponse", - (_message.Message,), - { - "DESCRIPTOR": _LISTMODELSRESPONSE, - "__module__": "google.cloud.bigquery_v2.proto.model_pb2", - "__doc__": """Protocol buffer. - - Attributes: - models: - Models in the requested dataset. Only the following fields are - populated: model_reference, model_type, creation_time, - last_modified_time and labels. - next_page_token: - A token to request the next page of results. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.ListModelsResponse) - }, -) -_sym_db.RegisterMessage(ListModelsResponse) - - -DESCRIPTOR._options = None -_MODEL_TRAININGRUN_TRAININGOPTIONS_LABELCLASSWEIGHTSENTRY._options = None -_MODEL_LABELSENTRY._options = None -_MODEL.fields_by_name["etag"]._options = None -_MODEL.fields_by_name["model_reference"]._options = None -_MODEL.fields_by_name["creation_time"]._options = None -_MODEL.fields_by_name["last_modified_time"]._options = None -_MODEL.fields_by_name["description"]._options = None -_MODEL.fields_by_name["friendly_name"]._options = None -_MODEL.fields_by_name["expiration_time"]._options = None -_MODEL.fields_by_name["location"]._options = None -_MODEL.fields_by_name["model_type"]._options = None -_MODEL.fields_by_name["training_runs"]._options = None -_MODEL.fields_by_name["feature_columns"]._options = None -_MODEL.fields_by_name["label_columns"]._options = None -_GETMODELREQUEST.fields_by_name["project_id"]._options = None -_GETMODELREQUEST.fields_by_name["dataset_id"]._options = None -_GETMODELREQUEST.fields_by_name["model_id"]._options = None -_PATCHMODELREQUEST.fields_by_name["project_id"]._options = None -_PATCHMODELREQUEST.fields_by_name["dataset_id"]._options = None -_PATCHMODELREQUEST.fields_by_name["model_id"]._options = None -_PATCHMODELREQUEST.fields_by_name["model"]._options = None -_DELETEMODELREQUEST.fields_by_name["project_id"]._options = None -_DELETEMODELREQUEST.fields_by_name["dataset_id"]._options = None -_DELETEMODELREQUEST.fields_by_name["model_id"]._options = None -_LISTMODELSREQUEST.fields_by_name["project_id"]._options = None -_LISTMODELSREQUEST.fields_by_name["dataset_id"]._options = None - -_MODELSERVICE = _descriptor.ServiceDescriptor( - name="ModelService", - full_name="google.cloud.bigquery.v2.ModelService", - file=DESCRIPTOR, - index=0, - serialized_options=b"\312A\027bigquery.googleapis.com\322A\302\001https://www.googleapis.com/auth/bigquery,https://www.googleapis.com/auth/bigquery.readonly,https://www.googleapis.com/auth/cloud-platform,https://www.googleapis.com/auth/cloud-platform.read-only", - create_key=_descriptor._internal_create_key, - serialized_start=7804, - serialized_end=8566, - methods=[ - _descriptor.MethodDescriptor( - name="GetModel", - full_name="google.cloud.bigquery.v2.ModelService.GetModel", - index=0, - containing_service=None, - input_type=_GETMODELREQUEST, - output_type=_MODEL, - serialized_options=b"\332A\036project_id,dataset_id,model_id", - create_key=_descriptor._internal_create_key, - ), - _descriptor.MethodDescriptor( - name="ListModels", - full_name="google.cloud.bigquery.v2.ModelService.ListModels", - index=1, - containing_service=None, - input_type=_LISTMODELSREQUEST, - output_type=_LISTMODELSRESPONSE, - serialized_options=b"\332A!project_id,dataset_id,max_results", - create_key=_descriptor._internal_create_key, - ), - _descriptor.MethodDescriptor( - name="PatchModel", - full_name="google.cloud.bigquery.v2.ModelService.PatchModel", - index=2, - containing_service=None, - input_type=_PATCHMODELREQUEST, - output_type=_MODEL, - serialized_options=b"\332A$project_id,dataset_id,model_id,model", - create_key=_descriptor._internal_create_key, - ), - _descriptor.MethodDescriptor( - name="DeleteModel", - full_name="google.cloud.bigquery.v2.ModelService.DeleteModel", - index=3, - containing_service=None, - input_type=_DELETEMODELREQUEST, - output_type=google_dot_protobuf_dot_empty__pb2._EMPTY, - serialized_options=b"\332A\036project_id,dataset_id,model_id", - create_key=_descriptor._internal_create_key, - ), - ], -) -_sym_db.RegisterServiceDescriptor(_MODELSERVICE) - -DESCRIPTOR.services_by_name["ModelService"] = _MODELSERVICE - -# @@protoc_insertion_point(module_scope) diff --git a/google/cloud/bigquery_v2/proto/model_reference.proto b/google/cloud/bigquery_v2/proto/model_reference.proto deleted file mode 100644 index c3d1a49a8..000000000 --- a/google/cloud/bigquery_v2/proto/model_reference.proto +++ /dev/null @@ -1,38 +0,0 @@ -// Copyright 2020 Google LLC -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -syntax = "proto3"; - -package google.cloud.bigquery.v2; - -import "google/api/field_behavior.proto"; -import "google/api/annotations.proto"; - -option go_package = "google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery"; -option java_outer_classname = "ModelReferenceProto"; -option java_package = "com.google.cloud.bigquery.v2"; - -// Id path of a model. -message ModelReference { - // Required. The ID of the project containing this model. - string project_id = 1 [(google.api.field_behavior) = REQUIRED]; - - // Required. The ID of the dataset containing this model. - string dataset_id = 2 [(google.api.field_behavior) = REQUIRED]; - - // Required. The ID of the model. The ID must contain only - // letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum - // length is 1,024 characters. - string model_id = 3 [(google.api.field_behavior) = REQUIRED]; -} diff --git a/google/cloud/bigquery_v2/proto/model_reference_pb2.py b/google/cloud/bigquery_v2/proto/model_reference_pb2.py deleted file mode 100644 index 2411c4863..000000000 --- a/google/cloud/bigquery_v2/proto/model_reference_pb2.py +++ /dev/null @@ -1,142 +0,0 @@ -# -*- coding: utf-8 -*- -# Generated by the protocol buffer compiler. DO NOT EDIT! -# source: google/cloud/bigquery_v2/proto/model_reference.proto -"""Generated protocol buffer code.""" -from google.protobuf import descriptor as _descriptor -from google.protobuf import message as _message -from google.protobuf import reflection as _reflection -from google.protobuf import symbol_database as _symbol_database - -# @@protoc_insertion_point(imports) - -_sym_db = _symbol_database.Default() - - -from google.api import field_behavior_pb2 as google_dot_api_dot_field__behavior__pb2 -from google.api import annotations_pb2 as google_dot_api_dot_annotations__pb2 - - -DESCRIPTOR = _descriptor.FileDescriptor( - name="google/cloud/bigquery_v2/proto/model_reference.proto", - package="google.cloud.bigquery.v2", - syntax="proto3", - serialized_options=b"\n\034com.google.cloud.bigquery.v2B\023ModelReferenceProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery", - create_key=_descriptor._internal_create_key, - serialized_pb=b'\n4google/cloud/bigquery_v2/proto/model_reference.proto\x12\x18google.cloud.bigquery.v2\x1a\x1fgoogle/api/field_behavior.proto\x1a\x1cgoogle/api/annotations.proto"Y\n\x0eModelReference\x12\x17\n\nproject_id\x18\x01 \x01(\tB\x03\xe0\x41\x02\x12\x17\n\ndataset_id\x18\x02 \x01(\tB\x03\xe0\x41\x02\x12\x15\n\x08model_id\x18\x03 \x01(\tB\x03\xe0\x41\x02\x42u\n\x1c\x63om.google.cloud.bigquery.v2B\x13ModelReferenceProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigqueryb\x06proto3', - dependencies=[ - google_dot_api_dot_field__behavior__pb2.DESCRIPTOR, - google_dot_api_dot_annotations__pb2.DESCRIPTOR, - ], -) - - -_MODELREFERENCE = _descriptor.Descriptor( - name="ModelReference", - full_name="google.cloud.bigquery.v2.ModelReference", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="project_id", - full_name="google.cloud.bigquery.v2.ModelReference.project_id", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="dataset_id", - full_name="google.cloud.bigquery.v2.ModelReference.dataset_id", - index=1, - number=2, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="model_id", - full_name="google.cloud.bigquery.v2.ModelReference.model_id", - index=2, - number=3, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=145, - serialized_end=234, -) - -DESCRIPTOR.message_types_by_name["ModelReference"] = _MODELREFERENCE -_sym_db.RegisterFileDescriptor(DESCRIPTOR) - -ModelReference = _reflection.GeneratedProtocolMessageType( - "ModelReference", - (_message.Message,), - { - "DESCRIPTOR": _MODELREFERENCE, - "__module__": "google.cloud.bigquery_v2.proto.model_reference_pb2", - "__doc__": """Id path of a model. - - Attributes: - project_id: - Required. The ID of the project containing this model. - dataset_id: - Required. The ID of the dataset containing this model. - model_id: - Required. The ID of the model. The ID must contain only - letters (a-z, A-Z), numbers (0-9), or underscores (_). The - maximum length is 1,024 characters. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.ModelReference) - }, -) -_sym_db.RegisterMessage(ModelReference) - - -DESCRIPTOR._options = None -_MODELREFERENCE.fields_by_name["project_id"]._options = None -_MODELREFERENCE.fields_by_name["dataset_id"]._options = None -_MODELREFERENCE.fields_by_name["model_id"]._options = None -# @@protoc_insertion_point(module_scope) diff --git a/google/cloud/bigquery_v2/proto/standard_sql.proto b/google/cloud/bigquery_v2/proto/standard_sql.proto deleted file mode 100644 index 1514eccbb..000000000 --- a/google/cloud/bigquery_v2/proto/standard_sql.proto +++ /dev/null @@ -1,112 +0,0 @@ -// Copyright 2020 Google LLC -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -syntax = "proto3"; - -package google.cloud.bigquery.v2; - -import "google/api/field_behavior.proto"; -import "google/api/annotations.proto"; - -option go_package = "google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery"; -option java_outer_classname = "StandardSqlProto"; -option java_package = "com.google.cloud.bigquery.v2"; - -// The type of a variable, e.g., a function argument. -// Examples: -// INT64: {type_kind="INT64"} -// ARRAY: {type_kind="ARRAY", array_element_type="STRING"} -// STRUCT>: -// {type_kind="STRUCT", -// struct_type={fields=[ -// {name="x", type={type_kind="STRING"}}, -// {name="y", type={type_kind="ARRAY", array_element_type="DATE"}} -// ]}} -message StandardSqlDataType { - enum TypeKind { - // Invalid type. - TYPE_KIND_UNSPECIFIED = 0; - - // Encoded as a string in decimal format. - INT64 = 2; - - // Encoded as a boolean "false" or "true". - BOOL = 5; - - // Encoded as a number, or string "NaN", "Infinity" or "-Infinity". - FLOAT64 = 7; - - // Encoded as a string value. - STRING = 8; - - // Encoded as a base64 string per RFC 4648, section 4. - BYTES = 9; - - // Encoded as an RFC 3339 timestamp with mandatory "Z" time zone string: - // 1985-04-12T23:20:50.52Z - TIMESTAMP = 19; - - // Encoded as RFC 3339 full-date format string: 1985-04-12 - DATE = 10; - - // Encoded as RFC 3339 partial-time format string: 23:20:50.52 - TIME = 20; - - // Encoded as RFC 3339 full-date "T" partial-time: 1985-04-12T23:20:50.52 - DATETIME = 21; - - // Encoded as WKT - GEOGRAPHY = 22; - - // Encoded as a decimal string. - NUMERIC = 23; - - // Encoded as a decimal string. - BIGNUMERIC = 24; - - // Encoded as a list with types matching Type.array_type. - ARRAY = 16; - - // Encoded as a list with fields of type Type.struct_type[i]. List is used - // because a JSON object cannot have duplicate field names. - STRUCT = 17; - } - - // Required. The top level type of this field. - // Can be any standard SQL data type (e.g., "INT64", "DATE", "ARRAY"). - TypeKind type_kind = 1 [(google.api.field_behavior) = REQUIRED]; - - oneof sub_type { - // The type of the array's elements, if type_kind = "ARRAY". - StandardSqlDataType array_element_type = 2; - - // The fields of this struct, in order, if type_kind = "STRUCT". - StandardSqlStructType struct_type = 3; - } -} - -// A field or a column. -message StandardSqlField { - // Optional. The name of this field. Can be absent for struct fields. - string name = 1 [(google.api.field_behavior) = OPTIONAL]; - - // Optional. The type of this parameter. Absent if not explicitly - // specified (e.g., CREATE FUNCTION statement can omit the return type; - // in this case the output parameter does not have this "type" field). - StandardSqlDataType type = 2 [(google.api.field_behavior) = OPTIONAL]; -} - -message StandardSqlStructType { - repeated StandardSqlField fields = 1; -} diff --git a/google/cloud/bigquery_v2/proto/standard_sql_pb2.py b/google/cloud/bigquery_v2/proto/standard_sql_pb2.py deleted file mode 100644 index bfe77f934..000000000 --- a/google/cloud/bigquery_v2/proto/standard_sql_pb2.py +++ /dev/null @@ -1,442 +0,0 @@ -# -*- coding: utf-8 -*- -# Generated by the protocol buffer compiler. DO NOT EDIT! -# source: google/cloud/bigquery_v2/proto/standard_sql.proto -"""Generated protocol buffer code.""" -from google.protobuf import descriptor as _descriptor -from google.protobuf import message as _message -from google.protobuf import reflection as _reflection -from google.protobuf import symbol_database as _symbol_database - -# @@protoc_insertion_point(imports) - -_sym_db = _symbol_database.Default() - - -from google.api import field_behavior_pb2 as google_dot_api_dot_field__behavior__pb2 -from google.api import annotations_pb2 as google_dot_api_dot_annotations__pb2 - - -DESCRIPTOR = _descriptor.FileDescriptor( - name="google/cloud/bigquery_v2/proto/standard_sql.proto", - package="google.cloud.bigquery.v2", - syntax="proto3", - serialized_options=b"\n\034com.google.cloud.bigquery.v2B\020StandardSqlProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery", - create_key=_descriptor._internal_create_key, - serialized_pb=b'\n1google/cloud/bigquery_v2/proto/standard_sql.proto\x12\x18google.cloud.bigquery.v2\x1a\x1fgoogle/api/field_behavior.proto\x1a\x1cgoogle/api/annotations.proto"\xcb\x03\n\x13StandardSqlDataType\x12N\n\ttype_kind\x18\x01 \x01(\x0e\x32\x36.google.cloud.bigquery.v2.StandardSqlDataType.TypeKindB\x03\xe0\x41\x02\x12K\n\x12\x61rray_element_type\x18\x02 \x01(\x0b\x32-.google.cloud.bigquery.v2.StandardSqlDataTypeH\x00\x12\x46\n\x0bstruct_type\x18\x03 \x01(\x0b\x32/.google.cloud.bigquery.v2.StandardSqlStructTypeH\x00"\xc2\x01\n\x08TypeKind\x12\x19\n\x15TYPE_KIND_UNSPECIFIED\x10\x00\x12\t\n\x05INT64\x10\x02\x12\x08\n\x04\x42OOL\x10\x05\x12\x0b\n\x07\x46LOAT64\x10\x07\x12\n\n\x06STRING\x10\x08\x12\t\n\x05\x42YTES\x10\t\x12\r\n\tTIMESTAMP\x10\x13\x12\x08\n\x04\x44\x41TE\x10\n\x12\x08\n\x04TIME\x10\x14\x12\x0c\n\x08\x44\x41TETIME\x10\x15\x12\r\n\tGEOGRAPHY\x10\x16\x12\x0b\n\x07NUMERIC\x10\x17\x12\t\n\x05\x41RRAY\x10\x10\x12\n\n\x06STRUCT\x10\x11\x42\n\n\x08sub_type"g\n\x10StandardSqlField\x12\x11\n\x04name\x18\x01 \x01(\tB\x03\xe0\x41\x01\x12@\n\x04type\x18\x02 \x01(\x0b\x32-.google.cloud.bigquery.v2.StandardSqlDataTypeB\x03\xe0\x41\x01"S\n\x15StandardSqlStructType\x12:\n\x06\x66ields\x18\x01 \x03(\x0b\x32*.google.cloud.bigquery.v2.StandardSqlFieldBr\n\x1c\x63om.google.cloud.bigquery.v2B\x10StandardSqlProtoZ@google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigqueryb\x06proto3', - dependencies=[ - google_dot_api_dot_field__behavior__pb2.DESCRIPTOR, - google_dot_api_dot_annotations__pb2.DESCRIPTOR, - ], -) - - -_STANDARDSQLDATATYPE_TYPEKIND = _descriptor.EnumDescriptor( - name="TypeKind", - full_name="google.cloud.bigquery.v2.StandardSqlDataType.TypeKind", - filename=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - values=[ - _descriptor.EnumValueDescriptor( - name="TYPE_KIND_UNSPECIFIED", - index=0, - number=0, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="INT64", - index=1, - number=2, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="BOOL", - index=2, - number=5, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="FLOAT64", - index=3, - number=7, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="STRING", - index=4, - number=8, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="BYTES", - index=5, - number=9, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="TIMESTAMP", - index=6, - number=19, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="DATE", - index=7, - number=10, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="TIME", - index=8, - number=20, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="DATETIME", - index=9, - number=21, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="GEOGRAPHY", - index=10, - number=22, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="NUMERIC", - index=11, - number=23, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="ARRAY", - index=12, - number=16, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - _descriptor.EnumValueDescriptor( - name="STRUCT", - index=13, - number=17, - serialized_options=None, - type=None, - create_key=_descriptor._internal_create_key, - ), - ], - containing_type=None, - serialized_options=None, - serialized_start=396, - serialized_end=590, -) -_sym_db.RegisterEnumDescriptor(_STANDARDSQLDATATYPE_TYPEKIND) - - -_STANDARDSQLDATATYPE = _descriptor.Descriptor( - name="StandardSqlDataType", - full_name="google.cloud.bigquery.v2.StandardSqlDataType", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="type_kind", - full_name="google.cloud.bigquery.v2.StandardSqlDataType.type_kind", - index=0, - number=1, - type=14, - cpp_type=8, - label=1, - has_default_value=False, - default_value=0, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\002", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="array_element_type", - full_name="google.cloud.bigquery.v2.StandardSqlDataType.array_element_type", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="struct_type", - full_name="google.cloud.bigquery.v2.StandardSqlDataType.struct_type", - index=2, - number=3, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[_STANDARDSQLDATATYPE_TYPEKIND,], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[ - _descriptor.OneofDescriptor( - name="sub_type", - full_name="google.cloud.bigquery.v2.StandardSqlDataType.sub_type", - index=0, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[], - ), - ], - serialized_start=143, - serialized_end=602, -) - - -_STANDARDSQLFIELD = _descriptor.Descriptor( - name="StandardSqlField", - full_name="google.cloud.bigquery.v2.StandardSqlField", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="name", - full_name="google.cloud.bigquery.v2.StandardSqlField.name", - index=0, - number=1, - type=9, - cpp_type=9, - label=1, - has_default_value=False, - default_value=b"".decode("utf-8"), - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\001", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - _descriptor.FieldDescriptor( - name="type", - full_name="google.cloud.bigquery.v2.StandardSqlField.type", - index=1, - number=2, - type=11, - cpp_type=10, - label=1, - has_default_value=False, - default_value=None, - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=b"\340A\001", - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=604, - serialized_end=707, -) - - -_STANDARDSQLSTRUCTTYPE = _descriptor.Descriptor( - name="StandardSqlStructType", - full_name="google.cloud.bigquery.v2.StandardSqlStructType", - filename=None, - file=DESCRIPTOR, - containing_type=None, - create_key=_descriptor._internal_create_key, - fields=[ - _descriptor.FieldDescriptor( - name="fields", - full_name="google.cloud.bigquery.v2.StandardSqlStructType.fields", - index=0, - number=1, - type=11, - cpp_type=10, - label=3, - has_default_value=False, - default_value=[], - message_type=None, - enum_type=None, - containing_type=None, - is_extension=False, - extension_scope=None, - serialized_options=None, - file=DESCRIPTOR, - create_key=_descriptor._internal_create_key, - ), - ], - extensions=[], - nested_types=[], - enum_types=[], - serialized_options=None, - is_extendable=False, - syntax="proto3", - extension_ranges=[], - oneofs=[], - serialized_start=709, - serialized_end=792, -) - -_STANDARDSQLDATATYPE.fields_by_name[ - "type_kind" -].enum_type = _STANDARDSQLDATATYPE_TYPEKIND -_STANDARDSQLDATATYPE.fields_by_name[ - "array_element_type" -].message_type = _STANDARDSQLDATATYPE -_STANDARDSQLDATATYPE.fields_by_name["struct_type"].message_type = _STANDARDSQLSTRUCTTYPE -_STANDARDSQLDATATYPE_TYPEKIND.containing_type = _STANDARDSQLDATATYPE -_STANDARDSQLDATATYPE.oneofs_by_name["sub_type"].fields.append( - _STANDARDSQLDATATYPE.fields_by_name["array_element_type"] -) -_STANDARDSQLDATATYPE.fields_by_name[ - "array_element_type" -].containing_oneof = _STANDARDSQLDATATYPE.oneofs_by_name["sub_type"] -_STANDARDSQLDATATYPE.oneofs_by_name["sub_type"].fields.append( - _STANDARDSQLDATATYPE.fields_by_name["struct_type"] -) -_STANDARDSQLDATATYPE.fields_by_name[ - "struct_type" -].containing_oneof = _STANDARDSQLDATATYPE.oneofs_by_name["sub_type"] -_STANDARDSQLFIELD.fields_by_name["type"].message_type = _STANDARDSQLDATATYPE -_STANDARDSQLSTRUCTTYPE.fields_by_name["fields"].message_type = _STANDARDSQLFIELD -DESCRIPTOR.message_types_by_name["StandardSqlDataType"] = _STANDARDSQLDATATYPE -DESCRIPTOR.message_types_by_name["StandardSqlField"] = _STANDARDSQLFIELD -DESCRIPTOR.message_types_by_name["StandardSqlStructType"] = _STANDARDSQLSTRUCTTYPE -_sym_db.RegisterFileDescriptor(DESCRIPTOR) - -StandardSqlDataType = _reflection.GeneratedProtocolMessageType( - "StandardSqlDataType", - (_message.Message,), - { - "DESCRIPTOR": _STANDARDSQLDATATYPE, - "__module__": "google.cloud.bigquery_v2.proto.standard_sql_pb2", - "__doc__": """The type of a variable, e.g., a function argument. Examples: INT64: - {type_kind=``INT64``} ARRAY: {type_kind=``ARRAY``, - array_element_type=``STRING``} STRUCT: - {type_kind=``STRUCT``, struct_type={fields=[ {name=``x``, - type={type_kind=``STRING``}}, {name=``y``, type={type_kind=``ARRAY``, - array_element_type=``DATE``}} ]}} - - Attributes: - type_kind: - Required. The top level type of this field. Can be any - standard SQL data type (e.g., ``INT64``, ``DATE``, ``ARRAY``). - array_element_type: - The type of the array’s elements, if type_kind = ``ARRAY``. - struct_type: - The fields of this struct, in order, if type_kind = ``STRUCT``. - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.StandardSqlDataType) - }, -) -_sym_db.RegisterMessage(StandardSqlDataType) - -StandardSqlField = _reflection.GeneratedProtocolMessageType( - "StandardSqlField", - (_message.Message,), - { - "DESCRIPTOR": _STANDARDSQLFIELD, - "__module__": "google.cloud.bigquery_v2.proto.standard_sql_pb2", - "__doc__": """A field or a column. - - Attributes: - name: - Optional. The name of this field. Can be absent for struct - fields. - type: - Optional. The type of this parameter. Absent if not explicitly - specified (e.g., CREATE FUNCTION statement can omit the return - type; in this case the output parameter does not have this - ``type`` field). - """, - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.StandardSqlField) - }, -) -_sym_db.RegisterMessage(StandardSqlField) - -StandardSqlStructType = _reflection.GeneratedProtocolMessageType( - "StandardSqlStructType", - (_message.Message,), - { - "DESCRIPTOR": _STANDARDSQLSTRUCTTYPE, - "__module__": "google.cloud.bigquery_v2.proto.standard_sql_pb2" - # @@protoc_insertion_point(class_scope:google.cloud.bigquery.v2.StandardSqlStructType) - }, -) -_sym_db.RegisterMessage(StandardSqlStructType) - - -DESCRIPTOR._options = None -_STANDARDSQLDATATYPE.fields_by_name["type_kind"]._options = None -_STANDARDSQLFIELD.fields_by_name["name"]._options = None -_STANDARDSQLFIELD.fields_by_name["type"]._options = None -# @@protoc_insertion_point(module_scope) diff --git a/google/cloud/bigquery_v2/proto/table_reference.proto b/google/cloud/bigquery_v2/proto/table_reference.proto deleted file mode 100644 index ba02f80c4..000000000 --- a/google/cloud/bigquery_v2/proto/table_reference.proto +++ /dev/null @@ -1,39 +0,0 @@ -// Copyright 2020 Google LLC -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -syntax = "proto3"; - -package google.cloud.bigquery.v2; - -import "google/api/field_behavior.proto"; -import "google/api/annotations.proto"; - -option go_package = "google.golang.org/genproto/googleapis/cloud/bigquery/v2;bigquery"; -option java_outer_classname = "TableReferenceProto"; -option java_package = "com.google.cloud.bigquery.v2"; - -message TableReference { - // Required. The ID of the project containing this table. - string project_id = 1 [(google.api.field_behavior) = REQUIRED]; - - // Required. The ID of the dataset containing this table. - string dataset_id = 2 [(google.api.field_behavior) = REQUIRED]; - - // Required. The ID of the table. The ID must contain only - // letters (a-z, A-Z), numbers (0-9), or underscores (_). The maximum - // length is 1,024 characters. Certain operations allow - // suffixing of the table ID with a partition decorator, such as - // `sample_table$20190123`. - string table_id = 3 [(google.api.field_behavior) = REQUIRED]; -} diff --git a/google/cloud/bigquery_v2/types/__init__.py b/google/cloud/bigquery_v2/types/__init__.py index b76e65c65..83bbb3a54 100644 --- a/google/cloud/bigquery_v2/types/__init__.py +++ b/google/cloud/bigquery_v2/types/__init__.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -14,7 +13,6 @@ # See the License for the specific language governing permissions and # limitations under the License. # - from .encryption_config import EncryptionConfiguration from .model import ( DeleteModelRequest, @@ -29,6 +27,7 @@ StandardSqlDataType, StandardSqlField, StandardSqlStructType, + StandardSqlTableType, ) from .table_reference import TableReference @@ -44,5 +43,6 @@ "StandardSqlDataType", "StandardSqlField", "StandardSqlStructType", + "StandardSqlTableType", "TableReference", ) diff --git a/google/cloud/bigquery_v2/types/encryption_config.py b/google/cloud/bigquery_v2/types/encryption_config.py index 2d801bde3..4b9139733 100644 --- a/google/cloud/bigquery_v2/types/encryption_config.py +++ b/google/cloud/bigquery_v2/types/encryption_config.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -14,11 +13,9 @@ # See the License for the specific language governing permissions and # limitations under the License. # - import proto # type: ignore - -from google.protobuf import wrappers_pb2 as wrappers # type: ignore +from google.protobuf import wrappers_pb2 # type: ignore __protobuf__ = proto.module( @@ -28,7 +25,6 @@ class EncryptionConfiguration(proto.Message): r""" - Attributes: kms_key_name (google.protobuf.wrappers_pb2.StringValue): Optional. Describes the Cloud KMS encryption @@ -38,7 +34,9 @@ class EncryptionConfiguration(proto.Message): this encryption key. """ - kms_key_name = proto.Field(proto.MESSAGE, number=1, message=wrappers.StringValue,) + kms_key_name = proto.Field( + proto.MESSAGE, number=1, message=wrappers_pb2.StringValue, + ) __all__ = tuple(sorted(__protobuf__.manifest)) diff --git a/google/cloud/bigquery_v2/types/model.py b/google/cloud/bigquery_v2/types/model.py index 8ae158b64..706418401 100644 --- a/google/cloud/bigquery_v2/types/model.py +++ b/google/cloud/bigquery_v2/types/model.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -14,16 +13,14 @@ # See the License for the specific language governing permissions and # limitations under the License. # - import proto # type: ignore - from google.cloud.bigquery_v2.types import encryption_config from google.cloud.bigquery_v2.types import model_reference as gcb_model_reference from google.cloud.bigquery_v2.types import standard_sql from google.cloud.bigquery_v2.types import table_reference -from google.protobuf import timestamp_pb2 as timestamp # type: ignore -from google.protobuf import wrappers_pb2 as wrappers # type: ignore +from google.protobuf import timestamp_pb2 # type: ignore +from google.protobuf import wrappers_pb2 # type: ignore __protobuf__ = proto.module( @@ -41,7 +38,6 @@ class Model(proto.Message): r""" - Attributes: etag (str): Output only. A hash of this resource. @@ -100,6 +96,8 @@ class Model(proto.Message): Output only. Label columns that were used to train this model. The output of the model will have a `predicted_` prefix to these columns. + best_trial_id (int): + The best trial_id across all training runs. """ class ModelType(proto.Enum): @@ -117,6 +115,7 @@ class ModelType(proto.Enum): ARIMA = 11 AUTOML_REGRESSOR = 12 AUTOML_CLASSIFIER = 13 + ARIMA_PLUS = 19 class LossType(proto.Enum): r"""Loss metric to evaluate model training performance.""" @@ -155,6 +154,7 @@ class DataFrequency(proto.Enum): WEEKLY = 5 DAILY = 6 HOURLY = 7 + PER_MINUTE = 8 class HolidayRegion(proto.Enum): r"""Type of supported holiday regions for time series forecasting @@ -251,7 +251,7 @@ class FeedbackType(proto.Enum): EXPLICIT = 2 class SeasonalPeriod(proto.Message): - r"""""" + r""" """ class SeasonalPeriodType(proto.Enum): r"""""" @@ -264,7 +264,7 @@ class SeasonalPeriodType(proto.Enum): YEARLY = 6 class KmeansEnums(proto.Message): - r"""""" + r""" """ class KmeansInitializationMethod(proto.Enum): r"""Indicates the method used to initialize the centroids for @@ -289,26 +289,24 @@ class RegressionMetrics(proto.Message): median_absolute_error (google.protobuf.wrappers_pb2.DoubleValue): Median absolute error. r_squared (google.protobuf.wrappers_pb2.DoubleValue): - R^2 score. + R^2 score. This corresponds to r2_score in ML.EVALUATE. """ mean_absolute_error = proto.Field( - proto.MESSAGE, number=1, message=wrappers.DoubleValue, + proto.MESSAGE, number=1, message=wrappers_pb2.DoubleValue, ) - mean_squared_error = proto.Field( - proto.MESSAGE, number=2, message=wrappers.DoubleValue, + proto.MESSAGE, number=2, message=wrappers_pb2.DoubleValue, ) - mean_squared_log_error = proto.Field( - proto.MESSAGE, number=3, message=wrappers.DoubleValue, + proto.MESSAGE, number=3, message=wrappers_pb2.DoubleValue, ) - median_absolute_error = proto.Field( - proto.MESSAGE, number=4, message=wrappers.DoubleValue, + proto.MESSAGE, number=4, message=wrappers_pb2.DoubleValue, + ) + r_squared = proto.Field( + proto.MESSAGE, number=5, message=wrappers_pb2.DoubleValue, ) - - r_squared = proto.Field(proto.MESSAGE, number=5, message=wrappers.DoubleValue,) class AggregateClassificationMetrics(proto.Message): r"""Aggregate metrics for classification/classifier models. For @@ -350,19 +348,25 @@ class AggregateClassificationMetrics(proto.Message): is a macro-averaged metric. """ - precision = proto.Field(proto.MESSAGE, number=1, message=wrappers.DoubleValue,) - - recall = proto.Field(proto.MESSAGE, number=2, message=wrappers.DoubleValue,) - - accuracy = proto.Field(proto.MESSAGE, number=3, message=wrappers.DoubleValue,) - - threshold = proto.Field(proto.MESSAGE, number=4, message=wrappers.DoubleValue,) - - f1_score = proto.Field(proto.MESSAGE, number=5, message=wrappers.DoubleValue,) - - log_loss = proto.Field(proto.MESSAGE, number=6, message=wrappers.DoubleValue,) - - roc_auc = proto.Field(proto.MESSAGE, number=7, message=wrappers.DoubleValue,) + precision = proto.Field( + proto.MESSAGE, number=1, message=wrappers_pb2.DoubleValue, + ) + recall = proto.Field(proto.MESSAGE, number=2, message=wrappers_pb2.DoubleValue,) + accuracy = proto.Field( + proto.MESSAGE, number=3, message=wrappers_pb2.DoubleValue, + ) + threshold = proto.Field( + proto.MESSAGE, number=4, message=wrappers_pb2.DoubleValue, + ) + f1_score = proto.Field( + proto.MESSAGE, number=5, message=wrappers_pb2.DoubleValue, + ) + log_loss = proto.Field( + proto.MESSAGE, number=6, message=wrappers_pb2.DoubleValue, + ) + roc_auc = proto.Field( + proto.MESSAGE, number=7, message=wrappers_pb2.DoubleValue, + ) class BinaryClassificationMetrics(proto.Message): r"""Evaluation metrics for binary classification/classifier @@ -382,7 +386,6 @@ class BinaryClassificationMetrics(proto.Message): class BinaryConfusionMatrix(proto.Message): r"""Confusion matrix for binary classification models. - Attributes: positive_class_threshold (google.protobuf.wrappers_pb2.DoubleValue): Threshold value used when computing each of @@ -410,52 +413,43 @@ class BinaryConfusionMatrix(proto.Message): """ positive_class_threshold = proto.Field( - proto.MESSAGE, number=1, message=wrappers.DoubleValue, + proto.MESSAGE, number=1, message=wrappers_pb2.DoubleValue, ) - true_positives = proto.Field( - proto.MESSAGE, number=2, message=wrappers.Int64Value, + proto.MESSAGE, number=2, message=wrappers_pb2.Int64Value, ) - false_positives = proto.Field( - proto.MESSAGE, number=3, message=wrappers.Int64Value, + proto.MESSAGE, number=3, message=wrappers_pb2.Int64Value, ) - true_negatives = proto.Field( - proto.MESSAGE, number=4, message=wrappers.Int64Value, + proto.MESSAGE, number=4, message=wrappers_pb2.Int64Value, ) - false_negatives = proto.Field( - proto.MESSAGE, number=5, message=wrappers.Int64Value, + proto.MESSAGE, number=5, message=wrappers_pb2.Int64Value, ) - precision = proto.Field( - proto.MESSAGE, number=6, message=wrappers.DoubleValue, + proto.MESSAGE, number=6, message=wrappers_pb2.DoubleValue, + ) + recall = proto.Field( + proto.MESSAGE, number=7, message=wrappers_pb2.DoubleValue, ) - - recall = proto.Field(proto.MESSAGE, number=7, message=wrappers.DoubleValue,) - f1_score = proto.Field( - proto.MESSAGE, number=8, message=wrappers.DoubleValue, + proto.MESSAGE, number=8, message=wrappers_pb2.DoubleValue, ) - accuracy = proto.Field( - proto.MESSAGE, number=9, message=wrappers.DoubleValue, + proto.MESSAGE, number=9, message=wrappers_pb2.DoubleValue, ) aggregate_classification_metrics = proto.Field( proto.MESSAGE, number=1, message="Model.AggregateClassificationMetrics", ) - binary_confusion_matrix_list = proto.RepeatedField( proto.MESSAGE, number=2, message="Model.BinaryClassificationMetrics.BinaryConfusionMatrix", ) - - positive_label = proto.Field(proto.STRING, number=3) - - negative_label = proto.Field(proto.STRING, number=4) + positive_label = proto.Field(proto.STRING, number=3,) + negative_label = proto.Field(proto.STRING, number=4,) class MultiClassClassificationMetrics(proto.Message): r"""Evaluation metrics for multi-class classification/classifier @@ -470,7 +464,6 @@ class MultiClassClassificationMetrics(proto.Message): class ConfusionMatrix(proto.Message): r"""Confusion matrix for multi-class classification models. - Attributes: confidence_threshold (google.protobuf.wrappers_pb2.DoubleValue): Confidence threshold used when computing the @@ -481,7 +474,6 @@ class ConfusionMatrix(proto.Message): class Entry(proto.Message): r"""A single entry in the confusion matrix. - Attributes: predicted_label (str): The predicted label. For confidence_threshold > 0, we will @@ -492,15 +484,13 @@ class Entry(proto.Message): label. """ - predicted_label = proto.Field(proto.STRING, number=1) - + predicted_label = proto.Field(proto.STRING, number=1,) item_count = proto.Field( - proto.MESSAGE, number=2, message=wrappers.Int64Value, + proto.MESSAGE, number=2, message=wrappers_pb2.Int64Value, ) class Row(proto.Message): r"""A single row in the confusion matrix. - Attributes: actual_label (str): The original label of this row. @@ -508,8 +498,7 @@ class Row(proto.Message): Info describing predicted label distribution. """ - actual_label = proto.Field(proto.STRING, number=1) - + actual_label = proto.Field(proto.STRING, number=1,) entries = proto.RepeatedField( proto.MESSAGE, number=2, @@ -517,9 +506,8 @@ class Row(proto.Message): ) confidence_threshold = proto.Field( - proto.MESSAGE, number=1, message=wrappers.DoubleValue, + proto.MESSAGE, number=1, message=wrappers_pb2.DoubleValue, ) - rows = proto.RepeatedField( proto.MESSAGE, number=2, @@ -529,7 +517,6 @@ class Row(proto.Message): aggregate_classification_metrics = proto.Field( proto.MESSAGE, number=1, message="Model.AggregateClassificationMetrics", ) - confusion_matrix_list = proto.RepeatedField( proto.MESSAGE, number=2, @@ -538,7 +525,6 @@ class Row(proto.Message): class ClusteringMetrics(proto.Message): r"""Evaluation metrics for clustering models. - Attributes: davies_bouldin_index (google.protobuf.wrappers_pb2.DoubleValue): Davies-Bouldin index. @@ -546,12 +532,11 @@ class ClusteringMetrics(proto.Message): Mean of squared distances between each sample to its cluster centroid. clusters (Sequence[google.cloud.bigquery_v2.types.Model.ClusteringMetrics.Cluster]): - [Beta] Information for all clusters. + Information for all clusters. """ class Cluster(proto.Message): r"""Message containing the information about one cluster. - Attributes: centroid_id (int): Centroid id. @@ -565,7 +550,6 @@ class Cluster(proto.Message): class FeatureValue(proto.Message): r"""Representative value of a single feature within the cluster. - Attributes: feature_column (str): The feature column name. @@ -578,7 +562,6 @@ class FeatureValue(proto.Message): class CategoricalValue(proto.Message): r"""Representative value of a categorical feature. - Attributes: category_counts (Sequence[google.cloud.bigquery_v2.types.Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount]): Counts of all categories for the categorical feature. If @@ -590,7 +573,6 @@ class CategoricalValue(proto.Message): class CategoryCount(proto.Message): r"""Represents the count of a single category within the cluster. - Attributes: category (str): The name of category. @@ -599,10 +581,9 @@ class CategoryCount(proto.Message): category within the cluster. """ - category = proto.Field(proto.STRING, number=1) - + category = proto.Field(proto.STRING, number=1,) count = proto.Field( - proto.MESSAGE, number=2, message=wrappers.Int64Value, + proto.MESSAGE, number=2, message=wrappers_pb2.Int64Value, ) category_counts = proto.RepeatedField( @@ -611,15 +592,13 @@ class CategoryCount(proto.Message): message="Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue.CategoryCount", ) - feature_column = proto.Field(proto.STRING, number=1) - + feature_column = proto.Field(proto.STRING, number=1,) numerical_value = proto.Field( proto.MESSAGE, number=2, oneof="value", - message=wrappers.DoubleValue, + message=wrappers_pb2.DoubleValue, ) - categorical_value = proto.Field( proto.MESSAGE, number=3, @@ -627,24 +606,22 @@ class CategoryCount(proto.Message): message="Model.ClusteringMetrics.Cluster.FeatureValue.CategoricalValue", ) - centroid_id = proto.Field(proto.INT64, number=1) - + centroid_id = proto.Field(proto.INT64, number=1,) feature_values = proto.RepeatedField( proto.MESSAGE, number=2, message="Model.ClusteringMetrics.Cluster.FeatureValue", ) - - count = proto.Field(proto.MESSAGE, number=3, message=wrappers.Int64Value,) + count = proto.Field( + proto.MESSAGE, number=3, message=wrappers_pb2.Int64Value, + ) davies_bouldin_index = proto.Field( - proto.MESSAGE, number=1, message=wrappers.DoubleValue, + proto.MESSAGE, number=1, message=wrappers_pb2.DoubleValue, ) - mean_squared_distance = proto.Field( - proto.MESSAGE, number=2, message=wrappers.DoubleValue, + proto.MESSAGE, number=2, message=wrappers_pb2.DoubleValue, ) - clusters = proto.RepeatedField( proto.MESSAGE, number=3, message="Model.ClusteringMetrics.Cluster", ) @@ -677,24 +654,20 @@ class RankingMetrics(proto.Message): """ mean_average_precision = proto.Field( - proto.MESSAGE, number=1, message=wrappers.DoubleValue, + proto.MESSAGE, number=1, message=wrappers_pb2.DoubleValue, ) - mean_squared_error = proto.Field( - proto.MESSAGE, number=2, message=wrappers.DoubleValue, + proto.MESSAGE, number=2, message=wrappers_pb2.DoubleValue, ) - normalized_discounted_cumulative_gain = proto.Field( - proto.MESSAGE, number=3, message=wrappers.DoubleValue, + proto.MESSAGE, number=3, message=wrappers_pb2.DoubleValue, ) - average_rank = proto.Field( - proto.MESSAGE, number=4, message=wrappers.DoubleValue, + proto.MESSAGE, number=4, message=wrappers_pb2.DoubleValue, ) class ArimaForecastingMetrics(proto.Message): r"""Model evaluation metrics for ARIMA forecasting models. - Attributes: non_seasonal_order (Sequence[google.cloud.bigquery_v2.types.Model.ArimaOrder]): Non-seasonal order. @@ -728,44 +701,64 @@ class ArimaSingleModelForecastingMetrics(proto.Message): Is arima model fitted with drift or not. It is always false when d is not 1. time_series_id (str): - The id to indicate different time series. + The time_series_id value for this time series. It will be + one of the unique values from the time_series_id_column + specified during ARIMA model training. Only present when + time_series_id_column training option was used. + time_series_ids (Sequence[str]): + The tuple of time_series_ids identifying this time series. + It will be one of the unique tuples of values present in the + time_series_id_columns specified during ARIMA model + training. Only present when time_series_id_columns training + option was used and the order of values here are same as the + order of time_series_id_columns. seasonal_periods (Sequence[google.cloud.bigquery_v2.types.Model.SeasonalPeriod.SeasonalPeriodType]): Seasonal periods. Repeated because multiple periods are supported for one time series. + has_holiday_effect (google.protobuf.wrappers_pb2.BoolValue): + If true, holiday_effect is a part of time series + decomposition result. + has_spikes_and_dips (google.protobuf.wrappers_pb2.BoolValue): + If true, spikes_and_dips is a part of time series + decomposition result. + has_step_changes (google.protobuf.wrappers_pb2.BoolValue): + If true, step_changes is a part of time series decomposition + result. """ non_seasonal_order = proto.Field( proto.MESSAGE, number=1, message="Model.ArimaOrder", ) - arima_fitting_metrics = proto.Field( proto.MESSAGE, number=2, message="Model.ArimaFittingMetrics", ) - - has_drift = proto.Field(proto.BOOL, number=3) - - time_series_id = proto.Field(proto.STRING, number=4) - + has_drift = proto.Field(proto.BOOL, number=3,) + time_series_id = proto.Field(proto.STRING, number=4,) + time_series_ids = proto.RepeatedField(proto.STRING, number=9,) seasonal_periods = proto.RepeatedField( proto.ENUM, number=5, enum="Model.SeasonalPeriod.SeasonalPeriodType", ) + has_holiday_effect = proto.Field( + proto.MESSAGE, number=6, message=wrappers_pb2.BoolValue, + ) + has_spikes_and_dips = proto.Field( + proto.MESSAGE, number=7, message=wrappers_pb2.BoolValue, + ) + has_step_changes = proto.Field( + proto.MESSAGE, number=8, message=wrappers_pb2.BoolValue, + ) non_seasonal_order = proto.RepeatedField( proto.MESSAGE, number=1, message="Model.ArimaOrder", ) - arima_fitting_metrics = proto.RepeatedField( proto.MESSAGE, number=2, message="Model.ArimaFittingMetrics", ) - seasonal_periods = proto.RepeatedField( proto.ENUM, number=3, enum="Model.SeasonalPeriod.SeasonalPeriodType", ) - - has_drift = proto.RepeatedField(proto.BOOL, number=4) - - time_series_id = proto.RepeatedField(proto.STRING, number=5) - + has_drift = proto.RepeatedField(proto.BOOL, number=4,) + time_series_id = proto.RepeatedField(proto.STRING, number=5,) arima_single_model_forecasting_metrics = proto.RepeatedField( proto.MESSAGE, number=6, @@ -800,29 +793,24 @@ class EvaluationMetrics(proto.Message): regression_metrics = proto.Field( proto.MESSAGE, number=1, oneof="metrics", message="Model.RegressionMetrics", ) - binary_classification_metrics = proto.Field( proto.MESSAGE, number=2, oneof="metrics", message="Model.BinaryClassificationMetrics", ) - multi_class_classification_metrics = proto.Field( proto.MESSAGE, number=3, oneof="metrics", message="Model.MultiClassClassificationMetrics", ) - clustering_metrics = proto.Field( proto.MESSAGE, number=4, oneof="metrics", message="Model.ClusteringMetrics", ) - ranking_metrics = proto.Field( proto.MESSAGE, number=5, oneof="metrics", message="Model.RankingMetrics", ) - arima_forecasting_metrics = proto.Field( proto.MESSAGE, number=6, @@ -846,7 +834,6 @@ class DataSplitResult(proto.Message): training_table = proto.Field( proto.MESSAGE, number=1, message=table_reference.TableReference, ) - evaluation_table = proto.Field( proto.MESSAGE, number=2, message=table_reference.TableReference, ) @@ -864,15 +851,12 @@ class ArimaOrder(proto.Message): Order of the moving-average part. """ - p = proto.Field(proto.INT64, number=1) - - d = proto.Field(proto.INT64, number=2) - - q = proto.Field(proto.INT64, number=3) + p = proto.Field(proto.INT64, number=1,) + d = proto.Field(proto.INT64, number=2,) + q = proto.Field(proto.INT64, number=3,) class ArimaFittingMetrics(proto.Message): r"""ARIMA model fitting metrics. - Attributes: log_likelihood (float): Log-likelihood. @@ -882,11 +866,9 @@ class ArimaFittingMetrics(proto.Message): Variance. """ - log_likelihood = proto.Field(proto.DOUBLE, number=1) - - aic = proto.Field(proto.DOUBLE, number=2) - - variance = proto.Field(proto.DOUBLE, number=3) + log_likelihood = proto.Field(proto.DOUBLE, number=1,) + aic = proto.Field(proto.DOUBLE, number=2,) + variance = proto.Field(proto.DOUBLE, number=3,) class GlobalExplanation(proto.Message): r"""Global explanations containing the top most important @@ -906,7 +888,6 @@ class GlobalExplanation(proto.Message): class Explanation(proto.Message): r"""Explanation for a single feature. - Attributes: feature_name (str): Full name of the feature. For non-numerical features, will @@ -917,21 +898,18 @@ class Explanation(proto.Message): Attribution of feature. """ - feature_name = proto.Field(proto.STRING, number=1) - + feature_name = proto.Field(proto.STRING, number=1,) attribution = proto.Field( - proto.MESSAGE, number=2, message=wrappers.DoubleValue, + proto.MESSAGE, number=2, message=wrappers_pb2.DoubleValue, ) explanations = proto.RepeatedField( proto.MESSAGE, number=1, message="Model.GlobalExplanation.Explanation", ) - - class_label = proto.Field(proto.STRING, number=2) + class_label = proto.Field(proto.STRING, number=2,) class TrainingRun(proto.Message): r"""Information about a single training query run for the model. - Attributes: training_options (google.cloud.bigquery_v2.types.Model.TrainingRun.TrainingOptions): Options that were used for this training run, @@ -956,8 +934,7 @@ class TrainingRun(proto.Message): """ class TrainingOptions(proto.Message): - r""" - + r"""Options used in model training. Attributes: max_iterations (int): The maximum number of iterations in training. @@ -1028,8 +1005,9 @@ class TrainingOptions(proto.Message): num_clusters (int): Number of clusters for clustering models. model_uri (str): - [Beta] Google Cloud Storage URI from which the model was - imported. Only applicable for imported models. + Google Cloud Storage URI from which the model + was imported. Only applicable for imported + models. optimization_strategy (google.cloud.bigquery_v2.types.Model.OptimizationStrategy): Optimization strategy for training linear regression models. @@ -1086,8 +1064,11 @@ class TrainingOptions(proto.Message): If a valid value is specified, then holiday effects modeling is enabled. time_series_id_column (str): - The id column that will be used to indicate - different time series to forecast in parallel. + The time series id column that was used + during ARIMA model training. + time_series_id_columns (Sequence[str]): + The time series id columns that were used + during ARIMA model training. horizon (int): The number of periods ahead that need to be forecasted. @@ -1098,133 +1079,109 @@ class TrainingOptions(proto.Message): output feature name is A.b. auto_arima_max_order (int): The max value of non-seasonal p and q. + decompose_time_series (google.protobuf.wrappers_pb2.BoolValue): + If true, perform decompose time series and + save the results. + clean_spikes_and_dips (google.protobuf.wrappers_pb2.BoolValue): + If true, clean spikes and dips in the input + time series. + adjust_step_changes (google.protobuf.wrappers_pb2.BoolValue): + If true, detect step changes and make data + adjustment in the input time series. """ - max_iterations = proto.Field(proto.INT64, number=1) - + max_iterations = proto.Field(proto.INT64, number=1,) loss_type = proto.Field(proto.ENUM, number=2, enum="Model.LossType",) - - learn_rate = proto.Field(proto.DOUBLE, number=3) - + learn_rate = proto.Field(proto.DOUBLE, number=3,) l1_regularization = proto.Field( - proto.MESSAGE, number=4, message=wrappers.DoubleValue, + proto.MESSAGE, number=4, message=wrappers_pb2.DoubleValue, ) - l2_regularization = proto.Field( - proto.MESSAGE, number=5, message=wrappers.DoubleValue, + proto.MESSAGE, number=5, message=wrappers_pb2.DoubleValue, ) - min_relative_progress = proto.Field( - proto.MESSAGE, number=6, message=wrappers.DoubleValue, + proto.MESSAGE, number=6, message=wrappers_pb2.DoubleValue, ) - warm_start = proto.Field( - proto.MESSAGE, number=7, message=wrappers.BoolValue, + proto.MESSAGE, number=7, message=wrappers_pb2.BoolValue, ) - early_stop = proto.Field( - proto.MESSAGE, number=8, message=wrappers.BoolValue, + proto.MESSAGE, number=8, message=wrappers_pb2.BoolValue, ) - - input_label_columns = proto.RepeatedField(proto.STRING, number=9) - + input_label_columns = proto.RepeatedField(proto.STRING, number=9,) data_split_method = proto.Field( proto.ENUM, number=10, enum="Model.DataSplitMethod", ) - - data_split_eval_fraction = proto.Field(proto.DOUBLE, number=11) - - data_split_column = proto.Field(proto.STRING, number=12) - + data_split_eval_fraction = proto.Field(proto.DOUBLE, number=11,) + data_split_column = proto.Field(proto.STRING, number=12,) learn_rate_strategy = proto.Field( proto.ENUM, number=13, enum="Model.LearnRateStrategy", ) - - initial_learn_rate = proto.Field(proto.DOUBLE, number=16) - - label_class_weights = proto.MapField(proto.STRING, proto.DOUBLE, number=17) - - user_column = proto.Field(proto.STRING, number=18) - - item_column = proto.Field(proto.STRING, number=19) - + initial_learn_rate = proto.Field(proto.DOUBLE, number=16,) + label_class_weights = proto.MapField(proto.STRING, proto.DOUBLE, number=17,) + user_column = proto.Field(proto.STRING, number=18,) + item_column = proto.Field(proto.STRING, number=19,) distance_type = proto.Field( proto.ENUM, number=20, enum="Model.DistanceType", ) - - num_clusters = proto.Field(proto.INT64, number=21) - - model_uri = proto.Field(proto.STRING, number=22) - + num_clusters = proto.Field(proto.INT64, number=21,) + model_uri = proto.Field(proto.STRING, number=22,) optimization_strategy = proto.Field( proto.ENUM, number=23, enum="Model.OptimizationStrategy", ) - - hidden_units = proto.RepeatedField(proto.INT64, number=24) - - batch_size = proto.Field(proto.INT64, number=25) - + hidden_units = proto.RepeatedField(proto.INT64, number=24,) + batch_size = proto.Field(proto.INT64, number=25,) dropout = proto.Field( - proto.MESSAGE, number=26, message=wrappers.DoubleValue, + proto.MESSAGE, number=26, message=wrappers_pb2.DoubleValue, ) - - max_tree_depth = proto.Field(proto.INT64, number=27) - - subsample = proto.Field(proto.DOUBLE, number=28) - + max_tree_depth = proto.Field(proto.INT64, number=27,) + subsample = proto.Field(proto.DOUBLE, number=28,) min_split_loss = proto.Field( - proto.MESSAGE, number=29, message=wrappers.DoubleValue, + proto.MESSAGE, number=29, message=wrappers_pb2.DoubleValue, ) - - num_factors = proto.Field(proto.INT64, number=30) - + num_factors = proto.Field(proto.INT64, number=30,) feedback_type = proto.Field( proto.ENUM, number=31, enum="Model.FeedbackType", ) - wals_alpha = proto.Field( - proto.MESSAGE, number=32, message=wrappers.DoubleValue, + proto.MESSAGE, number=32, message=wrappers_pb2.DoubleValue, ) - kmeans_initialization_method = proto.Field( proto.ENUM, number=33, enum="Model.KmeansEnums.KmeansInitializationMethod", ) - - kmeans_initialization_column = proto.Field(proto.STRING, number=34) - - time_series_timestamp_column = proto.Field(proto.STRING, number=35) - - time_series_data_column = proto.Field(proto.STRING, number=36) - - auto_arima = proto.Field(proto.BOOL, number=37) - + kmeans_initialization_column = proto.Field(proto.STRING, number=34,) + time_series_timestamp_column = proto.Field(proto.STRING, number=35,) + time_series_data_column = proto.Field(proto.STRING, number=36,) + auto_arima = proto.Field(proto.BOOL, number=37,) non_seasonal_order = proto.Field( proto.MESSAGE, number=38, message="Model.ArimaOrder", ) - data_frequency = proto.Field( proto.ENUM, number=39, enum="Model.DataFrequency", ) - - include_drift = proto.Field(proto.BOOL, number=41) - + include_drift = proto.Field(proto.BOOL, number=41,) holiday_region = proto.Field( proto.ENUM, number=42, enum="Model.HolidayRegion", ) - - time_series_id_column = proto.Field(proto.STRING, number=43) - - horizon = proto.Field(proto.INT64, number=44) - - preserve_input_structs = proto.Field(proto.BOOL, number=45) - - auto_arima_max_order = proto.Field(proto.INT64, number=46) + time_series_id_column = proto.Field(proto.STRING, number=43,) + time_series_id_columns = proto.RepeatedField(proto.STRING, number=51,) + horizon = proto.Field(proto.INT64, number=44,) + preserve_input_structs = proto.Field(proto.BOOL, number=45,) + auto_arima_max_order = proto.Field(proto.INT64, number=46,) + decompose_time_series = proto.Field( + proto.MESSAGE, number=50, message=wrappers_pb2.BoolValue, + ) + clean_spikes_and_dips = proto.Field( + proto.MESSAGE, number=52, message=wrappers_pb2.BoolValue, + ) + adjust_step_changes = proto.Field( + proto.MESSAGE, number=53, message=wrappers_pb2.BoolValue, + ) class IterationResult(proto.Message): r"""Information about a single iteration of the training run. - Attributes: index (google.protobuf.wrappers_pb2.Int32Value): Index of the iteration, 0 based. @@ -1248,7 +1205,6 @@ class IterationResult(proto.Message): class ClusterInfo(proto.Message): r"""Information about a single cluster for clustering model. - Attributes: centroid_id (int): Centroid id. @@ -1260,14 +1216,12 @@ class ClusterInfo(proto.Message): assigned to the cluster. """ - centroid_id = proto.Field(proto.INT64, number=1) - + centroid_id = proto.Field(proto.INT64, number=1,) cluster_radius = proto.Field( - proto.MESSAGE, number=2, message=wrappers.DoubleValue, + proto.MESSAGE, number=2, message=wrappers_pb2.DoubleValue, ) - cluster_size = proto.Field( - proto.MESSAGE, number=3, message=wrappers.Int64Value, + proto.MESSAGE, number=3, message=wrappers_pb2.Int64Value, ) class ArimaResult(proto.Message): @@ -1287,7 +1241,6 @@ class ArimaResult(proto.Message): class ArimaCoefficients(proto.Message): r"""Arima coefficients. - Attributes: auto_regressive_coefficients (Sequence[float]): Auto-regressive coefficients, an array of @@ -1301,18 +1254,15 @@ class ArimaCoefficients(proto.Message): """ auto_regressive_coefficients = proto.RepeatedField( - proto.DOUBLE, number=1 + proto.DOUBLE, number=1, ) - moving_average_coefficients = proto.RepeatedField( - proto.DOUBLE, number=2 + proto.DOUBLE, number=2, ) - - intercept_coefficient = proto.Field(proto.DOUBLE, number=3) + intercept_coefficient = proto.Field(proto.DOUBLE, number=3,) class ArimaModelInfo(proto.Message): r"""Arima model information. - Attributes: non_seasonal_order (google.cloud.bigquery_v2.types.Model.ArimaOrder): Non-seasonal order. @@ -1324,70 +1274,89 @@ class ArimaModelInfo(proto.Message): Whether Arima model fitted with drift or not. It is always false when d is not 1. time_series_id (str): - The id to indicate different time series. + The time_series_id value for this time series. It will be + one of the unique values from the time_series_id_column + specified during ARIMA model training. Only present when + time_series_id_column training option was used. + time_series_ids (Sequence[str]): + The tuple of time_series_ids identifying this time series. + It will be one of the unique tuples of values present in the + time_series_id_columns specified during ARIMA model + training. Only present when time_series_id_columns training + option was used and the order of values here are same as the + order of time_series_id_columns. seasonal_periods (Sequence[google.cloud.bigquery_v2.types.Model.SeasonalPeriod.SeasonalPeriodType]): Seasonal periods. Repeated because multiple periods are supported for one time series. + has_holiday_effect (google.protobuf.wrappers_pb2.BoolValue): + If true, holiday_effect is a part of time series + decomposition result. + has_spikes_and_dips (google.protobuf.wrappers_pb2.BoolValue): + If true, spikes_and_dips is a part of time series + decomposition result. + has_step_changes (google.protobuf.wrappers_pb2.BoolValue): + If true, step_changes is a part of time series decomposition + result. """ non_seasonal_order = proto.Field( proto.MESSAGE, number=1, message="Model.ArimaOrder", ) - arima_coefficients = proto.Field( proto.MESSAGE, number=2, message="Model.TrainingRun.IterationResult.ArimaResult.ArimaCoefficients", ) - arima_fitting_metrics = proto.Field( proto.MESSAGE, number=3, message="Model.ArimaFittingMetrics", ) - - has_drift = proto.Field(proto.BOOL, number=4) - - time_series_id = proto.Field(proto.STRING, number=5) - + has_drift = proto.Field(proto.BOOL, number=4,) + time_series_id = proto.Field(proto.STRING, number=5,) + time_series_ids = proto.RepeatedField(proto.STRING, number=10,) seasonal_periods = proto.RepeatedField( proto.ENUM, number=6, enum="Model.SeasonalPeriod.SeasonalPeriodType", ) + has_holiday_effect = proto.Field( + proto.MESSAGE, number=7, message=wrappers_pb2.BoolValue, + ) + has_spikes_and_dips = proto.Field( + proto.MESSAGE, number=8, message=wrappers_pb2.BoolValue, + ) + has_step_changes = proto.Field( + proto.MESSAGE, number=9, message=wrappers_pb2.BoolValue, + ) arima_model_info = proto.RepeatedField( proto.MESSAGE, number=1, message="Model.TrainingRun.IterationResult.ArimaResult.ArimaModelInfo", ) - seasonal_periods = proto.RepeatedField( proto.ENUM, number=2, enum="Model.SeasonalPeriod.SeasonalPeriodType", ) - index = proto.Field(proto.MESSAGE, number=1, message=wrappers.Int32Value,) - + index = proto.Field( + proto.MESSAGE, number=1, message=wrappers_pb2.Int32Value, + ) duration_ms = proto.Field( - proto.MESSAGE, number=4, message=wrappers.Int64Value, + proto.MESSAGE, number=4, message=wrappers_pb2.Int64Value, ) - training_loss = proto.Field( - proto.MESSAGE, number=5, message=wrappers.DoubleValue, + proto.MESSAGE, number=5, message=wrappers_pb2.DoubleValue, ) - eval_loss = proto.Field( - proto.MESSAGE, number=6, message=wrappers.DoubleValue, + proto.MESSAGE, number=6, message=wrappers_pb2.DoubleValue, ) - - learn_rate = proto.Field(proto.DOUBLE, number=7) - + learn_rate = proto.Field(proto.DOUBLE, number=7,) cluster_infos = proto.RepeatedField( proto.MESSAGE, number=8, message="Model.TrainingRun.IterationResult.ClusterInfo", ) - arima_result = proto.Field( proto.MESSAGE, number=9, @@ -1397,65 +1366,49 @@ class ArimaModelInfo(proto.Message): training_options = proto.Field( proto.MESSAGE, number=1, message="Model.TrainingRun.TrainingOptions", ) - - start_time = proto.Field(proto.MESSAGE, number=8, message=timestamp.Timestamp,) - + start_time = proto.Field( + proto.MESSAGE, number=8, message=timestamp_pb2.Timestamp, + ) results = proto.RepeatedField( proto.MESSAGE, number=6, message="Model.TrainingRun.IterationResult", ) - evaluation_metrics = proto.Field( proto.MESSAGE, number=7, message="Model.EvaluationMetrics", ) - data_split_result = proto.Field( proto.MESSAGE, number=9, message="Model.DataSplitResult", ) - global_explanations = proto.RepeatedField( proto.MESSAGE, number=10, message="Model.GlobalExplanation", ) - etag = proto.Field(proto.STRING, number=1) - + etag = proto.Field(proto.STRING, number=1,) model_reference = proto.Field( proto.MESSAGE, number=2, message=gcb_model_reference.ModelReference, ) - - creation_time = proto.Field(proto.INT64, number=5) - - last_modified_time = proto.Field(proto.INT64, number=6) - - description = proto.Field(proto.STRING, number=12) - - friendly_name = proto.Field(proto.STRING, number=14) - - labels = proto.MapField(proto.STRING, proto.STRING, number=15) - - expiration_time = proto.Field(proto.INT64, number=16) - - location = proto.Field(proto.STRING, number=13) - + creation_time = proto.Field(proto.INT64, number=5,) + last_modified_time = proto.Field(proto.INT64, number=6,) + description = proto.Field(proto.STRING, number=12,) + friendly_name = proto.Field(proto.STRING, number=14,) + labels = proto.MapField(proto.STRING, proto.STRING, number=15,) + expiration_time = proto.Field(proto.INT64, number=16,) + location = proto.Field(proto.STRING, number=13,) encryption_configuration = proto.Field( proto.MESSAGE, number=17, message=encryption_config.EncryptionConfiguration, ) - model_type = proto.Field(proto.ENUM, number=7, enum=ModelType,) - training_runs = proto.RepeatedField(proto.MESSAGE, number=9, message=TrainingRun,) - feature_columns = proto.RepeatedField( proto.MESSAGE, number=10, message=standard_sql.StandardSqlField, ) - label_columns = proto.RepeatedField( proto.MESSAGE, number=11, message=standard_sql.StandardSqlField, ) + best_trial_id = proto.Field(proto.INT64, number=19,) class GetModelRequest(proto.Message): r""" - Attributes: project_id (str): Required. Project ID of the requested model. @@ -1465,16 +1418,13 @@ class GetModelRequest(proto.Message): Required. Model ID of the requested model. """ - project_id = proto.Field(proto.STRING, number=1) - - dataset_id = proto.Field(proto.STRING, number=2) - - model_id = proto.Field(proto.STRING, number=3) + project_id = proto.Field(proto.STRING, number=1,) + dataset_id = proto.Field(proto.STRING, number=2,) + model_id = proto.Field(proto.STRING, number=3,) class PatchModelRequest(proto.Message): r""" - Attributes: project_id (str): Required. Project ID of the model to patch. @@ -1489,18 +1439,14 @@ class PatchModelRequest(proto.Message): set to default value. """ - project_id = proto.Field(proto.STRING, number=1) - - dataset_id = proto.Field(proto.STRING, number=2) - - model_id = proto.Field(proto.STRING, number=3) - + project_id = proto.Field(proto.STRING, number=1,) + dataset_id = proto.Field(proto.STRING, number=2,) + model_id = proto.Field(proto.STRING, number=3,) model = proto.Field(proto.MESSAGE, number=4, message="Model",) class DeleteModelRequest(proto.Message): r""" - Attributes: project_id (str): Required. Project ID of the model to delete. @@ -1510,16 +1456,13 @@ class DeleteModelRequest(proto.Message): Required. Model ID of the model to delete. """ - project_id = proto.Field(proto.STRING, number=1) - - dataset_id = proto.Field(proto.STRING, number=2) - - model_id = proto.Field(proto.STRING, number=3) + project_id = proto.Field(proto.STRING, number=1,) + dataset_id = proto.Field(proto.STRING, number=2,) + model_id = proto.Field(proto.STRING, number=3,) class ListModelsRequest(proto.Message): r""" - Attributes: project_id (str): Required. Project ID of the models to list. @@ -1534,18 +1477,16 @@ class ListModelsRequest(proto.Message): request the next page of results """ - project_id = proto.Field(proto.STRING, number=1) - - dataset_id = proto.Field(proto.STRING, number=2) - - max_results = proto.Field(proto.MESSAGE, number=3, message=wrappers.UInt32Value,) - - page_token = proto.Field(proto.STRING, number=4) + project_id = proto.Field(proto.STRING, number=1,) + dataset_id = proto.Field(proto.STRING, number=2,) + max_results = proto.Field( + proto.MESSAGE, number=3, message=wrappers_pb2.UInt32Value, + ) + page_token = proto.Field(proto.STRING, number=4,) class ListModelsResponse(proto.Message): r""" - Attributes: models (Sequence[google.cloud.bigquery_v2.types.Model]): Models in the requested dataset. Only the following fields @@ -1560,8 +1501,7 @@ def raw_page(self): return self models = proto.RepeatedField(proto.MESSAGE, number=1, message="Model",) - - next_page_token = proto.Field(proto.STRING, number=2) + next_page_token = proto.Field(proto.STRING, number=2,) __all__ = tuple(sorted(__protobuf__.manifest)) diff --git a/google/cloud/bigquery_v2/types/model_reference.py b/google/cloud/bigquery_v2/types/model_reference.py index e3891d6c1..a9ebad613 100644 --- a/google/cloud/bigquery_v2/types/model_reference.py +++ b/google/cloud/bigquery_v2/types/model_reference.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -14,7 +13,6 @@ # See the License for the specific language governing permissions and # limitations under the License. # - import proto # type: ignore @@ -25,7 +23,6 @@ class ModelReference(proto.Message): r"""Id path of a model. - Attributes: project_id (str): Required. The ID of the project containing @@ -39,11 +36,9 @@ class ModelReference(proto.Message): maximum length is 1,024 characters. """ - project_id = proto.Field(proto.STRING, number=1) - - dataset_id = proto.Field(proto.STRING, number=2) - - model_id = proto.Field(proto.STRING, number=3) + project_id = proto.Field(proto.STRING, number=1,) + dataset_id = proto.Field(proto.STRING, number=2,) + model_id = proto.Field(proto.STRING, number=3,) __all__ = tuple(sorted(__protobuf__.manifest)) diff --git a/google/cloud/bigquery_v2/types/standard_sql.py b/google/cloud/bigquery_v2/types/standard_sql.py index 3bc6afedc..7a845fc48 100644 --- a/google/cloud/bigquery_v2/types/standard_sql.py +++ b/google/cloud/bigquery_v2/types/standard_sql.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -14,13 +13,17 @@ # See the License for the specific language governing permissions and # limitations under the License. # - import proto # type: ignore __protobuf__ = proto.module( package="google.cloud.bigquery.v2", - manifest={"StandardSqlDataType", "StandardSqlField", "StandardSqlStructType",}, + manifest={ + "StandardSqlDataType", + "StandardSqlField", + "StandardSqlStructType", + "StandardSqlTableType", + }, ) @@ -56,18 +59,18 @@ class TypeKind(proto.Enum): DATE = 10 TIME = 20 DATETIME = 21 + INTERVAL = 26 GEOGRAPHY = 22 NUMERIC = 23 BIGNUMERIC = 24 + JSON = 25 ARRAY = 16 STRUCT = 17 type_kind = proto.Field(proto.ENUM, number=1, enum=TypeKind,) - array_element_type = proto.Field( proto.MESSAGE, number=2, oneof="sub_type", message="StandardSqlDataType", ) - struct_type = proto.Field( proto.MESSAGE, number=3, oneof="sub_type", message="StandardSqlStructType", ) @@ -75,7 +78,6 @@ class TypeKind(proto.Enum): class StandardSqlField(proto.Message): r"""A field or a column. - Attributes: name (str): Optional. The name of this field. Can be @@ -88,14 +90,12 @@ class StandardSqlField(proto.Message): this "type" field). """ - name = proto.Field(proto.STRING, number=1) - + name = proto.Field(proto.STRING, number=1,) type = proto.Field(proto.MESSAGE, number=2, message="StandardSqlDataType",) class StandardSqlStructType(proto.Message): r""" - Attributes: fields (Sequence[google.cloud.bigquery_v2.types.StandardSqlField]): @@ -104,4 +104,14 @@ class StandardSqlStructType(proto.Message): fields = proto.RepeatedField(proto.MESSAGE, number=1, message="StandardSqlField",) +class StandardSqlTableType(proto.Message): + r"""A table type + Attributes: + columns (Sequence[google.cloud.bigquery_v2.types.StandardSqlField]): + The columns in this table type + """ + + columns = proto.RepeatedField(proto.MESSAGE, number=1, message="StandardSqlField",) + + __all__ = tuple(sorted(__protobuf__.manifest)) diff --git a/google/cloud/bigquery_v2/types/table_reference.py b/google/cloud/bigquery_v2/types/table_reference.py index d213e8bb6..d56e5b09f 100644 --- a/google/cloud/bigquery_v2/types/table_reference.py +++ b/google/cloud/bigquery_v2/types/table_reference.py @@ -1,5 +1,4 @@ # -*- coding: utf-8 -*- - # Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); @@ -14,7 +13,6 @@ # See the License for the specific language governing permissions and # limitations under the License. # - import proto # type: ignore @@ -25,7 +23,6 @@ class TableReference(proto.Message): r""" - Attributes: project_id (str): Required. The ID of the project containing @@ -39,13 +36,23 @@ class TableReference(proto.Message): maximum length is 1,024 characters. Certain operations allow suffixing of the table ID with a partition decorator, such as ``sample_table$20190123``. + project_id_alternative (Sequence[str]): + The alternative field that will be used when ESF is not able + to translate the received data to the project_id field. + dataset_id_alternative (Sequence[str]): + The alternative field that will be used when ESF is not able + to translate the received data to the project_id field. + table_id_alternative (Sequence[str]): + The alternative field that will be used when ESF is not able + to translate the received data to the project_id field. """ - project_id = proto.Field(proto.STRING, number=1) - - dataset_id = proto.Field(proto.STRING, number=2) - - table_id = proto.Field(proto.STRING, number=3) + project_id = proto.Field(proto.STRING, number=1,) + dataset_id = proto.Field(proto.STRING, number=2,) + table_id = proto.Field(proto.STRING, number=3,) + project_id_alternative = proto.RepeatedField(proto.STRING, number=4,) + dataset_id_alternative = proto.RepeatedField(proto.STRING, number=5,) + table_id_alternative = proto.RepeatedField(proto.STRING, number=6,) __all__ = tuple(sorted(__protobuf__.manifest)) diff --git a/noxfile.py b/noxfile.py index a52025635..9077924e9 100644 --- a/noxfile.py +++ b/noxfile.py @@ -142,6 +142,9 @@ def system(session): else: session.install("google-cloud-storage", "-c", constraints_path) + # Data Catalog needed for the column ACL test with a real Policy Tag. + session.install("google-cloud-datacatalog", "-c", constraints_path) + session.install("-e", ".[all]", "-c", constraints_path) session.install("ipython", "-c", constraints_path) @@ -157,10 +160,6 @@ def snippets(session): if os.environ.get("RUN_SNIPPETS_TESTS", "true") == "false": session.skip("RUN_SNIPPETS_TESTS is set to false, skipping") - # Sanity check: Only run snippets tests if the environment variable is set. - if not os.environ.get("GOOGLE_APPLICATION_CREDENTIALS", ""): - session.skip("Credentials must be set via environment variable.") - constraints_path = str( CURRENT_DIRECTORY / "testing" / f"constraints-{session.python}.txt" ) @@ -211,6 +210,7 @@ def prerelease_deps(session): session.install("--pre", "grpcio", "pandas") session.install( "freezegun", + "google-cloud-datacatalog", "google-cloud-storage", "google-cloud-testutils", "IPython", @@ -271,7 +271,7 @@ def blacken(session): def docs(session): """Build the docs.""" - session.install("ipython", "recommonmark", "sphinx", "sphinx_rtd_theme") + session.install("ipython", "recommonmark", "sphinx==4.0.1", "sphinx_rtd_theme") session.install("google-cloud-storage") session.install("-e", ".[all]") @@ -295,7 +295,9 @@ def docfx(session): """Build the docfx yaml files for this library.""" session.install("-e", ".") - session.install("sphinx", "alabaster", "recommonmark", "gcp-sphinx-docfx-yaml") + session.install( + "sphinx==4.0.1", "alabaster", "recommonmark", "gcp-sphinx-docfx-yaml" + ) shutil.rmtree(os.path.join("docs", "_build"), ignore_errors=True) session.run( diff --git a/owlbot.py b/owlbot.py index f45c24fbb..8664b658a 100644 --- a/owlbot.py +++ b/owlbot.py @@ -24,19 +24,32 @@ default_version = "v2" for library in s.get_staging_dirs(default_version): - # Do not expose ModelServiceClient, as there is no public API endpoint for the - # models service. + # Do not expose ModelServiceClient and ModelServiceAsyncClient, as there + # is no public API endpoint for the models service. s.replace( library / f"google/cloud/bigquery_{library.name}/__init__.py", r"from \.services\.model_service import ModelServiceClient", "", ) + + s.replace( + library / f"google/cloud/bigquery_{library.name}/__init__.py", + r"from \.services\.model_service import ModelServiceAsyncClient", + "", + ) + s.replace( library / f"google/cloud/bigquery_{library.name}/__init__.py", r"""["']ModelServiceClient["'],""", "", ) + s.replace( + library / f"google/cloud/bigquery_{library.name}/__init__.py", + r"""["']ModelServiceAsyncClient["'],""", + "", + ) + # Adjust Model docstring so that Sphinx does not think that "predicted_" is # a reference to something, issuing a false warning. s.replace( @@ -50,13 +63,14 @@ s.replace( library / f"google/cloud/bigquery_{library.name}/types/standard_sql.py", r"type_ ", - "type " + "type ", ) s.move( library, excludes=[ "*.tar.gz", + ".coveragerc", "docs/index.rst", f"docs/bigquery_{library.name}/*_service.rst", f"docs/bigquery_{library.name}/services.rst", @@ -64,8 +78,8 @@ "noxfile.py", "setup.py", f"scripts/fixup_bigquery_{library.name}_keywords.py", - f"google/cloud/bigquery/__init__.py", - f"google/cloud/bigquery/py.typed", + "google/cloud/bigquery/__init__.py", + "google/cloud/bigquery/py.typed", # There are no public API endpoints for the generated ModelServiceClient, # thus there's no point in generating it and its tests. f"google/cloud/bigquery_{library.name}/services/**", @@ -83,6 +97,10 @@ samples=True, microgenerator=True, split_system_tests=True, + intersphinx_dependencies={ + "pandas": "http://pandas.pydata.org/pandas-docs/dev", + "geopandas": "https://geopandas.org/", + }, ) # BigQuery has a custom multiprocessing note @@ -95,7 +113,11 @@ # Include custom SNIPPETS_TESTS job for performance. # https://github.com/googleapis/python-bigquery/issues/191 ".kokoro/presubmit/presubmit.cfg", - ] + # Group all renovate PRs together. If this works well, remove this and + # update the shared templates (possibly with configuration option to + # py_library.) + "renovate.json", + ], ) # ---------------------------------------------------------------------------- @@ -107,14 +129,14 @@ s.replace( "docs/conf.py", r'\{"members": True\}', - '{"members": True, "inherited-members": True}' + '{"members": True, "inherited-members": True}', ) # Tell Sphinx to ingore autogenerated docs files. s.replace( "docs/conf.py", r'"samples/snippets/README\.rst",', - '\g<0>\n "bigquery_v2/services.rst", # generated by the code generator', + '\\g<0>\n "bigquery_v2/services.rst", # generated by the code generator', ) # ---------------------------------------------------------------------------- @@ -122,13 +144,14 @@ # ---------------------------------------------------------------------------- # Add .pytype to .gitignore -s.replace(".gitignore", r"\.pytest_cache", "\g<0>\n.pytype") +s.replace(".gitignore", r"\.pytest_cache", "\\g<0>\n.pytype") # Add pytype config to setup.cfg s.replace( "setup.cfg", r"universal = 1", - textwrap.dedent(""" \g<0> + textwrap.dedent( + """ \\g<0> [pytype] python_version = 3.8 @@ -142,7 +165,8 @@ # There's some issue with finding some pyi files, thus disabling. # The issue https://github.com/google/pytype/issues/150 is closed, but the # error still occurs for some reason. - pyi-error""") + pyi-error""" + ), ) s.shell.run(["nox", "-s", "blacken"], hide_output=False) diff --git a/renovate.json b/renovate.json index c04895563..713c60bb4 100644 --- a/renovate.json +++ b/renovate.json @@ -1,6 +1,6 @@ { "extends": [ - "config:base", ":preserveSemverRanges" + "config:base", "group:all", ":preserveSemverRanges" ], "ignorePaths": [".pre-commit-config.yaml"], "pip_requirements": { diff --git a/samples/client_query_w_timestamp_params.py b/samples/client_query_w_timestamp_params.py index ca8eec0b5..41a27770e 100644 --- a/samples/client_query_w_timestamp_params.py +++ b/samples/client_query_w_timestamp_params.py @@ -18,7 +18,6 @@ def client_query_w_timestamp_params(): # [START bigquery_query_params_timestamps] import datetime - import pytz from google.cloud import bigquery # Construct a BigQuery client object. @@ -30,7 +29,7 @@ def client_query_w_timestamp_params(): bigquery.ScalarQueryParameter( "ts_value", "TIMESTAMP", - datetime.datetime(2016, 12, 7, 8, 0, tzinfo=pytz.UTC), + datetime.datetime(2016, 12, 7, 8, 0, tzinfo=datetime.timezone.utc), ) ] ) diff --git a/samples/create_routine.py b/samples/create_routine.py index 012c7927a..1cb4a80b4 100644 --- a/samples/create_routine.py +++ b/samples/create_routine.py @@ -22,7 +22,7 @@ def create_routine(routine_id): # Construct a BigQuery client object. client = bigquery.Client() - # TODO(developer): Choose a fully-qualified ID for the routine. + # TODO(developer): Choose a fully qualified ID for the routine. # routine_id = "my-project.my_dataset.my_routine" routine = bigquery.Routine( diff --git a/samples/geography/noxfile.py b/samples/geography/noxfile.py index be1a3f251..b008613f0 100644 --- a/samples/geography/noxfile.py +++ b/samples/geography/noxfile.py @@ -28,8 +28,9 @@ # WARNING - WARNING - WARNING - WARNING - WARNING # WARNING - WARNING - WARNING - WARNING - WARNING -# Copy `noxfile_config.py` to your directory and modify it instead. +BLACK_VERSION = "black==19.10b0" +# Copy `noxfile_config.py` to your directory and modify it instead. # `TEST_CONFIG` dict is a configuration hook that allows users to # modify the test configurations. The values here should be in sync @@ -38,7 +39,7 @@ TEST_CONFIG = { # You can opt out from the test for specific Python versions. - "ignored_versions": ["2.7"], + "ignored_versions": [], # Old samples are opted out of enforcing Python type hints # All new samples should feature them "enforce_type_hints": False, @@ -48,6 +49,10 @@ # to use your own Cloud project. "gcloud_project_env": "GOOGLE_CLOUD_PROJECT", # 'gcloud_project_env': 'BUILD_SPECIFIC_GCLOUD_PROJECT', + # If you need to use a specific version of pip, + # change pip_version_override to the string representation + # of the version number, for example, "20.2.4" + "pip_version_override": None, # A dictionary you want to inject into your test. Don't put any # secrets here. These values will override predefined values. "envs": {}, @@ -81,15 +86,18 @@ def get_pytest_env_vars() -> Dict[str, str]: # DO NOT EDIT - automatically generated. -# All versions used to tested samples. -ALL_VERSIONS = ["2.7", "3.6", "3.7", "3.8", "3.9"] +# All versions used to test samples. +ALL_VERSIONS = ["3.6", "3.7", "3.8", "3.9"] # Any default versions that should be ignored. IGNORED_VERSIONS = TEST_CONFIG["ignored_versions"] TESTED_VERSIONS = sorted([v for v in ALL_VERSIONS if v not in IGNORED_VERSIONS]) -INSTALL_LIBRARY_FROM_SOURCE = bool(os.environ.get("INSTALL_LIBRARY_FROM_SOURCE", False)) +INSTALL_LIBRARY_FROM_SOURCE = os.environ.get("INSTALL_LIBRARY_FROM_SOURCE", False) in ( + "True", + "true", +) # # Style Checks # @@ -155,7 +163,7 @@ def lint(session: nox.sessions.Session) -> None: @nox.session def blacken(session: nox.sessions.Session) -> None: - session.install("black") + session.install(BLACK_VERSION) python_files = [path for path in os.listdir(".") if path.endswith(".py")] session.run("black", *python_files) @@ -172,6 +180,9 @@ def blacken(session: nox.sessions.Session) -> None: def _session_tests( session: nox.sessions.Session, post_install: Callable = None ) -> None: + if TEST_CONFIG["pip_version_override"]: + pip_version = TEST_CONFIG["pip_version_override"] + session.install(f"pip=={pip_version}") """Runs py.test for a particular project.""" if os.path.exists("requirements.txt"): if os.path.exists("constraints.txt"): @@ -198,7 +209,7 @@ def _session_tests( # on travis where slow and flaky tests are excluded. # See http://doc.pytest.org/en/latest/_modules/_pytest/main.html success_codes=[0, 5], - env=get_pytest_env_vars() + env=get_pytest_env_vars(), ) diff --git a/samples/geography/requirements.txt b/samples/geography/requirements.txt index e494fbaae..b5fe247cb 100644 --- a/samples/geography/requirements.txt +++ b/samples/geography/requirements.txt @@ -1,4 +1,50 @@ +attrs==21.2.0 +cachetools==4.2.2 +certifi==2021.5.30 +cffi==1.14.6 +charset-normalizer==2.0.4 +click==8.0.1 +click-plugins==1.1.1 +cligj==0.7.2 +dataclasses==0.6; python_version < '3.7' +Fiona==1.8.20 geojson==2.5.0 -google-cloud-bigquery==2.16.1 -google-cloud-bigquery-storage==2.4.0 +geopandas==0.9.0 +google-api-core==1.31.2 +google-auth==1.35.0 +google-cloud-bigquery==2.25.0 +google-cloud-bigquery-storage==2.6.3 +google-cloud-core==2.0.0 +google-crc32c==1.1.2 +google-resumable-media==1.3.3 +googleapis-common-protos==1.53.0 +grpcio==1.39.0 +idna==3.2 +importlib-metadata==4.6.4 +libcst==0.3.20 +munch==2.5.0 +mypy-extensions==0.4.3 +numpy==1.19.5; python_version < "3.7" +numpy==1.21.2; python_version > "3.6" +packaging==21.0 +pandas==1.1.5; python_version < '3.7' +pandas==1.3.2; python_version >= '3.7' +proto-plus==1.19.0 +protobuf==3.17.3 +pyarrow==5.0.0 +pyasn1==0.4.8 +pyasn1-modules==0.2.8 +pycparser==2.20 +pyparsing==2.4.7 +pyproj==3.0.1 +python-dateutil==2.8.2 +pytz==2021.1 +PyYAML==5.4.1 +requests==2.26.0 +rsa==4.7.2 Shapely==1.7.1 +six==1.16.0 +typing-extensions==3.10.0.0 +typing-inspect==0.7.1 +urllib3==1.26.6 +zipp==3.5.0 diff --git a/samples/geography/to_geodataframe.py b/samples/geography/to_geodataframe.py new file mode 100644 index 000000000..fa8073fef --- /dev/null +++ b/samples/geography/to_geodataframe.py @@ -0,0 +1,32 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from google.cloud import bigquery + +client = bigquery.Client() + + +def get_austin_service_requests_as_geography(): + # [START bigquery_query_results_geodataframe] + + sql = """ + SELECT created_date, complaint_description, + ST_GEOGPOINT(longitude, latitude) as location + FROM bigquery-public-data.austin_311.311_service_requests + LIMIT 10 + """ + + df = client.query(sql).to_geodataframe() + # [END bigquery_query_results_geodataframe] + return df diff --git a/samples/geography/to_geodataframe_test.py b/samples/geography/to_geodataframe_test.py new file mode 100644 index 000000000..7a2ba6937 --- /dev/null +++ b/samples/geography/to_geodataframe_test.py @@ -0,0 +1,25 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import pytest + +from .to_geodataframe import get_austin_service_requests_as_geography + + +def test_get_austin_service_requests_as_geography(): + geopandas = pytest.importorskip("geopandas") + df = get_austin_service_requests_as_geography() + assert isinstance(df, geopandas.GeoDataFrame) + assert len(list(df)) == 3 # verify the number of columns + assert len(df) == 10 # verify the number of rows diff --git a/samples/snippets/conftest.py b/samples/snippets/conftest.py index 0d0299ee5..74984f902 100644 --- a/samples/snippets/conftest.py +++ b/samples/snippets/conftest.py @@ -12,38 +12,18 @@ # See the License for the specific language governing permissions and # limitations under the License. -import datetime -import random - from google.cloud import bigquery import pytest +import test_utils.prefixer -RESOURCE_PREFIX = "python_bigquery_samples_snippets" -RESOURCE_DATE_FORMAT = "%Y%m%d_%H%M%S" -RESOURCE_DATE_LENGTH = 4 + 2 + 2 + 1 + 2 + 2 + 2 - - -def resource_prefix() -> str: - timestamp = datetime.datetime.utcnow().strftime(RESOURCE_DATE_FORMAT) - random_string = hex(random.randrange(1000000))[2:] - return f"{RESOURCE_PREFIX}_{timestamp}_{random_string}" - - -def resource_name_to_date(resource_name: str): - start_date = len(RESOURCE_PREFIX) + 1 - date_string = resource_name[start_date : start_date + RESOURCE_DATE_LENGTH] - return datetime.strptime(date_string, RESOURCE_DATE_FORMAT) +prefixer = test_utils.prefixer.Prefixer("python-bigquery", "samples/snippets") @pytest.fixture(scope="session", autouse=True) def cleanup_datasets(bigquery_client: bigquery.Client): - yesterday = datetime.datetime.utcnow() - datetime.timedelta(days=1) for dataset in bigquery_client.list_datasets(): - if ( - dataset.dataset_id.startswith(RESOURCE_PREFIX) - and resource_name_to_date(dataset.dataset_id) < yesterday - ): + if prefixer.should_cleanup(dataset.dataset_id): bigquery_client.delete_dataset( dataset, delete_contents=True, not_found_ok=True ) @@ -62,7 +42,7 @@ def project_id(bigquery_client): @pytest.fixture(scope="session") def dataset_id(bigquery_client: bigquery.Client, project_id: str): - dataset_id = resource_prefix() + dataset_id = prefixer.create_prefix() full_dataset_id = f"{project_id}.{dataset_id}" dataset = bigquery.Dataset(full_dataset_id) bigquery_client.create_dataset(dataset) @@ -70,6 +50,42 @@ def dataset_id(bigquery_client: bigquery.Client, project_id: str): bigquery_client.delete_dataset(dataset, delete_contents=True, not_found_ok=True) +@pytest.fixture(scope="session") +def dataset_id_us_east1(bigquery_client: bigquery.Client, project_id: str): + dataset_id = prefixer.create_prefix() + full_dataset_id = f"{project_id}.{dataset_id}" + dataset = bigquery.Dataset(full_dataset_id) + dataset.location = "us-east1" + bigquery_client.create_dataset(dataset) + yield dataset_id + bigquery_client.delete_dataset(dataset, delete_contents=True, not_found_ok=True) + + +@pytest.fixture(scope="session") +def table_id_us_east1( + bigquery_client: bigquery.Client, project_id: str, dataset_id_us_east1: str +): + table_id = prefixer.create_prefix() + full_table_id = f"{project_id}.{dataset_id_us_east1}.{table_id}" + table = bigquery.Table( + full_table_id, schema=[bigquery.SchemaField("string_col", "STRING")] + ) + bigquery_client.create_table(table) + yield full_table_id + bigquery_client.delete_table(table, not_found_ok=True) + + +@pytest.fixture +def random_table_id(bigquery_client: bigquery.Client, project_id: str, dataset_id: str): + """Create a new table ID each time, so random_table_id can be used as + target for load jobs. + """ + random_table_id = prefixer.create_prefix() + full_table_id = f"{project_id}.{dataset_id}.{random_table_id}" + yield full_table_id + bigquery_client.delete_table(full_table_id, not_found_ok=True) + + @pytest.fixture def bigquery_client_patch(monkeypatch, bigquery_client): monkeypatch.setattr(bigquery, "Client", lambda: bigquery_client) diff --git a/samples/snippets/delete_job.py b/samples/snippets/delete_job.py new file mode 100644 index 000000000..abed0c90d --- /dev/null +++ b/samples/snippets/delete_job.py @@ -0,0 +1,44 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + + +def delete_job_metadata(job_id: str, location: str): + orig_job_id = job_id + orig_location = location + # [START bigquery_delete_job] + from google.cloud import bigquery + from google.api_core import exceptions + + # TODO(developer): Set the job ID to the ID of the job whose metadata you + # wish to delete. + job_id = "abcd-efgh-ijkl-mnop" + + # TODO(developer): Set the location to the region or multi-region + # containing the job. + location = "us-east1" + + # [END bigquery_delete_job] + job_id = orig_job_id + location = orig_location + + # [START bigquery_delete_job] + client = bigquery.Client() + + client.delete_job_metadata(job_id, location=location) + + try: + client.get_job(job_id, location=location) + except exceptions.NotFound: + print(f"Job metadata for job {location}:{job_id} was deleted.") + # [END bigquery_delete_job] diff --git a/samples/snippets/delete_job_test.py b/samples/snippets/delete_job_test.py new file mode 100644 index 000000000..c9baa817d --- /dev/null +++ b/samples/snippets/delete_job_test.py @@ -0,0 +1,33 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from google.cloud import bigquery + +import delete_job + + +def test_delete_job_metadata( + capsys, bigquery_client: bigquery.Client, table_id_us_east1: str +): + query_job: bigquery.QueryJob = bigquery_client.query( + f"SELECT COUNT(*) FROM `{table_id_us_east1}`", location="us-east1", + ) + query_job.result() + assert query_job.job_id is not None + + delete_job.delete_job_metadata(query_job.job_id, "us-east1") + + out, _ = capsys.readouterr() + assert "deleted" in out + assert f"us-east1:{query_job.job_id}" in out diff --git a/samples/snippets/load_table_uri_firestore.py b/samples/snippets/load_table_uri_firestore.py new file mode 100644 index 000000000..bf9d01349 --- /dev/null +++ b/samples/snippets/load_table_uri_firestore.py @@ -0,0 +1,55 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + + +def load_table_uri_firestore(table_id): + orig_table_id = table_id + # [START bigquery_load_table_gcs_firestore] + # TODO(developer): Set table_id to the ID of the table to create. + table_id = "your-project.your_dataset.your_table_name" + + # TODO(developer): Set uri to the path of the kind export metadata + uri = ( + "gs://cloud-samples-data/bigquery/us-states" + "/2021-07-02T16:04:48_70344/all_namespaces/kind_us-states" + "/all_namespaces_kind_us-states.export_metadata" + ) + + # TODO(developer): Set projection_fields to a list of document properties + # to import. Leave unset or set to `None` for all fields. + projection_fields = ["name", "post_abbr"] + + # [END bigquery_load_table_gcs_firestore] + table_id = orig_table_id + + # [START bigquery_load_table_gcs_firestore] + from google.cloud import bigquery + + # Construct a BigQuery client object. + client = bigquery.Client() + + job_config = bigquery.LoadJobConfig( + source_format=bigquery.SourceFormat.DATASTORE_BACKUP, + projection_fields=projection_fields, + ) + + load_job = client.load_table_from_uri( + uri, table_id, job_config=job_config + ) # Make an API request. + + load_job.result() # Waits for the job to complete. + + destination_table = client.get_table(table_id) + print("Loaded {} rows.".format(destination_table.num_rows)) + # [END bigquery_load_table_gcs_firestore] diff --git a/samples/snippets/load_table_uri_firestore_test.py b/samples/snippets/load_table_uri_firestore_test.py new file mode 100644 index 000000000..ffa02cdf9 --- /dev/null +++ b/samples/snippets/load_table_uri_firestore_test.py @@ -0,0 +1,21 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import load_table_uri_firestore + + +def test_load_table_uri_firestore(capsys, random_table_id): + load_table_uri_firestore.load_table_uri_firestore(random_table_id) + out, _ = capsys.readouterr() + assert "Loaded 50 rows." in out diff --git a/samples/snippets/noxfile.py b/samples/snippets/noxfile.py index be1a3f251..b008613f0 100644 --- a/samples/snippets/noxfile.py +++ b/samples/snippets/noxfile.py @@ -28,8 +28,9 @@ # WARNING - WARNING - WARNING - WARNING - WARNING # WARNING - WARNING - WARNING - WARNING - WARNING -# Copy `noxfile_config.py` to your directory and modify it instead. +BLACK_VERSION = "black==19.10b0" +# Copy `noxfile_config.py` to your directory and modify it instead. # `TEST_CONFIG` dict is a configuration hook that allows users to # modify the test configurations. The values here should be in sync @@ -38,7 +39,7 @@ TEST_CONFIG = { # You can opt out from the test for specific Python versions. - "ignored_versions": ["2.7"], + "ignored_versions": [], # Old samples are opted out of enforcing Python type hints # All new samples should feature them "enforce_type_hints": False, @@ -48,6 +49,10 @@ # to use your own Cloud project. "gcloud_project_env": "GOOGLE_CLOUD_PROJECT", # 'gcloud_project_env': 'BUILD_SPECIFIC_GCLOUD_PROJECT', + # If you need to use a specific version of pip, + # change pip_version_override to the string representation + # of the version number, for example, "20.2.4" + "pip_version_override": None, # A dictionary you want to inject into your test. Don't put any # secrets here. These values will override predefined values. "envs": {}, @@ -81,15 +86,18 @@ def get_pytest_env_vars() -> Dict[str, str]: # DO NOT EDIT - automatically generated. -# All versions used to tested samples. -ALL_VERSIONS = ["2.7", "3.6", "3.7", "3.8", "3.9"] +# All versions used to test samples. +ALL_VERSIONS = ["3.6", "3.7", "3.8", "3.9"] # Any default versions that should be ignored. IGNORED_VERSIONS = TEST_CONFIG["ignored_versions"] TESTED_VERSIONS = sorted([v for v in ALL_VERSIONS if v not in IGNORED_VERSIONS]) -INSTALL_LIBRARY_FROM_SOURCE = bool(os.environ.get("INSTALL_LIBRARY_FROM_SOURCE", False)) +INSTALL_LIBRARY_FROM_SOURCE = os.environ.get("INSTALL_LIBRARY_FROM_SOURCE", False) in ( + "True", + "true", +) # # Style Checks # @@ -155,7 +163,7 @@ def lint(session: nox.sessions.Session) -> None: @nox.session def blacken(session: nox.sessions.Session) -> None: - session.install("black") + session.install(BLACK_VERSION) python_files = [path for path in os.listdir(".") if path.endswith(".py")] session.run("black", *python_files) @@ -172,6 +180,9 @@ def blacken(session: nox.sessions.Session) -> None: def _session_tests( session: nox.sessions.Session, post_install: Callable = None ) -> None: + if TEST_CONFIG["pip_version_override"]: + pip_version = TEST_CONFIG["pip_version_override"] + session.install(f"pip=={pip_version}") """Runs py.test for a particular project.""" if os.path.exists("requirements.txt"): if os.path.exists("constraints.txt"): @@ -198,7 +209,7 @@ def _session_tests( # on travis where slow and flaky tests are excluded. # See http://doc.pytest.org/en/latest/_modules/_pytest/main.html success_codes=[0, 5], - env=get_pytest_env_vars() + env=get_pytest_env_vars(), ) diff --git a/samples/snippets/requirements-test.txt b/samples/snippets/requirements-test.txt index b0cf76724..b8dee50d0 100644 --- a/samples/snippets/requirements-test.txt +++ b/samples/snippets/requirements-test.txt @@ -1,2 +1,3 @@ +google-cloud-testutils==1.0.0 pytest==6.2.4 mock==4.0.3 diff --git a/samples/snippets/requirements.txt b/samples/snippets/requirements.txt index 2dfee39b5..d75c747fb 100644 --- a/samples/snippets/requirements.txt +++ b/samples/snippets/requirements.txt @@ -1,12 +1,12 @@ -google-cloud-bigquery==2.16.1 -google-cloud-bigquery-storage==2.4.0 -google-auth-oauthlib==0.4.4 -grpcio==1.37.1 +google-cloud-bigquery==2.25.0 +google-cloud-bigquery-storage==2.6.3 +google-auth-oauthlib==0.4.5 +grpcio==1.39.0 ipython==7.16.1; python_version < '3.7' ipython==7.17.0; python_version >= '3.7' matplotlib==3.3.4; python_version < '3.7' matplotlib==3.4.1; python_version >= '3.7' pandas==1.1.5; python_version < '3.7' -pandas==1.2.0; python_version >= '3.7' -pyarrow==4.0.0 +pandas==1.3.2; python_version >= '3.7' +pyarrow==5.0.0 pytz==2021.1 diff --git a/samples/snippets/test_update_with_dml.py b/samples/snippets/test_update_with_dml.py index 3cca7a649..912fd76e2 100644 --- a/samples/snippets/test_update_with_dml.py +++ b/samples/snippets/test_update_with_dml.py @@ -15,13 +15,13 @@ from google.cloud import bigquery import pytest -from conftest import resource_prefix +from conftest import prefixer import update_with_dml @pytest.fixture def table_id(bigquery_client: bigquery.Client, project_id: str, dataset_id: str): - table_id = f"{resource_prefix()}_update_with_dml" + table_id = f"{prefixer.create_prefix()}_update_with_dml" yield table_id full_table_id = f"{project_id}.{dataset_id}.{table_id}" bigquery_client.delete_table(full_table_id, not_found_ok=True) diff --git a/scripts/readme-gen/templates/install_deps.tmpl.rst b/scripts/readme-gen/templates/install_deps.tmpl.rst index a0406dba8..275d64989 100644 --- a/scripts/readme-gen/templates/install_deps.tmpl.rst +++ b/scripts/readme-gen/templates/install_deps.tmpl.rst @@ -12,7 +12,7 @@ Install Dependencies .. _Python Development Environment Setup Guide: https://cloud.google.com/python/setup -#. Create a virtualenv. Samples are compatible with Python 2.7 and 3.4+. +#. Create a virtualenv. Samples are compatible with Python 3.6+. .. code-block:: bash diff --git a/setup.py b/setup.py index 6a6202ef9..e7515493d 100644 --- a/setup.py +++ b/setup.py @@ -29,10 +29,17 @@ # 'Development Status :: 5 - Production/Stable' release_status = "Development Status :: 5 - Production/Stable" dependencies = [ - "google-api-core[grpc] >= 1.23.0, < 2.0.0dev", + "grpcio >= 1.38.1, < 2.0dev", # https://github.com/googleapis/python-bigquery/issues/695 + # NOTE: Maintainers, please do not require google-api-core>=2.x.x + # Until this issue is closed + # https://github.com/googleapis/google-cloud-python/issues/10566 + "google-api-core[grpc] >= 1.29.0, <3.0.0dev", "proto-plus >= 1.10.0", - "google-cloud-core >= 1.4.1, < 2.0dev", - "google-resumable-media >= 0.6.0, < 2.0dev", + # NOTE: Maintainers, please do not require google-cloud-core>=2.x.x + # Until this issue is closed + # https://github.com/googleapis/google-cloud-python/issues/10566 + "google-cloud-core >= 1.4.1, <3.0.0dev", + "google-resumable-media >= 0.6.0, < 3.0dev", "packaging >= 14.3", "protobuf >= 3.12.0", "requests >= 2.18.0, < 3.0.0dev", @@ -46,11 +53,12 @@ # See: https://github.com/googleapis/python-bigquery/issues/83 The # grpc.Channel.close() method isn't added until 1.32.0. # https://github.com/grpc/grpc/pull/15254 - "grpcio >= 1.32.0, < 2.0dev", - "pyarrow >= 1.0.0, < 5.0dev", + "grpcio >= 1.38.1, < 2.0dev", + "pyarrow >= 3.0.0, < 6.0dev", ], - "pandas": ["pandas>=0.23.0", "pyarrow >= 1.0.0, < 5.0dev"], - "bignumeric_type": ["pyarrow >= 3.0.0, < 5.0dev"], + "geopandas": ["geopandas>=0.9.0, <1.0dev", "Shapely>=1.6.0, <2.0dev"], + "pandas": ["pandas>=0.23.0", "pyarrow >= 3.0.0, < 6.0dev"], + "bignumeric_type": ["pyarrow >= 3.0.0, < 6.0dev"], "tqdm": ["tqdm >= 4.7.4, <5.0.0dev"], "opentelemetry": [ "opentelemetry-api >= 0.11b0", diff --git a/testing/constraints-3.6.txt b/testing/constraints-3.6.txt index 322373eba..be1a992fa 100644 --- a/testing/constraints-3.6.txt +++ b/testing/constraints-3.6.txt @@ -5,18 +5,20 @@ # # e.g., if setup.py has "foo >= 1.14.0, < 2.0.0dev", # Then this file should have foo==1.14.0 -google-api-core==1.23.0 +geopandas==0.9.0 +google-api-core==1.29.0 google-cloud-bigquery-storage==2.0.0 google-cloud-core==1.4.1 google-resumable-media==0.6.0 -grpcio==1.32.0 +grpcio==1.38.1 opentelemetry-api==0.11b0 opentelemetry-instrumentation==0.11b0 opentelemetry-sdk==0.11b0 -pandas==0.23.0 +pandas==0.24.2 proto-plus==1.10.0 protobuf==3.12.0 -pyarrow==1.0.0 +pyarrow==3.0.0 requests==2.18.0 +shapely==1.6.0 six==1.13.0 tqdm==4.7.4 diff --git a/tests/__init__.py b/tests/__init__.py index e69de29bb..4de65971c 100644 --- a/tests/__init__.py +++ b/tests/__init__.py @@ -0,0 +1,15 @@ +# -*- coding: utf-8 -*- +# Copyright 2020 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# diff --git a/tests/data/numeric_38_12.parquet b/tests/data/numeric_38_12.parquet new file mode 100644 index 000000000..ef4db91ea Binary files /dev/null and b/tests/data/numeric_38_12.parquet differ diff --git a/tests/data/scalars.jsonl b/tests/data/scalars.jsonl new file mode 100644 index 000000000..e06139e5c --- /dev/null +++ b/tests/data/scalars.jsonl @@ -0,0 +1,2 @@ +{"bool_col": true, "bytes_col": "SGVsbG8sIFdvcmxkIQ==", "date_col": "2021-07-21", "datetime_col": "2021-07-21 11:39:45", "geography_col": "POINT(-122.0838511 37.3860517)", "int64_col": "123456789", "interval_col": "P7Y11M9DT4H15M37.123456S", "numeric_col": "1.23456789", "bignumeric_col": "10.111213141516171819", "float64_col": "1.25", "rowindex": 0, "string_col": "Hello, World!", "time_col": "11:41:43.07616", "timestamp_col": "2021-07-21T17:43:43.945289Z"} +{"bool_col": null, "bytes_col": null, "date_col": null, "datetime_col": null, "geography_col": null, "int64_col": null, "interval_col": null, "numeric_col": null, "bignumeric_col": null, "float64_col": null, "rowindex": 1, "string_col": null, "time_col": null, "timestamp_col": null} diff --git a/tests/data/scalars_extreme.jsonl b/tests/data/scalars_extreme.jsonl new file mode 100644 index 000000000..d0a33fdba --- /dev/null +++ b/tests/data/scalars_extreme.jsonl @@ -0,0 +1,5 @@ +{"bool_col": true, "bytes_col": "DQo=\n", "date_col": "9999-12-31", "datetime_col": "9999-12-31 23:59:59.999999", "geography_col": "POINT(-135.0000 90.0000)", "int64_col": "9223372036854775807", "interval_col": "P-10000Y0M-3660000DT-87840000H0M0S", "numeric_col": "9.9999999999999999999999999999999999999E+28", "bignumeric_col": "9.999999999999999999999999999999999999999999999999999999999999999999999999999E+37", "float64_col": "+inf", "rowindex": 0, "string_col": "Hello, World", "time_col": "23:59:59.999999", "timestamp_col": "9999-12-31T23:59:59.999999Z"} +{"bool_col": false, "bytes_col": "8J+Zgw==\n", "date_col": "0001-01-01", "datetime_col": "0001-01-01 00:00:00", "geography_col": "POINT(45.0000 -90.0000)", "int64_col": "-9223372036854775808", "interval_col": "P10000Y0M3660000DT87840000H0M0S", "numeric_col": "-9.9999999999999999999999999999999999999E+28", "bignumeric_col": "-9.999999999999999999999999999999999999999999999999999999999999999999999999999E+37", "float64_col": "-inf", "rowindex": 1, "string_col": "Hello, World", "time_col": "00:00:00", "timestamp_col": "0001-01-01T00:00:00.000000Z"} +{"bool_col": true, "bytes_col": "AA==\n", "date_col": "1900-01-01", "datetime_col": "1900-01-01 00:00:00", "geography_col": "POINT(-180.0000 0.0000)", "int64_col": "-1", "interval_col": "P0Y0M0DT0H0M0.000001S", "numeric_col": "0.000000001", "bignumeric_col": "-0.00000000000000000000000000000000000001", "float64_col": "nan", "rowindex": 2, "string_col": "こんにちは", "time_col": "00:00:00.000001", "timestamp_col": "1900-01-01T00:00:00.000000Z"} +{"bool_col": false, "bytes_col": "", "date_col": "1970-01-01", "datetime_col": "1970-01-01 00:00:00", "geography_col": "POINT(0 0)", "int64_col": "0", "interval_col": "P0Y0M0DT0H0M0S", "numeric_col": "0.0", "bignumeric_col": "0.0", "float64_col": 0.0, "rowindex": 3, "string_col": "", "time_col": "12:00:00", "timestamp_col": "1970-01-01T00:00:00.000000Z"} +{"bool_col": null, "bytes_col": null, "date_col": null, "datetime_col": null, "geography_col": null, "int64_col": null, "interval_col": null, "numeric_col": null, "bignumeric_col": null, "float64_col": null, "rowindex": 4, "string_col": null, "time_col": null, "timestamp_col": null} diff --git a/tests/data/scalars_schema.json b/tests/data/scalars_schema.json new file mode 100644 index 000000000..676d37d56 --- /dev/null +++ b/tests/data/scalars_schema.json @@ -0,0 +1,72 @@ +[ + { + "mode": "NULLABLE", + "name": "bool_col", + "type": "BOOLEAN" + }, + { + "mode": "NULLABLE", + "name": "bignumeric_col", + "type": "BIGNUMERIC" + }, + { + "mode": "NULLABLE", + "name": "bytes_col", + "type": "BYTES" + }, + { + "mode": "NULLABLE", + "name": "date_col", + "type": "DATE" + }, + { + "mode": "NULLABLE", + "name": "datetime_col", + "type": "DATETIME" + }, + { + "mode": "NULLABLE", + "name": "float64_col", + "type": "FLOAT" + }, + { + "mode": "NULLABLE", + "name": "geography_col", + "type": "GEOGRAPHY" + }, + { + "mode": "NULLABLE", + "name": "int64_col", + "type": "INTEGER" + }, + { + "mode": "NULLABLE", + "name": "interval_col", + "type": "INTERVAL" + }, + { + "mode": "NULLABLE", + "name": "numeric_col", + "type": "NUMERIC" + }, + { + "mode": "REQUIRED", + "name": "rowindex", + "type": "INTEGER" + }, + { + "mode": "NULLABLE", + "name": "string_col", + "type": "STRING" + }, + { + "mode": "NULLABLE", + "name": "time_col", + "type": "TIME" + }, + { + "mode": "NULLABLE", + "name": "timestamp_col", + "type": "TIMESTAMP" + } +] diff --git a/tests/system/conftest.py b/tests/system/conftest.py index 4b5fcb543..cc2c2a4dc 100644 --- a/tests/system/conftest.py +++ b/tests/system/conftest.py @@ -12,18 +12,40 @@ # See the License for the specific language governing permissions and # limitations under the License. +import pathlib + import pytest +import test_utils.prefixer +from google.cloud import bigquery +from google.cloud.bigquery import enums from . import helpers +prefixer = test_utils.prefixer.Prefixer("python-bigquery", "tests/system") + +DATA_DIR = pathlib.Path(__file__).parent.parent / "data" + + +@pytest.fixture(scope="session", autouse=True) +def cleanup_datasets(bigquery_client: bigquery.Client): + for dataset in bigquery_client.list_datasets(): + if prefixer.should_cleanup(dataset.dataset_id): + bigquery_client.delete_dataset( + dataset, delete_contents=True, not_found_ok=True + ) + + @pytest.fixture(scope="session") def bigquery_client(): - from google.cloud import bigquery - return bigquery.Client() +@pytest.fixture(scope="session") +def project_id(bigquery_client: bigquery.Client): + return bigquery_client.project + + @pytest.fixture(scope="session") def bqstorage_client(bigquery_client): from google.cloud import bigquery_storage @@ -31,9 +53,48 @@ def bqstorage_client(bigquery_client): return bigquery_storage.BigQueryReadClient(credentials=bigquery_client._credentials) -@pytest.fixture +@pytest.fixture(scope="session") def dataset_id(bigquery_client): - dataset_id = f"bqsystem_{helpers.temp_suffix()}" + dataset_id = prefixer.create_prefix() bigquery_client.create_dataset(dataset_id) yield dataset_id - bigquery_client.delete_dataset(dataset_id, delete_contents=True) + bigquery_client.delete_dataset(dataset_id, delete_contents=True, not_found_ok=True) + + +@pytest.fixture +def table_id(dataset_id): + return f"{dataset_id}.table_{helpers.temp_suffix()}" + + +@pytest.fixture(scope="session") +def scalars_table(bigquery_client: bigquery.Client, project_id: str, dataset_id: str): + schema = bigquery_client.schema_from_json(DATA_DIR / "scalars_schema.json") + job_config = bigquery.LoadJobConfig() + job_config.schema = schema + job_config.source_format = enums.SourceFormat.NEWLINE_DELIMITED_JSON + full_table_id = f"{project_id}.{dataset_id}.scalars" + with open(DATA_DIR / "scalars.jsonl", "rb") as data_file: + job = bigquery_client.load_table_from_file( + data_file, full_table_id, job_config=job_config + ) + job.result() + yield full_table_id + bigquery_client.delete_table(full_table_id) + + +@pytest.fixture(scope="session") +def scalars_extreme_table( + bigquery_client: bigquery.Client, project_id: str, dataset_id: str +): + schema = bigquery_client.schema_from_json(DATA_DIR / "scalars_schema.json") + job_config = bigquery.LoadJobConfig() + job_config.schema = schema + job_config.source_format = enums.SourceFormat.NEWLINE_DELIMITED_JSON + full_table_id = f"{project_id}.{dataset_id}.scalars_extreme" + with open(DATA_DIR / "scalars_extreme.jsonl", "rb") as data_file: + job = bigquery_client.load_table_from_file( + data_file, full_table_id, job_config=job_config + ) + job.result() + yield full_table_id + bigquery_client.delete_table(full_table_id) diff --git a/tests/system/test_arrow.py b/tests/system/test_arrow.py new file mode 100644 index 000000000..12f7af9cb --- /dev/null +++ b/tests/system/test_arrow.py @@ -0,0 +1,112 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +"""System tests for Arrow connector.""" + +from typing import Optional + +import pytest + +from google.cloud import bigquery +from google.cloud.bigquery import enums + + +pyarrow = pytest.importorskip( + "pyarrow", minversion="3.0.0" +) # Needs decimal256 for BIGNUMERIC columns. + + +@pytest.mark.parametrize( + ("max_results", "scalars_table_name"), + ( + (None, "scalars_table"), # Use BQ Storage API. + (10, "scalars_table"), # Use REST API. + (None, "scalars_extreme_table"), # Use BQ Storage API. + (10, "scalars_extreme_table"), # Use REST API. + ), +) +def test_list_rows_nullable_scalars_dtypes( + bigquery_client: bigquery.Client, + scalars_table: str, + scalars_extreme_table: str, + max_results: Optional[int], + scalars_table_name: str, +): + table_id = scalars_table + if scalars_table_name == "scalars_extreme_table": + table_id = scalars_extreme_table + + # TODO(GH#836): Avoid INTERVAL columns until they are supported by the + # BigQuery Storage API and pyarrow. + schema = [ + bigquery.SchemaField("bool_col", enums.SqlTypeNames.BOOLEAN), + bigquery.SchemaField("bignumeric_col", enums.SqlTypeNames.BIGNUMERIC), + bigquery.SchemaField("bytes_col", enums.SqlTypeNames.BYTES), + bigquery.SchemaField("date_col", enums.SqlTypeNames.DATE), + bigquery.SchemaField("datetime_col", enums.SqlTypeNames.DATETIME), + bigquery.SchemaField("float64_col", enums.SqlTypeNames.FLOAT64), + bigquery.SchemaField("geography_col", enums.SqlTypeNames.GEOGRAPHY), + bigquery.SchemaField("int64_col", enums.SqlTypeNames.INT64), + bigquery.SchemaField("numeric_col", enums.SqlTypeNames.NUMERIC), + bigquery.SchemaField("string_col", enums.SqlTypeNames.STRING), + bigquery.SchemaField("time_col", enums.SqlTypeNames.TIME), + bigquery.SchemaField("timestamp_col", enums.SqlTypeNames.TIMESTAMP), + ] + + arrow_table = bigquery_client.list_rows( + table_id, max_results=max_results, selected_fields=schema, + ).to_arrow() + + schema = arrow_table.schema + bignumeric_type = schema.field("bignumeric_col").type + # 77th digit is partial. + # https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#decimal_types + assert bignumeric_type.precision in {76, 77} + assert bignumeric_type.scale == 38 + + bool_type = schema.field("bool_col").type + assert bool_type.equals(pyarrow.bool_()) + + bytes_type = schema.field("bytes_col").type + assert bytes_type.equals(pyarrow.binary()) + + date_type = schema.field("date_col").type + assert date_type.equals(pyarrow.date32()) + + datetime_type = schema.field("datetime_col").type + assert datetime_type.unit == "us" + assert datetime_type.tz is None + + float64_type = schema.field("float64_col").type + assert float64_type.equals(pyarrow.float64()) + + geography_type = schema.field("geography_col").type + assert geography_type.equals(pyarrow.string()) + + int64_type = schema.field("int64_col").type + assert int64_type.equals(pyarrow.int64()) + + numeric_type = schema.field("numeric_col").type + assert numeric_type.precision == 38 + assert numeric_type.scale == 9 + + string_type = schema.field("string_col").type + assert string_type.equals(pyarrow.string()) + + time_type = schema.field("time_col").type + assert time_type.equals(pyarrow.time64("us")) + + timestamp_type = schema.field("timestamp_col").type + assert timestamp_type.unit == "us" + assert timestamp_type.tz is not None diff --git a/tests/system/test_client.py b/tests/system/test_client.py index 7c8ef50fa..9da45ee6e 100644 --- a/tests/system/test_client.py +++ b/tests/system/test_client.py @@ -30,7 +30,6 @@ import psutil import pytest -from google.cloud.bigquery._pandas_helpers import _BIGNUMERIC_SUPPORT from . import helpers try: @@ -63,11 +62,12 @@ from google.cloud import bigquery_v2 from google.cloud.bigquery.dataset import Dataset from google.cloud.bigquery.dataset import DatasetReference -from google.cloud.bigquery.schema import SchemaField from google.cloud.bigquery.table import Table from google.cloud._helpers import UTC from google.cloud.bigquery import dbapi, enums from google.cloud import storage +from google.cloud.datacatalog_v1 import types as datacatalog_types +from google.cloud.datacatalog_v1 import PolicyTagManagerClient from test_utils.retry import RetryErrors from test_utils.retry import RetryInstanceState @@ -152,7 +152,6 @@ class Config(object): CLIENT: Optional[bigquery.Client] = None CURSOR = None - DATASET = None def setUpModule(): @@ -162,11 +161,11 @@ def setUpModule(): class TestBigQuery(unittest.TestCase): def setUp(self): - Config.DATASET = _make_dataset_id("bq_system_tests") - dataset = Config.CLIENT.create_dataset(Config.DATASET) - self.to_delete = [dataset] + self.to_delete = [] def tearDown(self): + policy_tag_client = PolicyTagManagerClient() + def _still_in_use(bad_request): return any( error["reason"] == "resourceInUse" for error in bad_request._errors @@ -183,6 +182,8 @@ def _still_in_use(bad_request): retry_in_use(Config.CLIENT.delete_dataset)(doomed, delete_contents=True) elif isinstance(doomed, (Table, bigquery.TableReference)): retry_in_use(Config.CLIENT.delete_table)(doomed) + elif isinstance(doomed, datacatalog_types.Taxonomy): + policy_tag_client.delete_taxonomy(name=doomed.name) else: doomed.delete() @@ -381,6 +382,68 @@ def test_create_table_with_policy(self): table2 = Config.CLIENT.update_table(table, ["schema"]) self.assertEqual(policy_2, table2.schema[1].policy_tags) + def test_create_table_with_real_custom_policy(self): + from google.cloud.bigquery.schema import PolicyTagList + + policy_tag_client = PolicyTagManagerClient() + taxonomy_parent = f"projects/{Config.CLIENT.project}/locations/us" + + new_taxonomy = datacatalog_types.Taxonomy( + display_name="Custom test taxonomy" + unique_resource_id(), + description="This taxonomy is ony used for a test.", + activated_policy_types=[ + datacatalog_types.Taxonomy.PolicyType.FINE_GRAINED_ACCESS_CONTROL + ], + ) + + taxonomy = policy_tag_client.create_taxonomy( + parent=taxonomy_parent, taxonomy=new_taxonomy + ) + self.to_delete.insert(0, taxonomy) + + parent_policy_tag = policy_tag_client.create_policy_tag( + parent=taxonomy.name, + policy_tag=datacatalog_types.PolicyTag( + display_name="Parent policy tag", parent_policy_tag=None + ), + ) + child_policy_tag = policy_tag_client.create_policy_tag( + parent=taxonomy.name, + policy_tag=datacatalog_types.PolicyTag( + display_name="Child policy tag", + parent_policy_tag=parent_policy_tag.name, + ), + ) + + dataset = self.temp_dataset( + _make_dataset_id("create_table_with_real_custom_policy") + ) + table_id = "test_table" + policy_1 = PolicyTagList(names=[parent_policy_tag.name]) + policy_2 = PolicyTagList(names=[child_policy_tag.name]) + + schema = [ + bigquery.SchemaField( + "first_name", "STRING", mode="REQUIRED", policy_tags=policy_1 + ), + bigquery.SchemaField( + "age", "INTEGER", mode="REQUIRED", policy_tags=policy_2 + ), + ] + table_arg = Table(dataset.table(table_id), schema=schema) + self.assertFalse(_table_exists(table_arg)) + + table = helpers.retry_403(Config.CLIENT.create_table)(table_arg) + self.to_delete.insert(0, table) + + self.assertTrue(_table_exists(table)) + self.assertCountEqual( + list(table.schema[0].policy_tags.names), [parent_policy_tag.name] + ) + self.assertCountEqual( + list(table.schema[1].policy_tags.names), [child_policy_tag.name] + ) + def test_create_table_w_time_partitioning_w_clustering_fields(self): from google.cloud.bigquery.table import TimePartitioning from google.cloud.bigquery.table import TimePartitioningType @@ -438,22 +501,6 @@ def test_delete_dataset_delete_contents_false(self): with self.assertRaises(exceptions.BadRequest): Config.CLIENT.delete_dataset(dataset) - def test_delete_job_metadata(self): - dataset_id = _make_dataset_id("us_east1") - self.temp_dataset(dataset_id, location="us-east1") - full_table_id = f"{Config.CLIENT.project}.{dataset_id}.test_delete_job_metadata" - table = Table(full_table_id, schema=[SchemaField("col", "STRING")]) - Config.CLIENT.create_table(table) - query_job: bigquery.QueryJob = Config.CLIENT.query( - f"SELECT COUNT(*) FROM `{full_table_id}`", location="us-east1", - ) - query_job.result() - self.assertIsNotNone(Config.CLIENT.get_job(query_job)) - - Config.CLIENT.delete_job_metadata(query_job) - with self.assertRaises(NotFound): - Config.CLIENT.get_job(query_job) - def test_get_table_w_public_dataset(self): public = "bigquery-public-data" dataset_id = "samples" @@ -585,6 +632,56 @@ def test_update_table_schema(self): self.assertEqual(found.field_type, expected.field_type) self.assertEqual(found.mode, expected.mode) + def test_unset_table_schema_attributes(self): + from google.cloud.bigquery.schema import PolicyTagList + + dataset = self.temp_dataset(_make_dataset_id("unset_policy_tags")) + table_id = "test_table" + policy_tags = PolicyTagList( + names=[ + "projects/{}/locations/us/taxonomies/1/policyTags/2".format( + Config.CLIENT.project + ), + ] + ) + + schema = [ + bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"), + bigquery.SchemaField( + "secret_int", + "INTEGER", + mode="REQUIRED", + description="This field is numeric", + policy_tags=policy_tags, + ), + ] + table_arg = Table(dataset.table(table_id), schema=schema) + self.assertFalse(_table_exists(table_arg)) + + table = helpers.retry_403(Config.CLIENT.create_table)(table_arg) + self.to_delete.insert(0, table) + + self.assertTrue(_table_exists(table)) + self.assertEqual(policy_tags, table.schema[1].policy_tags) + + # Amend the schema to replace the policy tags + new_schema = table.schema[:] + old_field = table.schema[1] + new_schema[1] = bigquery.SchemaField( + name=old_field.name, + field_type=old_field.field_type, + mode=old_field.mode, + description=None, + fields=old_field.fields, + policy_tags=None, + ) + + table.schema = new_schema + updated_table = Config.CLIENT.update_table(table, ["schema"]) + + self.assertFalse(updated_table.schema[1].description) # Empty string or None. + self.assertEqual(updated_table.schema[1].policy_tags.names, ()) + def test_update_table_clustering_configuration(self): dataset = self.temp_dataset(_make_dataset_id("update_table")) @@ -746,6 +843,60 @@ def test_load_table_from_local_avro_file_then_dump_table(self): sorted(row_tuples, key=by_wavelength), sorted(ROWS, key=by_wavelength) ) + def test_load_table_from_local_parquet_file_decimal_types(self): + from google.cloud.bigquery.enums import DecimalTargetType + from google.cloud.bigquery.job import SourceFormat + from google.cloud.bigquery.job import WriteDisposition + + TABLE_NAME = "test_table_parquet" + + expected_rows = [ + (decimal.Decimal("123.999999999999"),), + (decimal.Decimal("99999999999999999999999999.999999999999"),), + ] + + dataset = self.temp_dataset(_make_dataset_id("load_local_parquet_then_dump")) + table_ref = dataset.table(TABLE_NAME) + table = Table(table_ref) + self.to_delete.insert(0, table) + + job_config = bigquery.LoadJobConfig() + job_config.source_format = SourceFormat.PARQUET + job_config.write_disposition = WriteDisposition.WRITE_TRUNCATE + job_config.decimal_target_types = [ + DecimalTargetType.NUMERIC, + DecimalTargetType.BIGNUMERIC, + DecimalTargetType.STRING, + ] + + with open(DATA_PATH / "numeric_38_12.parquet", "rb") as parquet_file: + job = Config.CLIENT.load_table_from_file( + parquet_file, table_ref, job_config=job_config + ) + + job.result(timeout=JOB_TIMEOUT) # Retry until done. + + self.assertEqual(job.output_rows, len(expected_rows)) + + table = Config.CLIENT.get_table(table) + rows = self._fetch_single_page(table) + row_tuples = [r.values() for r in rows] + self.assertEqual(sorted(row_tuples), sorted(expected_rows)) + + # Forcing the NUMERIC type, however, should result in an error. + job_config.decimal_target_types = [DecimalTargetType.NUMERIC] + + with open(DATA_PATH / "numeric_38_12.parquet", "rb") as parquet_file: + job = Config.CLIENT.load_table_from_file( + parquet_file, table_ref, job_config=job_config + ) + + with self.assertRaises(BadRequest) as exc_info: + job.result(timeout=JOB_TIMEOUT) + + exc_msg = str(exc_info.exception) + self.assertIn("out of valid NUMERIC range", exc_msg) + def test_load_table_from_json_basic_use(self): table_schema = ( bigquery.SchemaField("name", "STRING", mode="REQUIRED"), @@ -1055,7 +1206,7 @@ def test_extract_table(self): job.result(timeout=100) self.to_delete.insert(0, destination) - got_bytes = retry_storage_errors(destination.download_as_string)() + got_bytes = retry_storage_errors(destination.download_as_bytes)() got = got_bytes.decode("utf-8") self.assertIn("Bharney Rhubble", got) @@ -1349,6 +1500,96 @@ def test_query_statistics(self): self.assertGreater(stages_with_inputs, 0) self.assertGreater(len(plan), stages_with_inputs) + def test_dml_statistics(self): + table_schema = ( + bigquery.SchemaField("foo", "STRING"), + bigquery.SchemaField("bar", "INTEGER"), + ) + + dataset_id = _make_dataset_id("bq_system_test") + self.temp_dataset(dataset_id) + table_id = "{}.{}.test_dml_statistics".format(Config.CLIENT.project, dataset_id) + + # Create the table before loading so that the column order is deterministic. + table = helpers.retry_403(Config.CLIENT.create_table)( + Table(table_id, schema=table_schema) + ) + self.to_delete.insert(0, table) + + # Insert a few rows and check the stats. + sql = f""" + INSERT INTO `{table_id}` + VALUES ("one", 1), ("two", 2), ("three", 3), ("four", 4); + """ + query_job = Config.CLIENT.query(sql) + query_job.result() + + assert query_job.dml_stats is not None + assert query_job.dml_stats.inserted_row_count == 4 + assert query_job.dml_stats.updated_row_count == 0 + assert query_job.dml_stats.deleted_row_count == 0 + + # Update some of the rows. + sql = f""" + UPDATE `{table_id}` + SET bar = bar + 1 + WHERE bar > 2; + """ + query_job = Config.CLIENT.query(sql) + query_job.result() + + assert query_job.dml_stats is not None + assert query_job.dml_stats.inserted_row_count == 0 + assert query_job.dml_stats.updated_row_count == 2 + assert query_job.dml_stats.deleted_row_count == 0 + + # Now delete a few rows and check the stats. + sql = f""" + DELETE FROM `{table_id}` + WHERE foo != "two"; + """ + query_job = Config.CLIENT.query(sql) + query_job.result() + + assert query_job.dml_stats is not None + assert query_job.dml_stats.inserted_row_count == 0 + assert query_job.dml_stats.updated_row_count == 0 + assert query_job.dml_stats.deleted_row_count == 3 + + def test_transaction_info(self): + table_schema = ( + bigquery.SchemaField("foo", "STRING"), + bigquery.SchemaField("bar", "INTEGER"), + ) + + dataset_id = _make_dataset_id("bq_system_test") + self.temp_dataset(dataset_id) + table_id = f"{Config.CLIENT.project}.{dataset_id}.test_dml_statistics" + + # Create the table before loading so that the column order is deterministic. + table = helpers.retry_403(Config.CLIENT.create_table)( + Table(table_id, schema=table_schema) + ) + self.to_delete.insert(0, table) + + # Insert a few rows and check the stats. + sql = f""" + BEGIN TRANSACTION; + INSERT INTO `{table_id}` + VALUES ("one", 1), ("two", 2), ("three", 3), ("four", 4); + + UPDATE `{table_id}` + SET bar = bar + 1 + WHERE bar > 2; + COMMIT TRANSACTION; + """ + query_job = Config.CLIENT.query(sql) + query_job.result() + + # Transaction ID set by the server should be accessible + assert query_job.transaction_info is not None + assert query_job.transaction_info.transaction_id != "" + def test_dbapi_w_standard_sql_types(self): for sql, expected in helpers.STANDARD_SQL_EXAMPLES: Config.CURSOR.execute(sql) @@ -1394,20 +1635,6 @@ def test_dbapi_fetchall_from_script(self): row_tuples = [r.values() for r in rows] self.assertEqual(row_tuples, [(5, "foo"), (6, "bar"), (7, "baz")]) - def test_dbapi_create_view(self): - - query = """ - CREATE VIEW {}.dbapi_create_view - AS SELECT name, SUM(number) AS total - FROM `bigquery-public-data.usa_names.usa_1910_2013` - GROUP BY name; - """.format( - Config.DATASET - ) - - Config.CURSOR.execute(query) - self.assertEqual(Config.CURSOR.rowcount, 0, "expected 0 rows") - @unittest.skipIf( bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" ) @@ -1744,15 +1971,12 @@ def test_query_w_query_params(self): "expected": {"friends": [phred_name, bharney_name]}, "query_parameters": [with_friends_param], }, + { + "sql": "SELECT @bignum_param", + "expected": bignum, + "query_parameters": [bignum_param], + }, ] - if _BIGNUMERIC_SUPPORT: - examples.append( - { - "sql": "SELECT @bignum_param", - "expected": bignum, - "query_parameters": [bignum_param], - } - ) for example in examples: jconfig = QueryJobConfig() @@ -2000,6 +2224,85 @@ def test_create_routine(self): assert len(rows) == 1 assert rows[0].max_value == 100.0 + def test_create_tvf_routine(self): + from google.cloud.bigquery import Routine, RoutineArgument, RoutineType + + StandardSqlDataType = bigquery_v2.types.StandardSqlDataType + StandardSqlField = bigquery_v2.types.StandardSqlField + StandardSqlTableType = bigquery_v2.types.StandardSqlTableType + + INT64 = StandardSqlDataType.TypeKind.INT64 + STRING = StandardSqlDataType.TypeKind.STRING + + client = Config.CLIENT + + dataset = self.temp_dataset(_make_dataset_id("create_tvf_routine")) + routine_ref = dataset.routine("test_tvf_routine") + + routine_body = """ + SELECT int_col, str_col + FROM ( + UNNEST([1, 2, 3]) int_col + JOIN + (SELECT str_col FROM UNNEST(["one", "two", "three"]) str_col) + ON TRUE + ) + WHERE int_col > threshold + """ + + return_table_type = StandardSqlTableType( + columns=[ + StandardSqlField( + name="int_col", type=StandardSqlDataType(type_kind=INT64), + ), + StandardSqlField( + name="str_col", type=StandardSqlDataType(type_kind=STRING), + ), + ] + ) + + routine_args = [ + RoutineArgument( + name="threshold", data_type=StandardSqlDataType(type_kind=INT64), + ) + ] + + routine_def = Routine( + routine_ref, + type_=RoutineType.TABLE_VALUED_FUNCTION, + arguments=routine_args, + return_table_type=return_table_type, + body=routine_body, + ) + + # Create TVF routine. + client.delete_routine(routine_ref, not_found_ok=True) + routine = client.create_routine(routine_def) + + assert routine.body == routine_body + assert routine.return_table_type == return_table_type + assert routine.arguments == routine_args + + # Execute the routine to see if it's working as expected. + query_job = client.query( + f""" + SELECT int_col, str_col + FROM `{routine.reference}`(1) + ORDER BY int_col, str_col ASC + """ + ) + + result_rows = [tuple(row) for row in query_job.result()] + expected = [ + (2, "one"), + (2, "three"), + (2, "two"), + (3, "one"), + (3, "three"), + (3, "two"), + ] + assert result_rows == expected + def test_create_table_rows_fetch_nested_schema(self): table_name = "test_table" dataset = self.temp_dataset(_make_dataset_id("create_table_nested_schema")) @@ -2057,9 +2360,6 @@ def test_create_table_rows_fetch_nested_schema(self): self.assertEqual(found[7], e_favtime) self.assertEqual(found[8], decimal.Decimal(expected["FavoriteNumber"])) - def _fetch_dataframe(self, query): - return Config.CLIENT.query(query).result().to_dataframe() - @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") @unittest.skipIf( bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" @@ -2110,69 +2410,17 @@ def test_nested_table_to_arrow(self): self.assertEqual(tbl.num_rows, 1) self.assertEqual(tbl.num_columns, 3) # Columns may not appear in the requested order. - self.assertTrue( - pyarrow.types.is_float64(tbl.schema.field_by_name("float_col").type) - ) - self.assertTrue( - pyarrow.types.is_string(tbl.schema.field_by_name("string_col").type) - ) - record_col = tbl.schema.field_by_name("record_col").type + self.assertTrue(pyarrow.types.is_float64(tbl.schema.field("float_col").type)) + self.assertTrue(pyarrow.types.is_string(tbl.schema.field("string_col").type)) + record_col = tbl.schema.field("record_col").type self.assertTrue(pyarrow.types.is_struct(record_col)) - self.assertEqual(record_col.num_children, 2) + self.assertEqual(record_col.num_fields, 2) self.assertEqual(record_col[0].name, "nested_string") self.assertTrue(pyarrow.types.is_string(record_col[0].type)) self.assertEqual(record_col[1].name, "nested_repeated") self.assertTrue(pyarrow.types.is_list(record_col[1].type)) self.assertTrue(pyarrow.types.is_int64(record_col[1].type.value_type)) - def test_list_rows_empty_table(self): - from google.cloud.bigquery.table import RowIterator - - dataset_id = _make_dataset_id("empty_table") - dataset = self.temp_dataset(dataset_id) - table_ref = dataset.table("empty_table") - table = Config.CLIENT.create_table(bigquery.Table(table_ref)) - - # It's a bit silly to list rows for an empty table, but this does - # happen as the result of a DDL query from an IPython magic command. - rows = Config.CLIENT.list_rows(table) - self.assertIsInstance(rows, RowIterator) - self.assertEqual(tuple(rows), ()) - - def test_list_rows_page_size(self): - from google.cloud.bigquery.job import SourceFormat - from google.cloud.bigquery.job import WriteDisposition - - num_items = 7 - page_size = 3 - num_pages, num_last_page = divmod(num_items, page_size) - - SF = bigquery.SchemaField - schema = [SF("string_col", "STRING", mode="NULLABLE")] - to_insert = [{"string_col": "item%d" % i} for i in range(num_items)] - rows = [json.dumps(row) for row in to_insert] - body = io.BytesIO("{}\n".format("\n".join(rows)).encode("ascii")) - - table_id = "test_table" - dataset = self.temp_dataset(_make_dataset_id("nested_df")) - table = dataset.table(table_id) - self.to_delete.insert(0, table) - job_config = bigquery.LoadJobConfig() - job_config.write_disposition = WriteDisposition.WRITE_TRUNCATE - job_config.source_format = SourceFormat.NEWLINE_DELIMITED_JSON - job_config.schema = schema - # Load a table using a local JSON file from memory. - Config.CLIENT.load_table_from_file(body, table, job_config=job_config).result() - - df = Config.CLIENT.list_rows(table, selected_fields=schema, page_size=page_size) - pages = df.pages - - for i in range(num_pages): - page = next(pages) - self.assertEqual(page.num_items, page_size) - page = next(pages) - self.assertEqual(page.num_items, num_last_page) - def temp_dataset(self, dataset_id, location=None): project = Config.CLIENT.project dataset_ref = bigquery.DatasetReference(project, dataset_id) @@ -2203,3 +2451,108 @@ def _table_exists(t): return True except NotFound: return False + + +def test_dbapi_create_view(dataset_id): + + query = f""" + CREATE VIEW {dataset_id}.dbapi_create_view + AS SELECT name, SUM(number) AS total + FROM `bigquery-public-data.usa_names.usa_1910_2013` + GROUP BY name; + """ + + Config.CURSOR.execute(query) + assert Config.CURSOR.rowcount == 0, "expected 0 rows" + + +def test_parameterized_types_round_trip(dataset_id): + client = Config.CLIENT + table_id = f"{dataset_id}.test_parameterized_types_round_trip" + fields = ( + ("n", "NUMERIC"), + ("n9", "NUMERIC(9)"), + ("n92", "NUMERIC(9, 2)"), + ("bn", "BIGNUMERIC"), + ("bn9", "BIGNUMERIC(38)"), + ("bn92", "BIGNUMERIC(38, 22)"), + ("s", "STRING"), + ("s9", "STRING(9)"), + ("b", "BYTES"), + ("b9", "BYTES(9)"), + ) + client.query( + "create table {} ({})".format(table_id, ", ".join(" ".join(f) for f in fields)) + ).result() + table = client.get_table(table_id) + table_id2 = table_id + "2" + client.create_table(Table(f"{client.project}.{table_id2}", table.schema)) + table2 = client.get_table(table_id2) + + assert tuple(s._key()[:2] for s in table2.schema) == fields + + +def test_table_snapshots(dataset_id): + from google.cloud.bigquery import CopyJobConfig + from google.cloud.bigquery import OperationType + + client = Config.CLIENT + + source_table_path = f"{client.project}.{dataset_id}.test_table" + snapshot_table_path = f"{source_table_path}_snapshot" + + # Create the table before loading so that the column order is predictable. + schema = [ + bigquery.SchemaField("foo", "INTEGER"), + bigquery.SchemaField("bar", "STRING"), + ] + source_table = helpers.retry_403(Config.CLIENT.create_table)( + Table(source_table_path, schema=schema) + ) + + # Populate the table with initial data. + rows = [{"foo": 1, "bar": "one"}, {"foo": 2, "bar": "two"}] + load_job = Config.CLIENT.load_table_from_json(rows, source_table) + load_job.result() + + # Now create a snapshot before modifying the original table data. + copy_config = CopyJobConfig() + copy_config.operation_type = OperationType.SNAPSHOT + + copy_job = client.copy_table( + sources=source_table_path, + destination=snapshot_table_path, + job_config=copy_config, + ) + copy_job.result() + + # Modify data in original table. + sql = f'INSERT INTO `{source_table_path}`(foo, bar) VALUES (3, "three")' + query_job = client.query(sql) + query_job.result() + + # List rows from the source table and compare them to rows from the snapshot. + rows_iter = client.list_rows(source_table_path) + rows = sorted(row.values() for row in rows_iter) + assert rows == [(1, "one"), (2, "two"), (3, "three")] + + rows_iter = client.list_rows(snapshot_table_path) + rows = sorted(row.values() for row in rows_iter) + assert rows == [(1, "one"), (2, "two")] + + # Now restore the table from the snapshot and it should again contain the old + # set of rows. + copy_config = CopyJobConfig() + copy_config.operation_type = OperationType.RESTORE + copy_config.write_disposition = bigquery.WriteDisposition.WRITE_TRUNCATE + + copy_job = client.copy_table( + sources=snapshot_table_path, + destination=source_table_path, + job_config=copy_config, + ) + copy_job.result() + + rows_iter = client.list_rows(source_table_path) + rows = sorted(row.values() for row in rows_iter) + assert rows == [(1, "one"), (2, "two")] diff --git a/tests/system/test_job_retry.py b/tests/system/test_job_retry.py new file mode 100644 index 000000000..520545493 --- /dev/null +++ b/tests/system/test_job_retry.py @@ -0,0 +1,72 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import contextlib +import threading +import time + +import google.api_core.exceptions +import google.cloud.bigquery +import pytest + + +def thread(func): + thread = threading.Thread(target=func, daemon=True) + thread.start() + return thread + + +@pytest.mark.parametrize("job_retry_on_query", [True, False]) +def test_query_retry_539(bigquery_client, dataset_id, job_retry_on_query): + """ + Test job_retry + + See: https://github.com/googleapis/python-bigquery/issues/539 + """ + from google.api_core import exceptions + from google.api_core.retry import if_exception_type, Retry + + table_name = f"{dataset_id}.t539" + + # Without a custom retry, we fail: + with pytest.raises(google.api_core.exceptions.NotFound): + bigquery_client.query(f"select count(*) from {table_name}").result() + + retry_notfound = Retry(predicate=if_exception_type(exceptions.NotFound)) + + job_retry = dict(job_retry=retry_notfound) if job_retry_on_query else {} + job = bigquery_client.query(f"select count(*) from {table_name}", **job_retry) + job_id = job.job_id + + # We can already know that the job failed, but we're not supposed + # to find out until we call result, which is where retry happend + assert job.done() + assert job.exception() is not None + + @thread + def create_table(): + time.sleep(1) # Give the first retry attempt time to fail. + with contextlib.closing(google.cloud.bigquery.Client()) as client: + client.query(f"create table {table_name} (id int64)").result() + + job_retry = {} if job_retry_on_query else dict(job_retry=retry_notfound) + [[count]] = list(job.result(**job_retry)) + assert count == 0 + + # The job was retried, and thus got a new job id + assert job.job_id != job_id + + # Make sure we don't leave a thread behind: + create_table.join() + bigquery_client.query(f"drop table {table_name}").result() diff --git a/tests/system/test_list_rows.py b/tests/system/test_list_rows.py new file mode 100644 index 000000000..70388059e --- /dev/null +++ b/tests/system/test_list_rows.py @@ -0,0 +1,112 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import datetime +import decimal + +from google.cloud import bigquery +from google.cloud.bigquery import enums + + +def test_list_rows_empty_table(bigquery_client: bigquery.Client, table_id: str): + from google.cloud.bigquery.table import RowIterator + + table = bigquery_client.create_table(table_id) + + # It's a bit silly to list rows for an empty table, but this does + # happen as the result of a DDL query from an IPython magic command. + rows = bigquery_client.list_rows(table) + assert isinstance(rows, RowIterator) + assert tuple(rows) == () + + +def test_list_rows_page_size(bigquery_client: bigquery.Client, table_id: str): + num_items = 7 + page_size = 3 + num_pages, num_last_page = divmod(num_items, page_size) + + to_insert = [{"string_col": "item%d" % i, "rowindex": i} for i in range(num_items)] + bigquery_client.load_table_from_json(to_insert, table_id).result() + + df = bigquery_client.list_rows( + table_id, + selected_fields=[bigquery.SchemaField("string_col", enums.SqlTypeNames.STRING)], + page_size=page_size, + ) + pages = df.pages + + for i in range(num_pages): + page = next(pages) + assert page.num_items == page_size + page = next(pages) + assert page.num_items == num_last_page + + +def test_list_rows_scalars(bigquery_client: bigquery.Client, scalars_table: str): + rows = sorted( + bigquery_client.list_rows(scalars_table), key=lambda row: row["rowindex"] + ) + row = rows[0] + assert row["bool_col"] # True + assert row["bytes_col"] == b"Hello, World!" + assert row["date_col"] == datetime.date(2021, 7, 21) + assert row["datetime_col"] == datetime.datetime(2021, 7, 21, 11, 39, 45) + assert row["geography_col"] == "POINT(-122.0838511 37.3860517)" + assert row["int64_col"] == 123456789 + assert row["numeric_col"] == decimal.Decimal("1.23456789") + assert row["bignumeric_col"] == decimal.Decimal("10.111213141516171819") + assert row["float64_col"] == 1.25 + assert row["string_col"] == "Hello, World!" + assert row["time_col"] == datetime.time(11, 41, 43, 76160) + assert row["timestamp_col"] == datetime.datetime( + 2021, 7, 21, 17, 43, 43, 945289, tzinfo=datetime.timezone.utc + ) + + nullrow = rows[1] + for column, value in nullrow.items(): + if column == "rowindex": + assert value == 1 + else: + assert value is None + + +def test_list_rows_scalars_extreme( + bigquery_client: bigquery.Client, scalars_extreme_table: str +): + rows = sorted( + bigquery_client.list_rows(scalars_extreme_table), + key=lambda row: row["rowindex"], + ) + row = rows[0] + assert row["bool_col"] # True + assert row["bytes_col"] == b"\r\n" + assert row["date_col"] == datetime.date(9999, 12, 31) + assert row["datetime_col"] == datetime.datetime(9999, 12, 31, 23, 59, 59, 999999) + assert row["geography_col"] == "POINT(-135 90)" + assert row["int64_col"] == 9223372036854775807 + assert row["numeric_col"] == decimal.Decimal(f"9.{'9' * 37}E+28") + assert row["bignumeric_col"] == decimal.Decimal(f"9.{'9' * 75}E+37") + assert row["float64_col"] == float("Inf") + assert row["string_col"] == "Hello, World" + assert row["time_col"] == datetime.time(23, 59, 59, 999999) + assert row["timestamp_col"] == datetime.datetime( + 9999, 12, 31, 23, 59, 59, 999999, tzinfo=datetime.timezone.utc + ) + + nullrow = rows[4] + for column, value in nullrow.items(): + if column == "rowindex": + assert value == 4 + else: + assert value is None diff --git a/tests/system/test_pandas.py b/tests/system/test_pandas.py index 1164e36da..93ce23481 100644 --- a/tests/system/test_pandas.py +++ b/tests/system/test_pandas.py @@ -21,12 +21,11 @@ import io import operator +import google.api_core.retry import pkg_resources import pytest -import pytz from google.cloud import bigquery -from google.cloud.bigquery._pandas_helpers import _BIGNUMERIC_SUPPORT from . import helpers @@ -41,6 +40,10 @@ PANDAS_INT64_VERSION = pkg_resources.parse_version("1.0.0") +class MissingDataError(Exception): + pass + + def test_load_table_from_dataframe_w_automatic_schema(bigquery_client, dataset_id): """Test that a DataFrame with dtypes that map well to BigQuery types can be uploaded without specifying a schema. @@ -59,7 +62,7 @@ def test_load_table_from_dataframe_w_automatic_schema(bigquery_client, dataset_i datetime.datetime(2012, 3, 14, 15, 16), ], dtype="datetime64[ns]", - ).dt.tz_localize(pytz.utc), + ).dt.tz_localize(datetime.timezone.utc), ), ( "dt_col", @@ -149,7 +152,7 @@ def test_load_table_from_dataframe_w_nullable_int64_datatype( reason="Only `pandas version >=1.0.0` is supported", ) def test_load_table_from_dataframe_w_nullable_int64_datatype_automatic_schema( - bigquery_client, dataset_id + bigquery_client, dataset_id, table_id ): """Test that a DataFrame containing column with None-type values and int64 datatype can be uploaded without specifying a schema. @@ -157,9 +160,6 @@ def test_load_table_from_dataframe_w_nullable_int64_datatype_automatic_schema( https://github.com/googleapis/python-bigquery/issues/22 """ - table_id = "{}.{}.load_table_from_dataframe_w_nullable_int64_datatype".format( - bigquery_client.project, dataset_id - ) df_data = collections.OrderedDict( [("x", pandas.Series([1, 2, None, 4], dtype="Int64"))] ) @@ -187,12 +187,11 @@ def test_load_table_from_dataframe_w_nulls(bigquery_client, dataset_id): bigquery.SchemaField("geo_col", "GEOGRAPHY"), bigquery.SchemaField("int_col", "INTEGER"), bigquery.SchemaField("num_col", "NUMERIC"), + bigquery.SchemaField("bignum_col", "BIGNUMERIC"), bigquery.SchemaField("str_col", "STRING"), bigquery.SchemaField("time_col", "TIME"), bigquery.SchemaField("ts_col", "TIMESTAMP"), ) - if _BIGNUMERIC_SUPPORT: - scalars_schema += (bigquery.SchemaField("bignum_col", "BIGNUMERIC"),) table_schema = scalars_schema + ( # TODO: Array columns can't be read due to NULLABLE versus REPEATED @@ -214,12 +213,11 @@ def test_load_table_from_dataframe_w_nulls(bigquery_client, dataset_id): ("geo_col", nulls), ("int_col", nulls), ("num_col", nulls), + ("bignum_col", nulls), ("str_col", nulls), ("time_col", nulls), ("ts_col", nulls), ] - if _BIGNUMERIC_SUPPORT: - df_data.append(("bignum_col", nulls)) df_data = collections.OrderedDict(df_data) dataframe = pandas.DataFrame(df_data, columns=df_data.keys()) @@ -281,8 +279,6 @@ def test_load_table_from_dataframe_w_required(bigquery_client, dataset_id): def test_load_table_from_dataframe_w_explicit_schema(bigquery_client, dataset_id): # Schema with all scalar types. - # TODO: Uploading DATETIME columns currently fails, thus that field type - # is temporarily removed from the test. # See: # https://github.com/googleapis/python-bigquery/issues/61 # https://issuetracker.google.com/issues/151765076 @@ -290,17 +286,16 @@ def test_load_table_from_dataframe_w_explicit_schema(bigquery_client, dataset_id bigquery.SchemaField("bool_col", "BOOLEAN"), bigquery.SchemaField("bytes_col", "BYTES"), bigquery.SchemaField("date_col", "DATE"), - # bigquery.SchemaField("dt_col", "DATETIME"), + bigquery.SchemaField("dt_col", "DATETIME"), bigquery.SchemaField("float_col", "FLOAT"), bigquery.SchemaField("geo_col", "GEOGRAPHY"), bigquery.SchemaField("int_col", "INTEGER"), bigquery.SchemaField("num_col", "NUMERIC"), + bigquery.SchemaField("bignum_col", "BIGNUMERIC"), bigquery.SchemaField("str_col", "STRING"), bigquery.SchemaField("time_col", "TIME"), bigquery.SchemaField("ts_col", "TIMESTAMP"), ) - if _BIGNUMERIC_SUPPORT: - scalars_schema += (bigquery.SchemaField("bignum_col", "BIGNUMERIC"),) table_schema = scalars_schema + ( # TODO: Array columns can't be read due to NULLABLE versus REPEATED @@ -316,14 +311,14 @@ def test_load_table_from_dataframe_w_explicit_schema(bigquery_client, dataset_id ("bool_col", [True, None, False]), ("bytes_col", [b"abc", None, b"def"]), ("date_col", [datetime.date(1, 1, 1), None, datetime.date(9999, 12, 31)]), - # ( - # "dt_col", - # [ - # datetime.datetime(1, 1, 1, 0, 0, 0), - # None, - # datetime.datetime(9999, 12, 31, 23, 59, 59, 999999), - # ], - # ), + ( + "dt_col", + [ + datetime.datetime(1, 1, 1, 0, 0, 0), + None, + datetime.datetime(9999, 12, 31, 23, 59, 59, 999999), + ], + ), ("float_col", [float("-inf"), float("nan"), float("inf")]), ( "geo_col", @@ -338,6 +333,14 @@ def test_load_table_from_dataframe_w_explicit_schema(bigquery_client, dataset_id decimal.Decimal("99999999999999999999999999999.999999999"), ], ), + ( + "bignum_col", + [ + decimal.Decimal("-{d38}.{d38}".format(d38="9" * 38)), + None, + decimal.Decimal("{d38}.{d38}".format(d38="9" * 38)), + ], + ), ("str_col", ["abc", None, "def"]), ( "time_col", @@ -346,23 +349,14 @@ def test_load_table_from_dataframe_w_explicit_schema(bigquery_client, dataset_id ( "ts_col", [ - datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.utc), + datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc), None, - datetime.datetime(9999, 12, 31, 23, 59, 59, 999999, tzinfo=pytz.utc), + datetime.datetime( + 9999, 12, 31, 23, 59, 59, 999999, tzinfo=datetime.timezone.utc + ), ], ), ] - if _BIGNUMERIC_SUPPORT: - df_data.append( - ( - "bignum_col", - [ - decimal.Decimal("-{d38}.{d38}".format(d38="9" * 38)), - None, - decimal.Decimal("{d38}.{d38}".format(d38="9" * 38)), - ], - ) - ) df_data = collections.OrderedDict(df_data) dataframe = pandas.DataFrame(df_data, dtype="object", columns=df_data.keys()) @@ -482,10 +476,10 @@ def test_load_table_from_dataframe_w_explicit_schema_source_format_csv( ( "ts_col", [ - datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.utc), + datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc), None, datetime.datetime( - 9999, 12, 31, 23, 59, 59, 999999, tzinfo=pytz.utc + 9999, 12, 31, 23, 59, 59, 999999, tzinfo=datetime.timezone.utc ), ], ), @@ -511,7 +505,7 @@ def test_load_table_from_dataframe_w_explicit_schema_source_format_csv( def test_load_table_from_dataframe_w_explicit_schema_source_format_csv_floats( - bigquery_client, dataset_id + bigquery_client, dataset_id, table_id ): from google.cloud.bigquery.job import SourceFormat @@ -536,10 +530,6 @@ def test_load_table_from_dataframe_w_explicit_schema_source_format_csv_floats( ) dataframe = pandas.DataFrame(df_data, dtype="object", columns=df_data.keys()) - table_id = "{}.{}.load_table_from_dataframe_w_explicit_schema_csv".format( - bigquery_client.project, dataset_id - ) - job_config = bigquery.LoadJobConfig( schema=table_schema, source_format=SourceFormat.CSV ) @@ -673,19 +663,6 @@ def test_insert_rows_from_dataframe(bigquery_client, dataset_id): ) for errors in chunk_errors: assert not errors - - # Use query to fetch rows instead of listing directly from the table so - # that we get values from the streaming buffer. - rows = list( - bigquery_client.query( - "SELECT * FROM `{}.{}.{}`".format( - table.project, table.dataset_id, table.table_id - ) - ) - ) - - sorted_rows = sorted(rows, key=operator.attrgetter("int_col")) - row_tuples = [r.values() for r in sorted_rows] expected = [ # Pandas often represents NULL values as NaN. Convert to None for # easier comparison. @@ -693,7 +670,27 @@ def test_insert_rows_from_dataframe(bigquery_client, dataset_id): for data_row in dataframe.itertuples(index=False) ] - assert len(row_tuples) == len(expected) + # Use query to fetch rows instead of listing directly from the table so + # that we get values from the streaming buffer "within a few seconds". + # https://cloud.google.com/bigquery/streaming-data-into-bigquery#dataavailability + @google.api_core.retry.Retry( + predicate=google.api_core.retry.if_exception_type(MissingDataError) + ) + def get_rows(): + rows = list( + bigquery_client.query( + "SELECT * FROM `{}.{}.{}`".format( + table.project, table.dataset_id, table.table_id + ) + ) + ) + if len(rows) != len(expected): + raise MissingDataError() + return rows + + rows = get_rows() + sorted_rows = sorted(rows, key=operator.attrgetter("int_col")) + row_tuples = [r.values() for r in sorted_rows] for row, expected_row in zip(row_tuples, expected): assert ( @@ -799,3 +796,190 @@ def test_list_rows_max_results_w_bqstorage(bigquery_client): dataframe = row_iterator.to_dataframe(bqstorage_client=bqstorage_client) assert len(dataframe.index) == 100 + + +def test_upload_time_and_datetime_56(bigquery_client, dataset_id): + df = pandas.DataFrame( + dict( + dt=[ + datetime.datetime(2020, 1, 8, 8, 0, 0), + datetime.datetime( + 2020, + 1, + 8, + 8, + 0, + 0, + tzinfo=datetime.timezone(datetime.timedelta(hours=-7)), + ), + ], + t=[datetime.time(0, 0, 10, 100001), None], + ) + ) + table = f"{dataset_id}.test_upload_time_and_datetime" + bigquery_client.load_table_from_dataframe(df, table).result() + data = list(map(list, bigquery_client.list_rows(table))) + assert data == [ + [ + datetime.datetime(2020, 1, 8, 8, 0, tzinfo=datetime.timezone.utc), + datetime.time(0, 0, 10, 100001), + ], + [datetime.datetime(2020, 1, 8, 15, 0, tzinfo=datetime.timezone.utc), None], + ] + + from google.cloud.bigquery import job, schema + + table = f"{dataset_id}.test_upload_time_and_datetime_dt" + config = job.LoadJobConfig( + schema=[schema.SchemaField("dt", "DATETIME"), schema.SchemaField("t", "TIME")] + ) + + bigquery_client.load_table_from_dataframe(df, table, job_config=config).result() + data = list(map(list, bigquery_client.list_rows(table))) + assert data == [ + [datetime.datetime(2020, 1, 8, 8, 0), datetime.time(0, 0, 10, 100001)], + [datetime.datetime(2020, 1, 8, 15, 0), None], + ] + + +def test_to_dataframe_geography_as_objects(bigquery_client, dataset_id): + wkt = pytest.importorskip("shapely.wkt") + bigquery_client.query( + f"create table {dataset_id}.lake (name string, geog geography)" + ).result() + bigquery_client.query( + f""" + insert into {dataset_id}.lake (name, geog) values + ('foo', st_geogfromtext('point(0 0)')), + ('bar', st_geogfromtext('point(0 1)')), + ('baz', null) + """ + ).result() + df = bigquery_client.query( + f"select * from {dataset_id}.lake order by name" + ).to_dataframe(geography_as_object=True) + assert list(df["name"]) == ["bar", "baz", "foo"] + assert df["geog"][0] == wkt.loads("point(0 1)") + assert pandas.isna(df["geog"][1]) + assert df["geog"][2] == wkt.loads("point(0 0)") + + +def test_to_geodataframe(bigquery_client, dataset_id): + geopandas = pytest.importorskip("geopandas") + from shapely import wkt + + bigquery_client.query( + f"create table {dataset_id}.geolake (name string, geog geography)" + ).result() + bigquery_client.query( + f""" + insert into {dataset_id}.geolake (name, geog) values + ('foo', st_geogfromtext('point(0 0)')), + ('bar', st_geogfromtext('polygon((0 0, 1 0, 1 1, 0 0))')), + ('baz', null) + """ + ).result() + df = bigquery_client.query( + f"select * from {dataset_id}.geolake order by name" + ).to_geodataframe() + assert df["geog"][0] == wkt.loads("polygon((0 0, 1 0, 1 1, 0 0))") + assert pandas.isna(df["geog"][1]) + assert df["geog"][2] == wkt.loads("point(0 0)") + assert isinstance(df, geopandas.GeoDataFrame) + assert isinstance(df["geog"], geopandas.GeoSeries) + assert df.area[0] == 0.5 + assert pandas.isna(df.area[1]) + assert df.area[2] == 0.0 + assert df.crs.srs == "EPSG:4326" + assert df.crs.name == "WGS 84" + assert df.geog.crs.srs == "EPSG:4326" + assert df.geog.crs.name == "WGS 84" + + +def test_load_geodataframe(bigquery_client, dataset_id): + geopandas = pytest.importorskip("geopandas") + import pandas + from shapely import wkt + from google.cloud.bigquery.schema import SchemaField + + df = geopandas.GeoDataFrame( + pandas.DataFrame( + dict( + name=["foo", "bar"], + geo1=[None, None], + geo2=[None, wkt.loads("Point(1 1)")], + ) + ), + geometry="geo1", + ) + + table_id = f"{dataset_id}.lake_from_gp" + bigquery_client.load_table_from_dataframe(df, table_id).result() + + table = bigquery_client.get_table(table_id) + assert table.schema == [ + SchemaField("name", "STRING", "NULLABLE"), + SchemaField("geo1", "GEOGRAPHY", "NULLABLE"), + SchemaField("geo2", "GEOGRAPHY", "NULLABLE"), + ] + assert sorted(map(list, bigquery_client.list_rows(table_id))) == [ + ["bar", None, "POINT(1 1)"], + ["foo", None, None], + ] + + +def test_load_dataframe_w_shapely(bigquery_client, dataset_id): + wkt = pytest.importorskip("shapely.wkt") + from google.cloud.bigquery.schema import SchemaField + + df = pandas.DataFrame( + dict(name=["foo", "bar"], geo=[None, wkt.loads("Point(1 1)")]) + ) + + table_id = f"{dataset_id}.lake_from_shapes" + bigquery_client.load_table_from_dataframe(df, table_id).result() + + table = bigquery_client.get_table(table_id) + assert table.schema == [ + SchemaField("name", "STRING", "NULLABLE"), + SchemaField("geo", "GEOGRAPHY", "NULLABLE"), + ] + assert sorted(map(list, bigquery_client.list_rows(table_id))) == [ + ["bar", "POINT(1 1)"], + ["foo", None], + ] + + bigquery_client.load_table_from_dataframe(df, table_id).result() + assert sorted(map(list, bigquery_client.list_rows(table_id))) == [ + ["bar", "POINT(1 1)"], + ["bar", "POINT(1 1)"], + ["foo", None], + ["foo", None], + ] + + +def test_load_dataframe_w_wkb(bigquery_client, dataset_id): + wkt = pytest.importorskip("shapely.wkt") + from shapely import wkb + from google.cloud.bigquery.schema import SchemaField + + df = pandas.DataFrame( + dict(name=["foo", "bar"], geo=[None, wkb.dumps(wkt.loads("Point(1 1)"))]) + ) + + table_id = f"{dataset_id}.lake_from_wkb" + # We create the table first, to inform the interpretation of the wkb data + bigquery_client.query( + f"create table {table_id} (name string, geo GEOGRAPHY)" + ).result() + bigquery_client.load_table_from_dataframe(df, table_id).result() + + table = bigquery_client.get_table(table_id) + assert table.schema == [ + SchemaField("name", "STRING", "NULLABLE"), + SchemaField("geo", "GEOGRAPHY", "NULLABLE"), + ] + assert sorted(map(list, bigquery_client.list_rows(table_id))) == [ + ["bar", "POINT(1 1)"], + ["foo", None], + ] diff --git a/tests/system/test_structs.py b/tests/system/test_structs.py new file mode 100644 index 000000000..20740f614 --- /dev/null +++ b/tests/system/test_structs.py @@ -0,0 +1,31 @@ +import datetime + +import pytest + +from google.cloud.bigquery.dbapi import connect + +person_type = "struct>>" +person_type_sized = ( + "struct>>" +) + + +@pytest.mark.parametrize("person_type_decl", [person_type, person_type_sized]) +def test_structs(bigquery_client, dataset_id, person_type_decl, table_id): + conn = connect(bigquery_client) + cursor = conn.cursor() + cursor.execute(f"create table {table_id} (person {person_type_decl})") + data = dict( + name="par", + children=[ + dict(name="ch1", bdate=datetime.date(2021, 1, 1)), + dict(name="ch2", bdate=datetime.date(2021, 1, 2)), + ], + ) + cursor.execute( + f"insert into {table_id} (person) values (%(v:{person_type})s)", dict(v=data), + ) + + cursor.execute(f"select * from {table_id}") + [[result]] = list(cursor) + assert result == data diff --git a/tests/unit/__init__.py b/tests/unit/__init__.py index df379f1e9..4de65971c 100644 --- a/tests/unit/__init__.py +++ b/tests/unit/__init__.py @@ -1,4 +1,5 @@ -# Copyright 2016 Google LLC +# -*- coding: utf-8 -*- +# Copyright 2020 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. @@ -11,3 +12,4 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. +# diff --git a/tests/unit/gapic/__init__.py b/tests/unit/gapic/__init__.py new file mode 100644 index 000000000..4de65971c --- /dev/null +++ b/tests/unit/gapic/__init__.py @@ -0,0 +1,15 @@ +# -*- coding: utf-8 -*- +# Copyright 2020 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# diff --git a/tests/unit/job/helpers.py b/tests/unit/job/helpers.py index ea071c5ac..c792214e7 100644 --- a/tests/unit/job/helpers.py +++ b/tests/unit/job/helpers.py @@ -162,6 +162,7 @@ def _verifyInitialReadonlyProperties(self, job): self.assertIsNone(job.created) self.assertIsNone(job.started) self.assertIsNone(job.ended) + self.assertIsNone(job.transaction_info) # derived from resource['status'] self.assertIsNone(job.error_result) diff --git a/tests/unit/job/test_base.py b/tests/unit/job/test_base.py index 405ad6ee5..c3f7854e3 100644 --- a/tests/unit/job/test_base.py +++ b/tests/unit/job/test_base.py @@ -227,6 +227,20 @@ def test_script_statistics(self): self.assertEqual(stack_frame.end_column, 14) self.assertEqual(stack_frame.text, "QUERY TEXT") + def test_transaction_info(self): + from google.cloud.bigquery.job.base import TransactionInfo + + client = _make_client(project=self.PROJECT) + job = self._make_one(self.JOB_ID, client) + assert job.transaction_info is None + + statistics = job._properties["statistics"] = {} + assert job.transaction_info is None + + statistics["transactionInfo"] = {"transactionId": "123-abc-xyz"} + assert isinstance(job.transaction_info, TransactionInfo) + assert job.transaction_info.transaction_id == "123-abc-xyz" + def test_num_child_jobs(self): client = _make_client(project=self.PROJECT) job = self._make_one(self.JOB_ID, client) @@ -281,11 +295,11 @@ def test_user_email(self): @staticmethod def _datetime_and_millis(): import datetime - import pytz from google.cloud._helpers import _millis now = datetime.datetime.utcnow().replace( - microsecond=123000, tzinfo=pytz.UTC # stats timestamps have ms precision + microsecond=123000, + tzinfo=datetime.timezone.utc, # stats timestamps have ms precision ) return now, _millis(now) diff --git a/tests/unit/job/test_copy.py b/tests/unit/job/test_copy.py index fb0c87391..992efcf6b 100644 --- a/tests/unit/job/test_copy.py +++ b/tests/unit/job/test_copy.py @@ -28,18 +28,34 @@ def _get_target_class(): return CopyJobConfig + def test_ctor_defaults(self): + from google.cloud.bigquery.job import OperationType + + config = self._make_one() + + assert config.create_disposition is None + assert config.write_disposition is None + assert config.destination_encryption_configuration is None + assert config.operation_type == OperationType.OPERATION_TYPE_UNSPECIFIED + def test_ctor_w_properties(self): from google.cloud.bigquery.job import CreateDisposition + from google.cloud.bigquery.job import OperationType from google.cloud.bigquery.job import WriteDisposition create_disposition = CreateDisposition.CREATE_NEVER write_disposition = WriteDisposition.WRITE_TRUNCATE + snapshot_operation = OperationType.SNAPSHOT + config = self._get_target_class()( - create_disposition=create_disposition, write_disposition=write_disposition + create_disposition=create_disposition, + write_disposition=write_disposition, + operation_type=snapshot_operation, ) self.assertEqual(config.create_disposition, create_disposition) self.assertEqual(config.write_disposition, write_disposition) + self.assertEqual(config.operation_type, snapshot_operation) def test_to_api_repr_with_encryption(self): from google.cloud.bigquery.encryption_configuration import ( @@ -70,6 +86,22 @@ def test_to_api_repr_with_encryption_none(self): resource, {"copy": {"destinationEncryptionConfiguration": None}} ) + def test_operation_type_setting_none(self): + from google.cloud.bigquery.job import OperationType + + config = self._make_one(operation_type=OperationType.SNAPSHOT) + + # Setting it to None is the same as setting it to OPERATION_TYPE_UNSPECIFIED. + config.operation_type = None + assert config.operation_type == OperationType.OPERATION_TYPE_UNSPECIFIED + + def test_operation_type_setting_non_none(self): + from google.cloud.bigquery.job import OperationType + + config = self._make_one(operation_type=None) + config.operation_type = OperationType.RESTORE + assert config.operation_type == OperationType.RESTORE + class TestCopyJob(_Base): JOB_TYPE = "copy" diff --git a/tests/unit/job/test_load_config.py b/tests/unit/job/test_load_config.py index 63f15ec5a..cbe087dac 100644 --- a/tests/unit/job/test_load_config.py +++ b/tests/unit/job/test_load_config.py @@ -122,6 +122,45 @@ def test_create_disposition_setter(self): config.create_disposition = disposition self.assertEqual(config._properties["load"]["createDisposition"], disposition) + def test_decimal_target_types_miss(self): + config = self._get_target_class()() + self.assertIsNone(config.decimal_target_types) + + def test_decimal_target_types_hit(self): + from google.cloud.bigquery.enums import DecimalTargetType + + config = self._get_target_class()() + decimal_target_types = [DecimalTargetType.NUMERIC, DecimalTargetType.STRING] + config._properties["load"]["decimalTargetTypes"] = decimal_target_types + + expected = frozenset(decimal_target_types) + self.assertEqual(config.decimal_target_types, expected) + + def test_decimal_target_types_setter(self): + from google.cloud.bigquery.enums import DecimalTargetType + + decimal_target_types = (DecimalTargetType.NUMERIC, DecimalTargetType.BIGNUMERIC) + config = self._get_target_class()() + config.decimal_target_types = decimal_target_types + self.assertEqual( + config._properties["load"]["decimalTargetTypes"], + list(decimal_target_types), + ) + + def test_decimal_target_types_setter_w_none(self): + from google.cloud.bigquery.enums import DecimalTargetType + + config = self._get_target_class()() + decimal_target_types = [DecimalTargetType.BIGNUMERIC] + config._properties["load"]["decimalTargetTypes"] = decimal_target_types + + config.decimal_target_types = None + + self.assertIsNone(config.decimal_target_types) + self.assertNotIn("decimalTargetTypes", config._properties["load"]) + + config.decimal_target_types = None # No error if unsetting an unset property. + def test_destination_encryption_configuration_missing(self): config = self._get_target_class()() self.assertIsNone(config.destination_encryption_configuration) @@ -385,6 +424,17 @@ def test_null_marker_setter(self): config.null_marker = null_marker self.assertEqual(config._properties["load"]["nullMarker"], null_marker) + def test_projection_fields_miss(self): + config = self._get_target_class()() + self.assertIsNone(config.projection_fields) + + def test_projection_fields_hit(self): + config = self._get_target_class()() + fields = ["email", "postal_code"] + config.projection_fields = fields + self.assertEqual(config._properties["load"]["projectionFields"], fields) + self.assertEqual(config.projection_fields, fields) + def test_quote_character_missing(self): config = self._get_target_class()() self.assertIsNone(config.quote_character) @@ -434,11 +484,13 @@ def test_schema_setter_fields(self): "name": "full_name", "type": "STRING", "mode": "REQUIRED", + "policyTags": {"names": []}, } age_repr = { "name": "age", "type": "INTEGER", "mode": "REQUIRED", + "policyTags": {"names": []}, } self.assertEqual( config._properties["load"]["schema"], {"fields": [full_name_repr, age_repr]} @@ -451,11 +503,13 @@ def test_schema_setter_valid_mappings_list(self): "name": "full_name", "type": "STRING", "mode": "REQUIRED", + "policyTags": {"names": []}, } age_repr = { "name": "age", "type": "INTEGER", "mode": "REQUIRED", + "policyTags": {"names": []}, } schema = [full_name_repr, age_repr] config.schema = schema @@ -700,3 +754,38 @@ def test_write_disposition_setter(self): self.assertEqual( config._properties["load"]["writeDisposition"], write_disposition ) + + def test_parquet_options_missing(self): + config = self._get_target_class()() + self.assertIsNone(config.parquet_options) + + def test_parquet_options_hit(self): + config = self._get_target_class()() + config._properties["load"]["parquetOptions"] = dict( + enumAsString=True, enableListInference=False + ) + self.assertTrue(config.parquet_options.enum_as_string) + self.assertFalse(config.parquet_options.enable_list_inference) + + def test_parquet_options_setter(self): + from google.cloud.bigquery.format_options import ParquetOptions + + parquet_options = ParquetOptions.from_api_repr( + dict(enumAsString=False, enableListInference=True) + ) + config = self._get_target_class()() + + config.parquet_options = parquet_options + self.assertEqual( + config._properties["load"]["parquetOptions"], + {"enumAsString": False, "enableListInference": True}, + ) + + def test_parquet_options_setter_clearing(self): + config = self._get_target_class()() + config._properties["load"]["parquetOptions"] = dict( + enumAsString=False, enableListInference=True + ) + + config.parquet_options = None + self.assertNotIn("parquetOptions", config._properties["load"]) diff --git a/tests/unit/job/test_query.py b/tests/unit/job/test_query.py index 4665933ea..d41370520 100644 --- a/tests/unit/job/test_query.py +++ b/tests/unit/job/test_query.py @@ -110,6 +110,36 @@ def _verify_table_definitions(self, job, config): self.assertIsNotNone(expected_ec) self.assertEqual(found_ec.to_api_repr(), expected_ec) + def _verify_dml_stats_resource_properties(self, job, resource): + query_stats = resource.get("statistics", {}).get("query", {}) + + if "dmlStats" in query_stats: + resource_dml_stats = query_stats["dmlStats"] + job_dml_stats = job.dml_stats + assert str(job_dml_stats.inserted_row_count) == resource_dml_stats.get( + "insertedRowCount", "0" + ) + assert str(job_dml_stats.updated_row_count) == resource_dml_stats.get( + "updatedRowCount", "0" + ) + assert str(job_dml_stats.deleted_row_count) == resource_dml_stats.get( + "deletedRowCount", "0" + ) + else: + assert job.dml_stats is None + + def _verify_transaction_info_resource_properties(self, job, resource): + resource_stats = resource.get("statistics", {}) + + if "transactionInfo" in resource_stats: + resource_transaction_info = resource_stats["transactionInfo"] + job_transaction_info = job.transaction_info + assert job_transaction_info.transaction_id == resource_transaction_info.get( + "transactionId" + ) + else: + assert job.transaction_info is None + def _verify_configuration_properties(self, job, configuration): if "dryRun" in configuration: self.assertEqual(job.dry_run, configuration["dryRun"]) @@ -118,6 +148,8 @@ def _verify_configuration_properties(self, job, configuration): def _verifyResourceProperties(self, job, resource): self._verifyReadonlyResourceProperties(job, resource) + self._verify_dml_stats_resource_properties(job, resource) + self._verify_transaction_info_resource_properties(job, resource) configuration = resource.get("configuration", {}) self._verify_configuration_properties(job, configuration) @@ -130,16 +162,19 @@ def _verifyResourceProperties(self, job, resource): self._verify_table_definitions(job, query_config) self.assertEqual(job.query, query_config["query"]) + if "createDisposition" in query_config: self.assertEqual(job.create_disposition, query_config["createDisposition"]) else: self.assertIsNone(job.create_disposition) + if "defaultDataset" in query_config: ds_ref = job.default_dataset ds_ref = {"projectId": ds_ref.project, "datasetId": ds_ref.dataset_id} self.assertEqual(ds_ref, query_config["defaultDataset"]) else: self.assertIsNone(job.default_dataset) + if "destinationTable" in query_config: table = job.destination tb_ref = { @@ -150,14 +185,17 @@ def _verifyResourceProperties(self, job, resource): self.assertEqual(tb_ref, query_config["destinationTable"]) else: self.assertIsNone(job.destination) + if "priority" in query_config: self.assertEqual(job.priority, query_config["priority"]) else: self.assertIsNone(job.priority) + if "writeDisposition" in query_config: self.assertEqual(job.write_disposition, query_config["writeDisposition"]) else: self.assertIsNone(job.write_disposition) + if "destinationEncryptionConfiguration" in query_config: self.assertIsNotNone(job.destination_encryption_configuration) self.assertEqual( @@ -166,6 +204,7 @@ def _verifyResourceProperties(self, job, resource): ) else: self.assertIsNone(job.destination_encryption_configuration) + if "schemaUpdateOptions" in query_config: self.assertEqual( job.schema_update_options, query_config["schemaUpdateOptions"] @@ -190,6 +229,7 @@ def test_ctor_defaults(self): self.assertIsNone(job.create_disposition) self.assertIsNone(job.default_dataset) self.assertIsNone(job.destination) + self.assertIsNone(job.dml_stats) self.assertIsNone(job.flatten_results) self.assertIsNone(job.priority) self.assertIsNone(job.use_query_cache) @@ -278,6 +318,42 @@ def test_from_api_repr_with_encryption(self): self.assertIs(job._client, client) self._verifyResourceProperties(job, RESOURCE) + def test_from_api_repr_with_dml_stats(self): + self._setUpConstants() + client = _make_client(project=self.PROJECT) + RESOURCE = { + "id": self.JOB_ID, + "jobReference": {"projectId": self.PROJECT, "jobId": self.JOB_ID}, + "configuration": {"query": {"query": self.QUERY}}, + "statistics": { + "query": { + "dmlStats": {"insertedRowCount": "15", "updatedRowCount": "2"}, + }, + }, + } + klass = self._get_target_class() + + job = klass.from_api_repr(RESOURCE, client=client) + + self.assertIs(job._client, client) + self._verifyResourceProperties(job, RESOURCE) + + def test_from_api_repr_with_transaction_info(self): + self._setUpConstants() + client = _make_client(project=self.PROJECT) + RESOURCE = { + "id": self.JOB_ID, + "jobReference": {"projectId": self.PROJECT, "jobId": self.JOB_ID}, + "configuration": {"query": {"query": self.QUERY}}, + "statistics": {"transactionInfo": {"transactionId": "1a2b-3c4d"}}, + } + klass = self._get_target_class() + + job = klass.from_api_repr(RESOURCE, client=client) + + self.assertIs(job._client, client) + self._verifyResourceProperties(job, RESOURCE) + def test_from_api_repr_w_properties(self): from google.cloud.bigquery.job import CreateDisposition from google.cloud.bigquery.job import SchemaUpdateOption @@ -815,6 +891,23 @@ def test_estimated_bytes_processed(self): query_stats["estimatedBytesProcessed"] = str(est_bytes) self.assertEqual(job.estimated_bytes_processed, est_bytes) + def test_dml_stats(self): + from google.cloud.bigquery.job.query import DmlStats + + client = _make_client(project=self.PROJECT) + job = self._make_one(self.JOB_ID, self.QUERY, client) + assert job.dml_stats is None + + statistics = job._properties["statistics"] = {} + assert job.dml_stats is None + + query_stats = statistics["query"] = {} + assert job.dml_stats is None + + query_stats["dmlStats"] = {"insertedRowCount": "35"} + assert isinstance(job.dml_stats, DmlStats) + assert job.dml_stats.inserted_row_count == 35 + def test_result(self): from google.cloud.bigquery.table import RowIterator diff --git a/tests/unit/job/test_query_config.py b/tests/unit/job/test_query_config.py index db03d6a3b..109cf7e44 100644 --- a/tests/unit/job/test_query_config.py +++ b/tests/unit/job/test_query_config.py @@ -253,3 +253,59 @@ def test_from_api_repr_with_encryption(self): self.assertEqual( config.destination_encryption_configuration.kms_key_name, self.KMS_KEY_NAME ) + + def test_to_api_repr_with_script_options_none(self): + config = self._make_one() + config.script_options = None + + resource = config.to_api_repr() + + self.assertEqual(resource, {"query": {"scriptOptions": None}}) + self.assertIsNone(config.script_options) + + def test_to_api_repr_with_script_options(self): + from google.cloud.bigquery import KeyResultStatementKind + from google.cloud.bigquery import ScriptOptions + + config = self._make_one() + config.script_options = ScriptOptions( + statement_timeout_ms=60, + statement_byte_budget=999, + key_result_statement=KeyResultStatementKind.FIRST_SELECT, + ) + + resource = config.to_api_repr() + + expected_script_options_repr = { + "statementTimeoutMs": "60", + "statementByteBudget": "999", + "keyResultStatement": KeyResultStatementKind.FIRST_SELECT, + } + self.assertEqual( + resource, {"query": {"scriptOptions": expected_script_options_repr}} + ) + + def test_from_api_repr_with_script_options(self): + from google.cloud.bigquery import KeyResultStatementKind + from google.cloud.bigquery import ScriptOptions + + resource = { + "query": { + "scriptOptions": { + "statementTimeoutMs": "42", + "statementByteBudget": "123", + "keyResultStatement": KeyResultStatementKind.LAST, + }, + }, + } + klass = self._get_target_class() + + config = klass.from_api_repr(resource) + + script_options = config.script_options + self.assertIsInstance(script_options, ScriptOptions) + self.assertEqual(script_options.statement_timeout_ms, 42) + self.assertEqual(script_options.statement_byte_budget, 123) + self.assertEqual( + script_options.key_result_statement, KeyResultStatementKind.LAST + ) diff --git a/tests/unit/job/test_query_pandas.py b/tests/unit/job/test_query_pandas.py index 0f9623203..b5af90c0b 100644 --- a/tests/unit/job/test_query_pandas.py +++ b/tests/unit/job/test_query_pandas.py @@ -23,6 +23,14 @@ import pandas except (ImportError, AttributeError): # pragma: NO COVER pandas = None +try: + import shapely +except (ImportError, AttributeError): # pragma: NO COVER + shapely = None +try: + import geopandas +except (ImportError, AttributeError): # pragma: NO COVER + geopandas = None try: import pyarrow except (ImportError, AttributeError): # pragma: NO COVER @@ -238,6 +246,41 @@ def test_to_arrow(): ] +@pytest.mark.skipif(pyarrow is None, reason="Requires `pyarrow`") +def test_to_arrow_max_results_no_progress_bar(): + from google.cloud.bigquery import table + from google.cloud.bigquery.job import QueryJob as target_class + from google.cloud.bigquery.schema import SchemaField + + connection = _make_connection({}) + client = _make_client(connection=connection) + begun_resource = _make_job_resource(job_type="query") + job = target_class.from_api_repr(begun_resource, client) + + schema = [ + SchemaField("name", "STRING", mode="REQUIRED"), + SchemaField("age", "INTEGER", mode="REQUIRED"), + ] + rows = [ + {"f": [{"v": "Bharney Rhubble"}, {"v": "33"}]}, + {"f": [{"v": "Wylma Phlyntstone"}, {"v": "29"}]}, + ] + path = "/foo" + api_request = mock.Mock(return_value={"rows": rows}) + row_iterator = table.RowIterator(client, api_request, path, schema) + + result_patch = mock.patch( + "google.cloud.bigquery.job.QueryJob.result", return_value=row_iterator, + ) + with result_patch as result_patch_tqdm: + tbl = job.to_arrow(create_bqstorage_client=False, max_results=123) + + result_patch_tqdm.assert_called_once_with(max_results=123) + + assert isinstance(tbl, pyarrow.Table) + assert tbl.num_rows == 2 + + @pytest.mark.skipif(pyarrow is None, reason="Requires `pyarrow`") @pytest.mark.skipif(tqdm is None, reason="Requires `tqdm`") def test_to_arrow_w_tqdm_w_query_plan(): @@ -290,7 +333,9 @@ def test_to_arrow_w_tqdm_w_query_plan(): assert result_patch_tqdm.call_count == 3 assert isinstance(tbl, pyarrow.Table) assert tbl.num_rows == 2 - result_patch_tqdm.assert_called_with(timeout=_PROGRESS_BAR_UPDATE_INTERVAL) + result_patch_tqdm.assert_called_with( + timeout=_PROGRESS_BAR_UPDATE_INTERVAL, max_results=None + ) @pytest.mark.skipif(pyarrow is None, reason="Requires `pyarrow`") @@ -341,7 +386,9 @@ def test_to_arrow_w_tqdm_w_pending_status(): assert result_patch_tqdm.call_count == 2 assert isinstance(tbl, pyarrow.Table) assert tbl.num_rows == 2 - result_patch_tqdm.assert_called_with(timeout=_PROGRESS_BAR_UPDATE_INTERVAL) + result_patch_tqdm.assert_called_with( + timeout=_PROGRESS_BAR_UPDATE_INTERVAL, max_results=None + ) @pytest.mark.skipif(pyarrow is None, reason="Requires `pyarrow`") @@ -386,38 +433,41 @@ def test_to_arrow_w_tqdm_wo_query_plan(): result_patch_tqdm.assert_called() -@pytest.mark.skipif(pandas is None, reason="Requires `pandas`") -def test_to_dataframe(): +def _make_job(schema=(), rows=()): from google.cloud.bigquery.job import QueryJob as target_class begun_resource = _make_job_resource(job_type="query") query_resource = { "jobComplete": True, "jobReference": begun_resource["jobReference"], - "totalRows": "4", + "totalRows": str(len(rows)), "schema": { "fields": [ - {"name": "name", "type": "STRING", "mode": "NULLABLE"}, - {"name": "age", "type": "INTEGER", "mode": "NULLABLE"}, + dict(name=field[0], type=field[1], mode=field[2]) for field in schema ] }, } - tabledata_resource = { - "rows": [ - {"f": [{"v": "Phred Phlyntstone"}, {"v": "32"}]}, - {"f": [{"v": "Bharney Rhubble"}, {"v": "33"}]}, - {"f": [{"v": "Wylma Phlyntstone"}, {"v": "29"}]}, - {"f": [{"v": "Bhettye Rhubble"}, {"v": "27"}]}, - ] - } + tabledata_resource = {"rows": [{"f": [{"v": v} for v in row]} for row in rows]} done_resource = copy.deepcopy(begun_resource) done_resource["status"] = {"state": "DONE"} connection = _make_connection( begun_resource, query_resource, done_resource, tabledata_resource ) client = _make_client(connection=connection) - job = target_class.from_api_repr(begun_resource, client) + return target_class.from_api_repr(begun_resource, client) + +@pytest.mark.skipif(pandas is None, reason="Requires `pandas`") +def test_to_dataframe(): + job = _make_job( + (("name", "STRING", "NULLABLE"), ("age", "INTEGER", "NULLABLE")), + ( + ("Phred Phlyntstone", "32"), + ("Bharney Rhubble", "33"), + ("Wylma Phlyntstone", "29"), + ("Bhettye Rhubble", "27"), + ), + ) df = job.to_dataframe(create_bqstorage_client=False) assert isinstance(df, pandas.DataFrame) @@ -716,7 +766,9 @@ def test_to_dataframe_w_tqdm_pending(): assert isinstance(df, pandas.DataFrame) assert len(df) == 4 # verify the number of rows assert list(df) == ["name", "age"] # verify the column names - result_patch_tqdm.assert_called_with(timeout=_PROGRESS_BAR_UPDATE_INTERVAL) + result_patch_tqdm.assert_called_with( + timeout=_PROGRESS_BAR_UPDATE_INTERVAL, max_results=None + ) @pytest.mark.skipif(pandas is None, reason="Requires `pandas`") @@ -774,4 +826,147 @@ def test_to_dataframe_w_tqdm(): assert isinstance(df, pandas.DataFrame) assert len(df) == 4 # verify the number of rows assert list(df), ["name", "age"] # verify the column names - result_patch_tqdm.assert_called_with(timeout=_PROGRESS_BAR_UPDATE_INTERVAL) + result_patch_tqdm.assert_called_with( + timeout=_PROGRESS_BAR_UPDATE_INTERVAL, max_results=None + ) + + +@pytest.mark.skipif(pandas is None, reason="Requires `pandas`") +@pytest.mark.skipif(tqdm is None, reason="Requires `tqdm`") +def test_to_dataframe_w_tqdm_max_results(): + from google.cloud.bigquery import table + from google.cloud.bigquery.job import QueryJob as target_class + from google.cloud.bigquery.schema import SchemaField + from google.cloud.bigquery._tqdm_helpers import _PROGRESS_BAR_UPDATE_INTERVAL + + begun_resource = _make_job_resource(job_type="query") + schema = [ + SchemaField("name", "STRING", mode="NULLABLE"), + SchemaField("age", "INTEGER", mode="NULLABLE"), + ] + rows = [{"f": [{"v": "Phred Phlyntstone"}, {"v": "32"}]}] + + connection = _make_connection({}) + client = _make_client(connection=connection) + job = target_class.from_api_repr(begun_resource, client) + + path = "/foo" + api_request = mock.Mock(return_value={"rows": rows}) + row_iterator = table.RowIterator(client, api_request, path, schema) + + job._properties["statistics"] = { + "query": { + "queryPlan": [ + {"name": "S00: Input", "id": "0", "status": "COMPLETE"}, + {"name": "S01: Output", "id": "1", "status": "COMPLETE"}, + ] + }, + } + reload_patch = mock.patch( + "google.cloud.bigquery.job._AsyncJob.reload", autospec=True + ) + result_patch = mock.patch( + "google.cloud.bigquery.job.QueryJob.result", + side_effect=[concurrent.futures.TimeoutError, row_iterator], + ) + + with result_patch as result_patch_tqdm, reload_patch: + job.to_dataframe( + progress_bar_type="tqdm", create_bqstorage_client=False, max_results=3 + ) + + assert result_patch_tqdm.call_count == 2 + result_patch_tqdm.assert_called_with( + timeout=_PROGRESS_BAR_UPDATE_INTERVAL, max_results=3 + ) + + +@pytest.mark.skipif(pandas is None, reason="Requires `pandas`") +@pytest.mark.skipif(shapely is None, reason="Requires `shapely`") +def test_to_dataframe_geography_as_object(): + job = _make_job( + (("name", "STRING", "NULLABLE"), ("geog", "GEOGRAPHY", "NULLABLE")), + ( + ("Phred Phlyntstone", "Point(0 0)"), + ("Bharney Rhubble", "Point(0 1)"), + ("Wylma Phlyntstone", None), + ), + ) + df = job.to_dataframe(create_bqstorage_client=False, geography_as_object=True) + + assert isinstance(df, pandas.DataFrame) + assert len(df) == 3 # verify the number of rows + assert list(df) == ["name", "geog"] # verify the column names + assert [v.__class__.__name__ for v in df.geog] == [ + "Point", + "Point", + "float", + ] # float because nan + + +@pytest.mark.skipif(geopandas is None, reason="Requires `geopandas`") +def test_to_geodataframe(): + job = _make_job( + (("name", "STRING", "NULLABLE"), ("geog", "GEOGRAPHY", "NULLABLE")), + ( + ("Phred Phlyntstone", "Point(0 0)"), + ("Bharney Rhubble", "Point(0 1)"), + ("Wylma Phlyntstone", None), + ), + ) + df = job.to_geodataframe(create_bqstorage_client=False) + + assert isinstance(df, geopandas.GeoDataFrame) + assert len(df) == 3 # verify the number of rows + assert list(df) == ["name", "geog"] # verify the column names + assert [v.__class__.__name__ for v in df.geog] == [ + "Point", + "Point", + "NoneType", + ] # float because nan + assert isinstance(df.geog, geopandas.GeoSeries) + + +@pytest.mark.skipif(geopandas is None, reason="Requires `geopandas`") +@mock.patch("google.cloud.bigquery.job.query.wait_for_query") +def test_query_job_to_geodataframe_delegation(wait_for_query): + """ + QueryJob.to_geodataframe just delegates to RowIterator.to_geodataframe. + + This test just demonstrates that. We don't need to test all the + variations, which are tested for RowIterator. + """ + import numpy + + job = _make_job() + bqstorage_client = object() + dtypes = dict(xxx=numpy.dtype("int64")) + progress_bar_type = "normal" + create_bqstorage_client = False + date_as_object = False + max_results = 42 + geography_column = "g" + + df = job.to_geodataframe( + bqstorage_client=bqstorage_client, + dtypes=dtypes, + progress_bar_type=progress_bar_type, + create_bqstorage_client=create_bqstorage_client, + date_as_object=date_as_object, + max_results=max_results, + geography_column=geography_column, + ) + + wait_for_query.assert_called_once_with( + job, progress_bar_type, max_results=max_results + ) + row_iterator = wait_for_query.return_value + row_iterator.to_geodataframe.assert_called_once_with( + bqstorage_client=bqstorage_client, + dtypes=dtypes, + progress_bar_type=progress_bar_type, + create_bqstorage_client=create_bqstorage_client, + date_as_object=date_as_object, + geography_column=geography_column, + ) + assert df is row_iterator.to_geodataframe.return_value diff --git a/tests/unit/job/test_query_stats.py b/tests/unit/job/test_query_stats.py index 09a0efc45..e70eb097c 100644 --- a/tests/unit/job/test_query_stats.py +++ b/tests/unit/job/test_query_stats.py @@ -15,6 +15,43 @@ from .helpers import _Base +class TestDmlStats: + @staticmethod + def _get_target_class(): + from google.cloud.bigquery.job import DmlStats + + return DmlStats + + def _make_one(self, *args, **kw): + return self._get_target_class()(*args, **kw) + + def test_ctor_defaults(self): + dml_stats = self._make_one() + assert dml_stats.inserted_row_count == 0 + assert dml_stats.deleted_row_count == 0 + assert dml_stats.updated_row_count == 0 + + def test_from_api_repr_partial_stats(self): + klass = self._get_target_class() + result = klass.from_api_repr({"deletedRowCount": "12"}) + + assert isinstance(result, klass) + assert result.inserted_row_count == 0 + assert result.deleted_row_count == 12 + assert result.updated_row_count == 0 + + def test_from_api_repr_full_stats(self): + klass = self._get_target_class() + result = klass.from_api_repr( + {"updatedRowCount": "4", "insertedRowCount": "7", "deletedRowCount": "25"} + ) + + assert isinstance(result, klass) + assert result.inserted_row_count == 7 + assert result.deleted_row_count == 25 + assert result.updated_row_count == 4 + + class TestQueryPlanEntryStep(_Base): KIND = "KIND" SUBSTEPS = ("SUB1", "SUB2") diff --git a/tests/unit/routine/test_routine.py b/tests/unit/routine/test_routine.py index 0a59e7c5f..fdaf13324 100644 --- a/tests/unit/routine/test_routine.py +++ b/tests/unit/routine/test_routine.py @@ -156,12 +156,86 @@ def test_from_api_repr(target_class): assert actual_routine.return_type == bigquery_v2.types.StandardSqlDataType( type_kind=bigquery_v2.types.StandardSqlDataType.TypeKind.INT64 ) + assert actual_routine.return_table_type is None assert actual_routine.type_ == "SCALAR_FUNCTION" assert actual_routine._properties["someNewField"] == "someValue" assert actual_routine.description == "A routine description." assert actual_routine.determinism_level == "DETERMINISTIC" +def test_from_api_repr_tvf_function(target_class): + from google.cloud.bigquery.routine import RoutineArgument + from google.cloud.bigquery.routine import RoutineReference + from google.cloud.bigquery.routine import RoutineType + + StandardSqlDataType = bigquery_v2.types.StandardSqlDataType + StandardSqlField = bigquery_v2.types.StandardSqlField + StandardSqlTableType = bigquery_v2.types.StandardSqlTableType + + creation_time = datetime.datetime( + 2010, 5, 19, 16, 0, 0, tzinfo=google.cloud._helpers.UTC + ) + modified_time = datetime.datetime( + 2011, 10, 1, 16, 0, 0, tzinfo=google.cloud._helpers.UTC + ) + resource = { + "routineReference": { + "projectId": "my-project", + "datasetId": "my_dataset", + "routineId": "my_routine", + }, + "etag": "abcdefg", + "creationTime": str(google.cloud._helpers._millis(creation_time)), + "lastModifiedTime": str(google.cloud._helpers._millis(modified_time)), + "definitionBody": "SELECT x FROM UNNEST([1,2,3]) x WHERE x > a", + "arguments": [{"name": "a", "dataType": {"typeKind": "INT64"}}], + "language": "SQL", + "returnTableType": { + "columns": [{"name": "int_col", "type": {"typeKind": "INT64"}}] + }, + "routineType": "TABLE_VALUED_FUNCTION", + "someNewField": "someValue", + "description": "A routine description.", + "determinismLevel": bigquery.DeterminismLevel.DETERMINISTIC, + } + actual_routine = target_class.from_api_repr(resource) + + assert actual_routine.project == "my-project" + assert actual_routine.dataset_id == "my_dataset" + assert actual_routine.routine_id == "my_routine" + assert ( + actual_routine.path + == "/projects/my-project/datasets/my_dataset/routines/my_routine" + ) + assert actual_routine.reference == RoutineReference.from_string( + "my-project.my_dataset.my_routine" + ) + assert actual_routine.etag == "abcdefg" + assert actual_routine.created == creation_time + assert actual_routine.modified == modified_time + assert actual_routine.arguments == [ + RoutineArgument( + name="a", + data_type=StandardSqlDataType(type_kind=StandardSqlDataType.TypeKind.INT64), + ) + ] + assert actual_routine.body == "SELECT x FROM UNNEST([1,2,3]) x WHERE x > a" + assert actual_routine.language == "SQL" + assert actual_routine.return_type is None + assert actual_routine.return_table_type == StandardSqlTableType( + columns=[ + StandardSqlField( + name="int_col", + type=StandardSqlDataType(type_kind=StandardSqlDataType.TypeKind.INT64), + ) + ] + ) + assert actual_routine.type_ == RoutineType.TABLE_VALUED_FUNCTION + assert actual_routine._properties["someNewField"] == "someValue" + assert actual_routine.description == "A routine description." + assert actual_routine.determinism_level == "DETERMINISTIC" + + def test_from_api_repr_w_minimal_resource(target_class): from google.cloud.bigquery.routine import RoutineReference @@ -261,6 +335,24 @@ def test_from_api_repr_w_unknown_fields(target_class): ["return_type"], {"returnType": {"typeKind": "INT64"}}, ), + ( + { + "definitionBody": "SELECT x FROM UNNEST([1,2,3]) x WHERE x > 1", + "language": "SQL", + "returnTableType": { + "columns": [{"name": "int_col", "type": {"typeKind": "INT64"}}] + }, + "routineType": "TABLE_VALUED_FUNCTION", + "description": "A routine description.", + "determinismLevel": bigquery.DeterminismLevel.DETERMINISM_LEVEL_UNSPECIFIED, + }, + ["return_table_type"], + { + "returnTableType": { + "columns": [{"name": "int_col", "type": {"typeKind": "INT64"}}] + } + }, + ), ( { "arguments": [{"name": "x", "dataType": {"typeKind": "INT64"}}], @@ -361,6 +453,41 @@ def test_set_return_type_w_none(object_under_test): assert object_under_test._properties["returnType"] is None +def test_set_return_table_type_w_none(object_under_test): + object_under_test.return_table_type = None + assert object_under_test.return_table_type is None + assert object_under_test._properties["returnTableType"] is None + + +def test_set_return_table_type_w_not_none(object_under_test): + StandardSqlDataType = bigquery_v2.types.StandardSqlDataType + StandardSqlField = bigquery_v2.types.StandardSqlField + StandardSqlTableType = bigquery_v2.types.StandardSqlTableType + + table_type = StandardSqlTableType( + columns=[ + StandardSqlField( + name="int_col", + type=StandardSqlDataType(type_kind=StandardSqlDataType.TypeKind.INT64), + ), + StandardSqlField( + name="str_col", + type=StandardSqlDataType(type_kind=StandardSqlDataType.TypeKind.STRING), + ), + ] + ) + + object_under_test.return_table_type = table_type + + assert object_under_test.return_table_type == table_type + assert object_under_test._properties["returnTableType"] == { + "columns": [ + {"name": "int_col", "type": {"typeKind": "INT64"}}, + {"name": "str_col", "type": {"typeKind": "STRING"}}, + ] + } + + def test_set_description_w_none(object_under_test): object_under_test.description = None assert object_under_test.description is None diff --git a/tests/unit/test__helpers.py b/tests/unit/test__helpers.py index 2437f3568..f8d00e67d 100644 --- a/tests/unit/test__helpers.py +++ b/tests/unit/test__helpers.py @@ -19,6 +19,75 @@ import mock +try: + from google.cloud import bigquery_storage +except ImportError: # pragma: NO COVER + bigquery_storage = None + + +@unittest.skipIf(bigquery_storage is None, "Requires `google-cloud-bigquery-storage`") +class TestBQStorageVersions(unittest.TestCase): + def _object_under_test(self): + from google.cloud.bigquery import _helpers + + return _helpers.BQStorageVersions() + + def _call_fut(self): + from google.cloud.bigquery import _helpers + + _helpers.BQ_STORAGE_VERSIONS._installed_version = None + return _helpers.BQ_STORAGE_VERSIONS.verify_version() + + def test_raises_no_error_w_recent_bqstorage(self): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + with mock.patch("google.cloud.bigquery_storage.__version__", new="2.0.0"): + try: + self._call_fut() + except LegacyBigQueryStorageError: # pragma: NO COVER + self.fail("Legacy error raised with a non-legacy dependency version.") + + def test_raises_error_w_legacy_bqstorage(self): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + with mock.patch("google.cloud.bigquery_storage.__version__", new="1.9.9"): + with self.assertRaises(LegacyBigQueryStorageError): + self._call_fut() + + def test_raises_error_w_unknown_bqstorage_version(self): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + with mock.patch("google.cloud.bigquery_storage", autospec=True) as fake_module: + del fake_module.__version__ + error_pattern = r"version found: 0.0.0" + with self.assertRaisesRegex(LegacyBigQueryStorageError, error_pattern): + self._call_fut() + + def test_installed_version_returns_cached(self): + versions = self._object_under_test() + versions._installed_version = object() + assert versions.installed_version is versions._installed_version + + def test_installed_version_returns_parsed_version(self): + versions = self._object_under_test() + + with mock.patch("google.cloud.bigquery_storage.__version__", new="1.2.3"): + version = versions.installed_version + + assert version.major == 1 + assert version.minor == 2 + assert version.micro == 3 + + def test_is_read_session_optional_true(self): + versions = self._object_under_test() + with mock.patch("google.cloud.bigquery_storage.__version__", new="2.6.0"): + assert versions.is_read_session_optional + + def test_is_read_session_optional_false(self): + versions = self._object_under_test() + with mock.patch("google.cloud.bigquery_storage.__version__", new="2.5.0"): + assert not versions.is_read_session_optional + class Test_not_null(unittest.TestCase): def _call_fut(self, value, field): @@ -618,9 +687,48 @@ def _call_fut(self, value): return _float_to_json(value) + def test_w_none(self): + self.assertEqual(self._call_fut(None), None) + + def test_w_non_numeric(self): + with self.assertRaises(TypeError): + self._call_fut(object()) + + def test_w_integer(self): + result = self._call_fut(123) + self.assertIsInstance(result, float) + self.assertEqual(result, 123.0) + def test_w_float(self): self.assertEqual(self._call_fut(1.23), 1.23) + def test_w_float_as_string(self): + self.assertEqual(self._call_fut("1.23"), 1.23) + + def test_w_nan(self): + result = self._call_fut(float("nan")) + self.assertEqual(result.lower(), "nan") + + def test_w_nan_as_string(self): + result = self._call_fut("NaN") + self.assertEqual(result.lower(), "nan") + + def test_w_infinity(self): + result = self._call_fut(float("inf")) + self.assertEqual(result.lower(), "inf") + + def test_w_infinity_as_string(self): + result = self._call_fut("inf") + self.assertEqual(result.lower(), "inf") + + def test_w_negative_infinity(self): + result = self._call_fut(float("-inf")) + self.assertEqual(result.lower(), "-inf") + + def test_w_negative_infinity_as_string(self): + result = self._call_fut("-inf") + self.assertEqual(result.lower(), "-inf") + class Test_decimal_to_json(unittest.TestCase): def _call_fut(self, value): diff --git a/tests/unit/test__pandas_helpers.py b/tests/unit/test__pandas_helpers.py index 39a3d845b..a9b0ae21f 100644 --- a/tests/unit/test__pandas_helpers.py +++ b/tests/unit/test__pandas_helpers.py @@ -19,6 +19,7 @@ import operator import queue import warnings +import pkg_resources import mock @@ -35,22 +36,31 @@ # Mock out pyarrow when missing, because methods from pyarrow.types are # used in test parameterization. pyarrow = mock.Mock() +try: + import geopandas +except ImportError: # pragma: NO COVER + geopandas = None + import pytest -import pytz from google import api_core +from google.cloud.bigquery import _helpers from google.cloud.bigquery import schema -from google.cloud.bigquery._pandas_helpers import _BIGNUMERIC_SUPPORT try: from google.cloud import bigquery_storage + + _helpers.BQ_STORAGE_VERSIONS.verify_version() except ImportError: # pragma: NO COVER bigquery_storage = None +PANDAS_MINIUM_VERSION = pkg_resources.parse_version("1.0.0") -skip_if_no_bignumeric = pytest.mark.skipif( - not _BIGNUMERIC_SUPPORT, reason="BIGNUMERIC support requires pyarrow>=3.0.0", -) +if pandas is not None: + PANDAS_INSTALLED_VERSION = pkg_resources.get_distribution("pandas").parsed_version +else: + # Set to less than MIN version. + PANDAS_INSTALLED_VERSION = pkg_resources.parse_version("0.0.0") @pytest.fixture @@ -141,9 +151,7 @@ def test_all_(): ("FLOAT", "NULLABLE", pyarrow.types.is_float64), ("FLOAT64", "NULLABLE", pyarrow.types.is_float64), ("NUMERIC", "NULLABLE", is_numeric), - pytest.param( - "BIGNUMERIC", "NULLABLE", is_bignumeric, marks=skip_if_no_bignumeric, - ), + ("BIGNUMERIC", "NULLABLE", is_bignumeric), ("BOOLEAN", "NULLABLE", pyarrow.types.is_boolean), ("BOOL", "NULLABLE", pyarrow.types.is_boolean), ("TIMESTAMP", "NULLABLE", is_timestamp), @@ -222,11 +230,10 @@ def test_all_(): "REPEATED", all_(pyarrow.types.is_list, lambda type_: is_numeric(type_.value_type)), ), - pytest.param( + ( "BIGNUMERIC", "REPEATED", all_(pyarrow.types.is_list, lambda type_: is_bignumeric(type_.value_type)), - marks=skip_if_no_bignumeric, ), ( "BOOLEAN", @@ -300,6 +307,7 @@ def test_bq_to_arrow_data_type_w_struct(module_under_test, bq_type): schema.SchemaField("field05", "FLOAT"), schema.SchemaField("field06", "FLOAT64"), schema.SchemaField("field07", "NUMERIC"), + schema.SchemaField("field08", "BIGNUMERIC"), schema.SchemaField("field09", "BOOLEAN"), schema.SchemaField("field10", "BOOL"), schema.SchemaField("field11", "TIMESTAMP"), @@ -309,9 +317,6 @@ def test_bq_to_arrow_data_type_w_struct(module_under_test, bq_type): schema.SchemaField("field15", "GEOGRAPHY"), ) - if _BIGNUMERIC_SUPPORT: - fields += (schema.SchemaField("field08", "BIGNUMERIC"),) - field = schema.SchemaField("ignored_name", bq_type, mode="NULLABLE", fields=fields) actual = module_under_test.bq_to_arrow_data_type(field) @@ -323,6 +328,7 @@ def test_bq_to_arrow_data_type_w_struct(module_under_test, bq_type): pyarrow.field("field05", pyarrow.float64()), pyarrow.field("field06", pyarrow.float64()), pyarrow.field("field07", module_under_test.pyarrow_numeric()), + pyarrow.field("field08", module_under_test.pyarrow_bignumeric()), pyarrow.field("field09", pyarrow.bool_()), pyarrow.field("field10", pyarrow.bool_()), pyarrow.field("field11", module_under_test.pyarrow_timestamp()), @@ -331,8 +337,6 @@ def test_bq_to_arrow_data_type_w_struct(module_under_test, bq_type): pyarrow.field("field14", module_under_test.pyarrow_datetime()), pyarrow.field("field15", pyarrow.string()), ) - if _BIGNUMERIC_SUPPORT: - expected += (pyarrow.field("field08", module_under_test.pyarrow_bignumeric()),) expected = pyarrow.struct(expected) assert pyarrow.types.is_struct(actual) @@ -351,6 +355,7 @@ def test_bq_to_arrow_data_type_w_array_struct(module_under_test, bq_type): schema.SchemaField("field05", "FLOAT"), schema.SchemaField("field06", "FLOAT64"), schema.SchemaField("field07", "NUMERIC"), + schema.SchemaField("field08", "BIGNUMERIC"), schema.SchemaField("field09", "BOOLEAN"), schema.SchemaField("field10", "BOOL"), schema.SchemaField("field11", "TIMESTAMP"), @@ -360,9 +365,6 @@ def test_bq_to_arrow_data_type_w_array_struct(module_under_test, bq_type): schema.SchemaField("field15", "GEOGRAPHY"), ) - if _BIGNUMERIC_SUPPORT: - fields += (schema.SchemaField("field08", "BIGNUMERIC"),) - field = schema.SchemaField("ignored_name", bq_type, mode="REPEATED", fields=fields) actual = module_under_test.bq_to_arrow_data_type(field) @@ -374,6 +376,7 @@ def test_bq_to_arrow_data_type_w_array_struct(module_under_test, bq_type): pyarrow.field("field05", pyarrow.float64()), pyarrow.field("field06", pyarrow.float64()), pyarrow.field("field07", module_under_test.pyarrow_numeric()), + pyarrow.field("field08", module_under_test.pyarrow_bignumeric()), pyarrow.field("field09", pyarrow.bool_()), pyarrow.field("field10", pyarrow.bool_()), pyarrow.field("field11", module_under_test.pyarrow_timestamp()), @@ -382,8 +385,6 @@ def test_bq_to_arrow_data_type_w_array_struct(module_under_test, bq_type): pyarrow.field("field14", module_under_test.pyarrow_datetime()), pyarrow.field("field15", pyarrow.string()), ) - if _BIGNUMERIC_SUPPORT: - expected += (pyarrow.field("field08", module_under_test.pyarrow_bignumeric()),) expected_value_type = pyarrow.struct(expected) assert pyarrow.types.is_list(actual) @@ -429,7 +430,7 @@ def test_bq_to_arrow_data_type_w_struct_unknown_subfield(module_under_test): decimal.Decimal("999.123456789"), ], ), - pytest.param( + ( "BIGNUMERIC", [ decimal.Decimal("-{d38}.{d38}".format(d38="9" * 38)), @@ -437,17 +438,18 @@ def test_bq_to_arrow_data_type_w_struct_unknown_subfield(module_under_test): decimal.Decimal("{d38}.{d38}".format(d38="9" * 38)), decimal.Decimal("3.141592653589793238462643383279"), ], - marks=skip_if_no_bignumeric, ), ("BOOLEAN", [True, None, False, None]), ("BOOL", [False, None, True, None]), ( "TIMESTAMP", [ - datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=pytz.utc), + datetime.datetime(1, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc), None, - datetime.datetime(9999, 12, 31, 23, 59, 59, 999999, tzinfo=pytz.utc), - datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=pytz.utc), + datetime.datetime( + 9999, 12, 31, 23, 59, 59, 999999, tzinfo=datetime.timezone.utc + ), + datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc), ], ), ( @@ -587,6 +589,60 @@ def test_bq_to_arrow_array_w_special_floats(module_under_test): assert roundtrip[3] is None +@pytest.mark.skipif(geopandas is None, reason="Requires `geopandas`") +@pytest.mark.skipif(isinstance(pyarrow, mock.Mock), reason="Requires `pyarrow`") +def test_bq_to_arrow_array_w_geography_dtype(module_under_test): + from shapely import wkb, wkt + + bq_field = schema.SchemaField("field_name", "GEOGRAPHY") + + series = geopandas.GeoSeries([None, wkt.loads("point(0 0)")]) + array = module_under_test.bq_to_arrow_array(series, bq_field) + # The result is binary, because we use wkb format + assert array.type == pyarrow.binary() + assert array.to_pylist() == [None, wkb.dumps(series[1])] + + # All na: + series = geopandas.GeoSeries([None, None]) + array = module_under_test.bq_to_arrow_array(series, bq_field) + assert array.type == pyarrow.string() + assert array.to_pylist() == list(series) + + +@pytest.mark.skipif(geopandas is None, reason="Requires `geopandas`") +@pytest.mark.skipif(isinstance(pyarrow, mock.Mock), reason="Requires `pyarrow`") +def test_bq_to_arrow_array_w_geography_type_shapely_data(module_under_test): + from shapely import wkb, wkt + + bq_field = schema.SchemaField("field_name", "GEOGRAPHY") + + series = pandas.Series([None, wkt.loads("point(0 0)")]) + array = module_under_test.bq_to_arrow_array(series, bq_field) + # The result is binary, because we use wkb format + assert array.type == pyarrow.binary() + assert array.to_pylist() == [None, wkb.dumps(series[1])] + + # All na: + series = pandas.Series([None, None]) + array = module_under_test.bq_to_arrow_array(series, bq_field) + assert array.type == pyarrow.string() + assert array.to_pylist() == list(series) + + +@pytest.mark.skipif(geopandas is None, reason="Requires `geopandas`") +@pytest.mark.skipif(isinstance(pyarrow, mock.Mock), reason="Requires `pyarrow`") +def test_bq_to_arrow_array_w_geography_type_wkb_data(module_under_test): + from shapely import wkb, wkt + + bq_field = schema.SchemaField("field_name", "GEOGRAPHY") + + series = pandas.Series([None, wkb.dumps(wkt.loads("point(0 0)"))]) + array = module_under_test.bq_to_arrow_array(series, bq_field) + # The result is binary, because we use wkb format + assert array.type == pyarrow.binary() + assert array.to_pylist() == list(series) + + @pytest.mark.skipif(isinstance(pyarrow, mock.Mock), reason="Requires `pyarrow`") def test_bq_to_arrow_schema_w_unknown_type(module_under_test): fields = ( @@ -734,6 +790,37 @@ def test_list_columns_and_indexes_with_named_index_same_as_column_name( assert columns_and_indexes == expected +@pytest.mark.skipif( + pandas is None or PANDAS_INSTALLED_VERSION < PANDAS_MINIUM_VERSION, + reason="Requires `pandas version >= 1.0.0` which introduces pandas.NA", +) +def test_dataframe_to_json_generator(module_under_test): + utcnow = datetime.datetime.utcnow() + df_data = collections.OrderedDict( + [ + ("a_series", [pandas.NA, 2, 3, 4]), + ("b_series", [0.1, float("NaN"), 0.3, 0.4]), + ("c_series", ["a", "b", pandas.NA, "d"]), + ("d_series", [utcnow, utcnow, utcnow, pandas.NaT]), + ("e_series", [True, False, True, None]), + ] + ) + dataframe = pandas.DataFrame( + df_data, index=pandas.Index([4, 5, 6, 7], name="a_index") + ) + + dataframe = dataframe.astype({"a_series": pandas.Int64Dtype()}) + + rows = module_under_test.dataframe_to_json_generator(dataframe) + expected = [ + {"b_series": 0.1, "c_series": "a", "d_series": utcnow, "e_series": True}, + {"a_series": 2, "c_series": "b", "d_series": utcnow, "e_series": False}, + {"a_series": 3, "b_series": 0.3, "d_series": utcnow, "e_series": True}, + {"a_series": 4, "b_series": 0.4, "c_series": "d"}, + ] + assert list(rows) == expected + + @pytest.mark.skipif(pandas is None, reason="Requires `pandas`") def test_list_columns_and_indexes_with_named_index(module_under_test): df_data = collections.OrderedDict( @@ -895,6 +982,7 @@ def test_dataframe_to_arrow_with_required_fields(module_under_test): schema.SchemaField("field05", "FLOAT", mode="REQUIRED"), schema.SchemaField("field06", "FLOAT64", mode="REQUIRED"), schema.SchemaField("field07", "NUMERIC", mode="REQUIRED"), + schema.SchemaField("field08", "BIGNUMERIC", mode="REQUIRED"), schema.SchemaField("field09", "BOOLEAN", mode="REQUIRED"), schema.SchemaField("field10", "BOOL", mode="REQUIRED"), schema.SchemaField("field11", "TIMESTAMP", mode="REQUIRED"), @@ -903,8 +991,6 @@ def test_dataframe_to_arrow_with_required_fields(module_under_test): schema.SchemaField("field14", "DATETIME", mode="REQUIRED"), schema.SchemaField("field15", "GEOGRAPHY", mode="REQUIRED"), ) - if _BIGNUMERIC_SUPPORT: - bq_schema += (schema.SchemaField("field08", "BIGNUMERIC", mode="REQUIRED"),) data = { "field01": ["hello", "world"], @@ -914,11 +1000,15 @@ def test_dataframe_to_arrow_with_required_fields(module_under_test): "field05": [1.25, 9.75], "field06": [-1.75, -3.5], "field07": [decimal.Decimal("1.2345"), decimal.Decimal("6.7891")], + "field08": [ + decimal.Decimal("-{d38}.{d38}".format(d38="9" * 38)), + decimal.Decimal("{d38}.{d38}".format(d38="9" * 38)), + ], "field09": [True, False], "field10": [False, True], "field11": [ - datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=pytz.utc), - datetime.datetime(2012, 12, 21, 9, 7, 42, tzinfo=pytz.utc), + datetime.datetime(1970, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc), + datetime.datetime(2012, 12, 21, 9, 7, 42, tzinfo=datetime.timezone.utc), ], "field12": [datetime.date(9999, 12, 31), datetime.date(1970, 1, 1)], "field13": [datetime.time(23, 59, 59, 999999), datetime.time(12, 0, 0)], @@ -928,11 +1018,6 @@ def test_dataframe_to_arrow_with_required_fields(module_under_test): ], "field15": ["POINT(30 10)", "POLYGON ((30 10, 40 40, 20 40, 10 20, 30 10))"], } - if _BIGNUMERIC_SUPPORT: - data["field08"] = [ - decimal.Decimal("-{d38}.{d38}".format(d38="9" * 38)), - decimal.Decimal("{d38}.{d38}".format(d38="9" * 38)), - ] dataframe = pandas.DataFrame(data) arrow_table = module_under_test.dataframe_to_arrow(dataframe, bq_schema) @@ -1132,6 +1217,28 @@ def test_dataframe_to_bq_schema_pyarrow_fallback_fails(module_under_test): assert "struct_field" in str(expected_warnings[0]) +@pytest.mark.skipif(geopandas is None, reason="Requires `geopandas`") +def test_dataframe_to_bq_schema_geography(module_under_test): + from shapely import wkt + + df = geopandas.GeoDataFrame( + pandas.DataFrame( + dict( + name=["foo", "bar"], + geo1=[None, None], + geo2=[None, wkt.loads("Point(1 1)")], + ) + ), + geometry="geo1", + ) + bq_schema = module_under_test.dataframe_to_bq_schema(df, []) + assert bq_schema == ( + schema.SchemaField("name", "STRING"), + schema.SchemaField("geo1", "GEOGRAPHY"), + schema.SchemaField("geo2", "GEOGRAPHY"), + ) + + @pytest.mark.skipif(pandas is None, reason="Requires `pandas`") @pytest.mark.skipif(isinstance(pyarrow, mock.Mock), reason="Requires `pyarrow`") def test_augment_schema_type_detection_succeeds(module_under_test): @@ -1167,11 +1274,8 @@ def test_augment_schema_type_detection_succeeds(module_under_test): schema.SchemaField("bytes_field", field_type=None, mode="NULLABLE"), schema.SchemaField("string_field", field_type=None, mode="NULLABLE"), schema.SchemaField("numeric_field", field_type=None, mode="NULLABLE"), + schema.SchemaField("bignumeric_field", field_type=None, mode="NULLABLE"), ) - if _BIGNUMERIC_SUPPORT: - current_schema += ( - schema.SchemaField("bignumeric_field", field_type=None, mode="NULLABLE"), - ) with warnings.catch_warnings(record=True) as warned: augmented_schema = module_under_test.augment_schema(dataframe, current_schema) @@ -1193,13 +1297,10 @@ def test_augment_schema_type_detection_succeeds(module_under_test): schema.SchemaField("bytes_field", field_type="BYTES", mode="NULLABLE"), schema.SchemaField("string_field", field_type="STRING", mode="NULLABLE"), schema.SchemaField("numeric_field", field_type="NUMERIC", mode="NULLABLE"), + schema.SchemaField( + "bignumeric_field", field_type="BIGNUMERIC", mode="NULLABLE" + ), ) - if _BIGNUMERIC_SUPPORT: - expected_schema += ( - schema.SchemaField( - "bignumeric_field", field_type="BIGNUMERIC", mode="NULLABLE" - ), - ) by_name = operator.attrgetter("name") assert sorted(augmented_schema, key=by_name) == sorted(expected_schema, key=by_name) @@ -1271,6 +1372,72 @@ def test_dataframe_to_parquet_dict_sequence_schema(module_under_test): assert schema_arg == expected_schema_arg +@pytest.mark.skipif( + bigquery_storage is None, reason="Requires `google-cloud-bigquery-storage`" +) +def test__download_table_bqstorage_stream_includes_read_session( + monkeypatch, module_under_test +): + import google.cloud.bigquery_storage_v1.reader + import google.cloud.bigquery_storage_v1.types + + monkeypatch.setattr(_helpers.BQ_STORAGE_VERSIONS, "_installed_version", None) + monkeypatch.setattr(bigquery_storage, "__version__", "2.5.0") + bqstorage_client = mock.create_autospec( + bigquery_storage.BigQueryReadClient, instance=True + ) + reader = mock.create_autospec( + google.cloud.bigquery_storage_v1.reader.ReadRowsStream, instance=True + ) + bqstorage_client.read_rows.return_value = reader + session = google.cloud.bigquery_storage_v1.types.ReadSession() + + module_under_test._download_table_bqstorage_stream( + module_under_test._DownloadState(), + bqstorage_client, + session, + google.cloud.bigquery_storage_v1.types.ReadStream(name="test"), + queue.Queue(), + mock.Mock(), + ) + + reader.rows.assert_called_once_with(session) + + +@pytest.mark.skipif( + bigquery_storage is None + or not _helpers.BQ_STORAGE_VERSIONS.is_read_session_optional, + reason="Requires `google-cloud-bigquery-storage` >= 2.6.0", +) +def test__download_table_bqstorage_stream_omits_read_session( + monkeypatch, module_under_test +): + import google.cloud.bigquery_storage_v1.reader + import google.cloud.bigquery_storage_v1.types + + monkeypatch.setattr(_helpers.BQ_STORAGE_VERSIONS, "_installed_version", None) + monkeypatch.setattr(bigquery_storage, "__version__", "2.6.0") + bqstorage_client = mock.create_autospec( + bigquery_storage.BigQueryReadClient, instance=True + ) + reader = mock.create_autospec( + google.cloud.bigquery_storage_v1.reader.ReadRowsStream, instance=True + ) + bqstorage_client.read_rows.return_value = reader + session = google.cloud.bigquery_storage_v1.types.ReadSession() + + module_under_test._download_table_bqstorage_stream( + module_under_test._DownloadState(), + bqstorage_client, + session, + google.cloud.bigquery_storage_v1.types.ReadStream(name="test"), + queue.Queue(), + mock.Mock(), + ) + + reader.rows.assert_called_once_with() + + @pytest.mark.parametrize( "stream_count,maxsize_kwarg,expected_call_count,expected_maxsize", [ @@ -1468,3 +1635,22 @@ def test_download_dataframe_row_iterator_dict_sequence_schema(module_under_test) def test_table_data_listpage_to_dataframe_skips_stop_iteration(module_under_test): dataframe = module_under_test._row_iterator_page_to_dataframe([], [], {}) assert isinstance(dataframe, pandas.DataFrame) + + +@pytest.mark.skipif(isinstance(pyarrow, mock.Mock), reason="Requires `pyarrow`") +def test_bq_to_arrow_field_type_override(module_under_test): + # When loading pandas data, we may need to override the type + # decision based on data contents, because GEOGRAPHY data can be + # stored as either text or binary. + + assert ( + module_under_test.bq_to_arrow_field(schema.SchemaField("g", "GEOGRAPHY")).type + == pyarrow.string() + ) + + assert ( + module_under_test.bq_to_arrow_field( + schema.SchemaField("g", "GEOGRAPHY"), pyarrow.binary(), + ).type + == pyarrow.binary() + ) diff --git a/tests/unit/test_client.py b/tests/unit/test_client.py index 8f535145b..e9204f1de 100644 --- a/tests/unit/test_client.py +++ b/tests/unit/test_client.py @@ -27,9 +27,9 @@ import warnings import mock +import packaging import requests import pytest -import pytz import pkg_resources try: @@ -56,6 +56,7 @@ import google.cloud._helpers from google.cloud import bigquery_v2 from google.cloud.bigquery.dataset import DatasetReference +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT try: from google.cloud import bigquery_storage @@ -367,7 +368,7 @@ def test__get_query_results_miss_w_client_location(self): method="GET", path="/projects/PROJECT/queries/nothere", query_params={"maxResults": 0, "location": self.LOCATION}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test__get_query_results_hit(self): @@ -428,7 +429,9 @@ def test_get_service_account_email_w_alternate_project(self): service_account_email = client.get_service_account_email(project=project) final_attributes.assert_called_once_with({"path": path}, client, None) - conn.api_request.assert_called_once_with(method="GET", path=path, timeout=None) + conn.api_request.assert_called_once_with( + method="GET", path=path, timeout=DEFAULT_TIMEOUT + ) self.assertEqual(service_account_email, email) def test_get_service_account_email_w_custom_retry(self): @@ -471,221 +474,6 @@ def test_get_service_account_email_w_custom_retry(self): ], ) - def test_list_projects_defaults(self): - from google.cloud.bigquery.client import Project - - PROJECT_1 = "PROJECT_ONE" - PROJECT_2 = "PROJECT_TWO" - TOKEN = "TOKEN" - DATA = { - "nextPageToken": TOKEN, - "projects": [ - { - "kind": "bigquery#project", - "id": PROJECT_1, - "numericId": 1, - "projectReference": {"projectId": PROJECT_1}, - "friendlyName": "One", - }, - { - "kind": "bigquery#project", - "id": PROJECT_2, - "numericId": 2, - "projectReference": {"projectId": PROJECT_2}, - "friendlyName": "Two", - }, - ], - } - creds = _make_credentials() - client = self._make_one(PROJECT_1, creds) - conn = client._connection = make_connection(DATA) - iterator = client.list_projects() - - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/projects"}, client, None) - projects = list(page) - token = iterator.next_page_token - - self.assertEqual(len(projects), len(DATA["projects"])) - for found, expected in zip(projects, DATA["projects"]): - self.assertIsInstance(found, Project) - self.assertEqual(found.project_id, expected["id"]) - self.assertEqual(found.numeric_id, expected["numericId"]) - self.assertEqual(found.friendly_name, expected["friendlyName"]) - self.assertEqual(token, TOKEN) - - conn.api_request.assert_called_once_with( - method="GET", path="/projects", query_params={}, timeout=None - ) - - def test_list_projects_w_timeout(self): - PROJECT_1 = "PROJECT_ONE" - TOKEN = "TOKEN" - DATA = { - "nextPageToken": TOKEN, - "projects": [], - } - creds = _make_credentials() - client = self._make_one(PROJECT_1, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_projects(timeout=7.5) - - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/projects"}, client, None) - - conn.api_request.assert_called_once_with( - method="GET", path="/projects", query_params={}, timeout=7.5 - ) - - def test_list_projects_explicit_response_missing_projects_key(self): - TOKEN = "TOKEN" - DATA = {} - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_projects(max_results=3, page_token=TOKEN) - - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/projects"}, client, None) - projects = list(page) - token = iterator.next_page_token - - self.assertEqual(len(projects), 0) - self.assertIsNone(token) - - conn.api_request.assert_called_once_with( - method="GET", - path="/projects", - query_params={"maxResults": 3, "pageToken": TOKEN}, - timeout=None, - ) - - def test_list_datasets_defaults(self): - from google.cloud.bigquery.dataset import DatasetListItem - - DATASET_1 = "dataset_one" - DATASET_2 = "dataset_two" - PATH = "projects/%s/datasets" % self.PROJECT - TOKEN = "TOKEN" - DATA = { - "nextPageToken": TOKEN, - "datasets": [ - { - "kind": "bigquery#dataset", - "id": "%s:%s" % (self.PROJECT, DATASET_1), - "datasetReference": { - "datasetId": DATASET_1, - "projectId": self.PROJECT, - }, - "friendlyName": None, - }, - { - "kind": "bigquery#dataset", - "id": "%s:%s" % (self.PROJECT, DATASET_2), - "datasetReference": { - "datasetId": DATASET_2, - "projectId": self.PROJECT, - }, - "friendlyName": "Two", - }, - ], - } - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_datasets() - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) - datasets = list(page) - token = iterator.next_page_token - - self.assertEqual(len(datasets), len(DATA["datasets"])) - for found, expected in zip(datasets, DATA["datasets"]): - self.assertIsInstance(found, DatasetListItem) - self.assertEqual(found.full_dataset_id, expected["id"]) - self.assertEqual(found.friendly_name, expected["friendlyName"]) - self.assertEqual(token, TOKEN) - - conn.api_request.assert_called_once_with( - method="GET", path="/%s" % PATH, query_params={}, timeout=None - ) - - def test_list_datasets_w_project_and_timeout(self): - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection({}) - - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - list(client.list_datasets(project="other-project", timeout=7.5)) - - final_attributes.assert_called_once_with( - {"path": "/projects/other-project/datasets"}, client, None - ) - - conn.api_request.assert_called_once_with( - method="GET", - path="/projects/other-project/datasets", - query_params={}, - timeout=7.5, - ) - - def test_list_datasets_explicit_response_missing_datasets_key(self): - PATH = "projects/%s/datasets" % self.PROJECT - TOKEN = "TOKEN" - FILTER = "FILTER" - DATA = {} - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_datasets( - include_all=True, filter=FILTER, max_results=3, page_token=TOKEN - ) - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) - datasets = list(page) - token = iterator.next_page_token - - self.assertEqual(len(datasets), 0) - self.assertIsNone(token) - - conn.api_request.assert_called_once_with( - method="GET", - path="/%s" % PATH, - query_params={ - "all": True, - "filter": FILTER, - "maxResults": 3, - "pageToken": TOKEN, - }, - timeout=None, - ) - def test_dataset_with_specified_project(self): from google.cloud.bigquery.dataset import DatasetReference @@ -822,7 +610,7 @@ def test_get_dataset(self): @unittest.skipIf( bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" ) - def test_create_bqstorage_client(self): + def test_ensure_bqstorage_client_creating_new_instance(self): mock_client = mock.create_autospec(bigquery_storage.BigQueryReadClient) mock_client_instance = object() mock_client.return_value = mock_client_instance @@ -832,12 +620,19 @@ def test_create_bqstorage_client(self): with mock.patch( "google.cloud.bigquery_storage.BigQueryReadClient", mock_client ): - bqstorage_client = client._create_bqstorage_client() + bqstorage_client = client._ensure_bqstorage_client( + client_options=mock.sentinel.client_options, + client_info=mock.sentinel.client_info, + ) self.assertIs(bqstorage_client, mock_client_instance) - mock_client.assert_called_once_with(credentials=creds) + mock_client.assert_called_once_with( + credentials=creds, + client_options=mock.sentinel.client_options, + client_info=mock.sentinel.client_info, + ) - def test_create_bqstorage_client_missing_dependency(self): + def test_ensure_bqstorage_client_missing_dependency(self): creds = _make_credentials() client = self._make_one(project=self.PROJECT, credentials=creds) @@ -850,7 +645,7 @@ def fail_bqstorage_import(name, globals, locals, fromlist, level): no_bqstorage = maybe_fail_import(predicate=fail_bqstorage_import) with no_bqstorage, warnings.catch_warnings(record=True) as warned: - bqstorage_client = client._create_bqstorage_client() + bqstorage_client = client._ensure_bqstorage_client() self.assertIsNone(bqstorage_client) matching_warnings = [ @@ -861,6 +656,65 @@ def fail_bqstorage_import(name, globals, locals, fromlist, level): ] assert matching_warnings, "Missing dependency warning not raised." + @unittest.skipIf( + bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" + ) + def test_ensure_bqstorage_client_obsolete_dependency(self): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + creds = _make_credentials() + client = self._make_one(project=self.PROJECT, credentials=creds) + + patcher = mock.patch( + "google.cloud.bigquery.client.BQ_STORAGE_VERSIONS.verify_version", + side_effect=LegacyBigQueryStorageError("BQ Storage too old"), + ) + with patcher, warnings.catch_warnings(record=True) as warned: + bqstorage_client = client._ensure_bqstorage_client() + + self.assertIsNone(bqstorage_client) + matching_warnings = [ + warning for warning in warned if "BQ Storage too old" in str(warning) + ] + assert matching_warnings, "Obsolete dependency warning not raised." + + @unittest.skipIf( + bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" + ) + def test_ensure_bqstorage_client_existing_client_check_passes(self): + creds = _make_credentials() + client = self._make_one(project=self.PROJECT, credentials=creds) + mock_storage_client = mock.sentinel.mock_storage_client + + bqstorage_client = client._ensure_bqstorage_client( + bqstorage_client=mock_storage_client + ) + + self.assertIs(bqstorage_client, mock_storage_client) + + @unittest.skipIf( + bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" + ) + def test_ensure_bqstorage_client_existing_client_check_fails(self): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + creds = _make_credentials() + client = self._make_one(project=self.PROJECT, credentials=creds) + mock_storage_client = mock.sentinel.mock_storage_client + + patcher = mock.patch( + "google.cloud.bigquery.client.BQ_STORAGE_VERSIONS.verify_version", + side_effect=LegacyBigQueryStorageError("BQ Storage too old"), + ) + with patcher, warnings.catch_warnings(record=True) as warned: + bqstorage_client = client._ensure_bqstorage_client(mock_storage_client) + + self.assertIsNone(bqstorage_client) + matching_warnings = [ + warning for warning in warned if "BQ Storage too old" in str(warning) + ] + assert matching_warnings, "Obsolete dependency warning not raised." + def test_create_routine_w_minimal_resource(self): from google.cloud.bigquery.routine import Routine from google.cloud.bigquery.routine import RoutineReference @@ -920,7 +774,7 @@ def test_create_routine_w_conflict(self): } } conn.api_request.assert_called_once_with( - method="POST", path=path, data=resource, timeout=None, + method="POST", path=path, data=resource, timeout=DEFAULT_TIMEOUT, ) @unittest.skipIf(opentelemetry is None, "Requires `opentelemetry`") @@ -956,7 +810,7 @@ def test_span_status_is_set(self): } } conn.api_request.assert_called_once_with( - method="POST", path=path, data=resource, timeout=None, + method="POST", path=path, data=resource, timeout=DEFAULT_TIMEOUT, ) def test_create_routine_w_conflict_exists_ok(self): @@ -992,11 +846,13 @@ def test_create_routine_w_conflict_exists_ok(self): self.assertEqual(actual_routine.routine_id, "minimal_routine") conn.api_request.assert_has_calls( [ - mock.call(method="POST", path=path, data=resource, timeout=None,), + mock.call( + method="POST", path=path, data=resource, timeout=DEFAULT_TIMEOUT, + ), mock.call( method="GET", path="/projects/test-routine-project/datasets/test_routines/routines/minimal_routine", - timeout=None, + timeout=DEFAULT_TIMEOUT, ), ] ) @@ -1072,7 +928,7 @@ def test_create_table_w_custom_property(self): "newAlphaProperty": "unreleased property", "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got._properties["newAlphaProperty"], "unreleased property") self.assertEqual(got.table_id, self.TABLE_ID) @@ -1113,7 +969,7 @@ def test_create_table_w_encryption_configuration(self): "labels": {}, "encryptionConfiguration": {"kmsKeyName": self.KMS_KEY_NAME}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got.table_id, self.TABLE_ID) @@ -1149,7 +1005,7 @@ def test_create_table_w_day_partition_and_expire(self): "timePartitioning": {"type": "DAY", "expirationMs": "100"}, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(table.time_partitioning.type_, "DAY") self.assertEqual(table.time_partitioning.expiration_ms, 100) @@ -1168,8 +1024,18 @@ def test_create_table_w_schema_and_query(self): { "schema": { "fields": [ - {"name": "full_name", "type": "STRING", "mode": "REQUIRED"}, - {"name": "age", "type": "INTEGER", "mode": "REQUIRED"}, + { + "name": "full_name", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, + { + "name": "age", + "type": "INTEGER", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, ] }, "view": {"query": query}, @@ -1203,14 +1069,24 @@ def test_create_table_w_schema_and_query(self): }, "schema": { "fields": [ - {"name": "full_name", "type": "STRING", "mode": "REQUIRED"}, - {"name": "age", "type": "INTEGER", "mode": "REQUIRED"}, + { + "name": "full_name", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, + { + "name": "age", + "type": "INTEGER", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, ] }, "view": {"query": query, "useLegacySql": False}, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got.table_id, self.TABLE_ID) self.assertEqual(got.project, self.PROJECT) @@ -1265,7 +1141,7 @@ def test_create_table_w_external(self): }, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got.table_id, self.TABLE_ID) self.assertEqual(got.project, self.PROJECT) @@ -1304,7 +1180,7 @@ def test_create_table_w_reference(self): }, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got.table_id, self.TABLE_ID) @@ -1338,7 +1214,7 @@ def test_create_table_w_fully_qualified_string(self): }, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got.table_id, self.TABLE_ID) @@ -1370,7 +1246,7 @@ def test_create_table_w_string(self): }, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(got.table_id, self.TABLE_ID) @@ -1405,7 +1281,7 @@ def test_create_table_alreadyexists_w_exists_ok_false(self): }, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_create_table_alreadyexists_w_exists_ok_true(self): @@ -1448,9 +1324,9 @@ def test_create_table_alreadyexists_w_exists_ok_true(self): }, "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ), - mock.call(method="GET", path=get_path, timeout=None), + mock.call(method="GET", path=get_path, timeout=DEFAULT_TIMEOUT), ] ) @@ -1523,7 +1399,7 @@ def test_get_model_w_string(self): final_attributes.assert_called_once_with({"path": "/%s" % path}, client, None) conn.api_request.assert_called_once_with( - method="GET", path="/%s" % path, timeout=None + method="GET", path="/%s" % path, timeout=DEFAULT_TIMEOUT ) self.assertEqual(got.model_id, self.MODEL_ID) @@ -1632,7 +1508,7 @@ def test_get_table_sets_user_agent(self): "User-Agent": expected_user_agent, }, data=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertIn("my-application/1.2.3", expected_user_agent) @@ -1975,7 +1851,7 @@ def test_update_dataset_w_custom_property(self): data={"newAlphaProperty": "unreleased property"}, path=path, headers=None, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(dataset.dataset_id, self.DS_ID) @@ -2149,12 +2025,14 @@ def test_update_table(self): "type": "STRING", "mode": "REQUIRED", "description": None, + "policyTags": {"names": []}, }, { "name": "age", "type": "INTEGER", "mode": "REQUIRED", "description": "New field description", + "policyTags": {"names": []}, }, ] }, @@ -2196,12 +2074,14 @@ def test_update_table(self): "type": "STRING", "mode": "REQUIRED", "description": None, + "policyTags": {"names": []}, }, { "name": "age", "type": "INTEGER", "mode": "REQUIRED", "description": "New field description", + "policyTags": {"names": []}, }, ] }, @@ -2261,7 +2141,7 @@ def test_update_table_w_custom_property(self): path="/%s" % path, data={"newAlphaProperty": "unreleased property"}, headers=None, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual( updated_table._properties["newAlphaProperty"], "unreleased property" @@ -2296,7 +2176,7 @@ def test_update_table_only_use_legacy_sql(self): path="/%s" % path, data={"view": {"useLegacySql": True}}, headers=None, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(updated_table.view_use_legacy_sql, table.view_use_legacy_sql) @@ -2322,14 +2202,21 @@ def test_update_table_w_query(self): "type": "STRING", "mode": "REQUIRED", "description": None, + "policyTags": {"names": []}, }, { "name": "age", "type": "INTEGER", "mode": "REQUIRED", "description": "this is a column", + "policyTags": {"names": []}, + }, + { + "name": "country", + "type": "STRING", + "mode": "NULLABLE", + "policyTags": {"names": []}, }, - {"name": "country", "type": "STRING", "mode": "NULLABLE"}, ] } schema = [ @@ -2387,7 +2274,7 @@ def test_update_table_w_query(self): "schema": schema_resource, }, headers=None, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_update_table_w_schema_None(self): @@ -2516,7 +2403,7 @@ def test_delete_job_metadata_not_found(self): method="DELETE", path="/projects/client-proj/jobs/my-job/delete", query_params={"location": "client-loc"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_delete_job_metadata_with_id(self): @@ -2530,7 +2417,7 @@ def test_delete_job_metadata_with_id(self): method="DELETE", path="/projects/param-proj/jobs/my-job/delete", query_params={"location": "param-loc"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_delete_job_metadata_with_resource(self): @@ -2555,7 +2442,7 @@ def test_delete_job_metadata_with_resource(self): method="DELETE", path="/projects/job-based-proj/jobs/query_job/delete", query_params={"location": "us-east1"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_delete_model(self): @@ -2610,7 +2497,9 @@ def test_delete_model_w_not_found_ok_false(self): with self.assertRaises(google.api_core.exceptions.NotFound): client.delete_model("{}.{}".format(self.DS_ID, self.MODEL_ID)) - conn.api_request.assert_called_with(method="DELETE", path=path, timeout=None) + conn.api_request.assert_called_with( + method="DELETE", path=path, timeout=DEFAULT_TIMEOUT + ) def test_delete_model_w_not_found_ok_true(self): path = "/projects/{}/datasets/{}/models/{}".format( @@ -2631,7 +2520,9 @@ def test_delete_model_w_not_found_ok_true(self): final_attributes.assert_called_once_with({"path": path}, client, None) - conn.api_request.assert_called_with(method="DELETE", path=path, timeout=None) + conn.api_request.assert_called_with( + method="DELETE", path=path, timeout=DEFAULT_TIMEOUT + ) def test_delete_routine(self): from google.cloud.bigquery.routine import Routine @@ -2685,7 +2576,7 @@ def test_delete_routine_w_not_found_ok_false(self): final_attributes.assert_called_once_with({"path": path}, client, None) conn.api_request.assert_called_with( - method="DELETE", path=path, timeout=None, + method="DELETE", path=path, timeout=DEFAULT_TIMEOUT, ) def test_delete_routine_w_not_found_ok_true(self): @@ -2707,7 +2598,7 @@ def test_delete_routine_w_not_found_ok_true(self): final_attributes.assert_called_once_with({"path": path}, client, None) conn.api_request.assert_called_with( - method="DELETE", path=path, timeout=None, + method="DELETE", path=path, timeout=DEFAULT_TIMEOUT, ) def test_delete_table(self): @@ -2771,7 +2662,9 @@ def test_delete_table_w_not_found_ok_false(self): final_attributes.assert_called_once_with({"path": path}, client, None) - conn.api_request.assert_called_with(method="DELETE", path=path, timeout=None) + conn.api_request.assert_called_with( + method="DELETE", path=path, timeout=DEFAULT_TIMEOUT + ) def test_delete_table_w_not_found_ok_true(self): path = "/projects/{}/datasets/{}/tables/{}".format( @@ -2793,7 +2686,9 @@ def test_delete_table_w_not_found_ok_true(self): final_attributes.assert_called_once_with({"path": path}, client, None) - conn.api_request.assert_called_with(method="DELETE", path=path, timeout=None) + conn.api_request.assert_called_with( + method="DELETE", path=path, timeout=DEFAULT_TIMEOUT + ) def _create_job_helper(self, job_config): from google.cloud.bigquery import _helpers @@ -2815,7 +2710,7 @@ def _create_job_helper(self, job_config): method="POST", path="/projects/%s/jobs" % self.PROJECT, data=RESOURCE, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_create_job_load_config(self): @@ -2964,7 +2859,7 @@ def test_create_job_query_config_w_rateLimitExceeded_error(self): method="POST", path="/projects/PROJECT/jobs", data=data_without_destination, - timeout=None, + timeout=DEFAULT_TIMEOUT, ), ) @@ -3004,7 +2899,7 @@ def test_get_job_miss_w_explict_project(self): method="GET", path="/projects/OTHER_PROJECT/jobs/NONESUCH", query_params={"projection": "full"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_get_job_miss_w_client_location(self): @@ -3022,7 +2917,7 @@ def test_get_job_miss_w_client_location(self): method="GET", path="/projects/client-proj/jobs/NONESUCH", query_params={"projection": "full", "location": "client-loc"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_get_job_hit_w_timeout(self): @@ -3091,7 +2986,7 @@ def test_cancel_job_miss_w_explict_project(self): method="POST", path="/projects/OTHER_PROJECT/jobs/NONESUCH/cancel", query_params={"projection": "full", "location": self.LOCATION}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_cancel_job_miss_w_client_location(self): @@ -3110,347 +3005,68 @@ def test_cancel_job_miss_w_client_location(self): method="POST", path="/projects/OTHER_PROJECT/jobs/NONESUCH/cancel", query_params={"projection": "full", "location": self.LOCATION}, - timeout=None, - ) - - def test_cancel_job_hit(self): - from google.cloud.bigquery.job import QueryJob - - JOB_ID = "query_job" - QUERY = "SELECT * from test_dataset:test_table" - QUERY_JOB_RESOURCE = { - "id": "{}:{}".format(self.PROJECT, JOB_ID), - "jobReference": { - "projectId": "job-based-proj", - "jobId": "query_job", - "location": "asia-northeast1", - }, - "state": "RUNNING", - "configuration": {"query": {"query": QUERY}}, - } - RESOURCE = {"job": QUERY_JOB_RESOURCE} - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(RESOURCE) - job_from_resource = QueryJob.from_api_repr(QUERY_JOB_RESOURCE, client) - - job = client.cancel_job(job_from_resource) - - self.assertIsInstance(job, QueryJob) - self.assertEqual(job.job_id, JOB_ID) - self.assertEqual(job.project, "job-based-proj") - self.assertEqual(job.location, "asia-northeast1") - self.assertEqual(job.query, QUERY) - - conn.api_request.assert_called_once_with( - method="POST", - path="/projects/job-based-proj/jobs/query_job/cancel", - query_params={"projection": "full", "location": "asia-northeast1"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) - def test_cancel_job_w_timeout(self): - JOB_ID = "query_job" - QUERY = "SELECT * from test_dataset:test_table" - QUERY_JOB_RESOURCE = { - "id": "{}:{}".format(self.PROJECT, JOB_ID), - "jobReference": {"projectId": self.PROJECT, "jobId": "query_job"}, - "state": "RUNNING", - "configuration": {"query": {"query": QUERY}}, - } - RESOURCE = {"job": QUERY_JOB_RESOURCE} - - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(RESOURCE) - - client.cancel_job(JOB_ID, timeout=7.5) - - conn.api_request.assert_called_once_with( - method="POST", - path="/projects/{}/jobs/query_job/cancel".format(self.PROJECT), - query_params={"projection": "full"}, - timeout=7.5, - ) - - def test_list_jobs_defaults(self): - from google.cloud.bigquery.job import CopyJob - from google.cloud.bigquery.job import CreateDisposition - from google.cloud.bigquery.job import ExtractJob - from google.cloud.bigquery.job import LoadJob - from google.cloud.bigquery.job import QueryJob - from google.cloud.bigquery.job import WriteDisposition - - SOURCE_TABLE = "source_table" - DESTINATION_TABLE = "destination_table" - QUERY_DESTINATION_TABLE = "query_destination_table" - SOURCE_URI = "gs://test_bucket/src_object*" - DESTINATION_URI = "gs://test_bucket/dst_object*" - JOB_TYPES = { - "load_job": LoadJob, - "copy_job": CopyJob, - "extract_job": ExtractJob, - "query_job": QueryJob, - } - PATH = "projects/%s/jobs" % self.PROJECT - TOKEN = "TOKEN" - QUERY = "SELECT * from test_dataset:test_table" - ASYNC_QUERY_DATA = { - "id": "%s:%s" % (self.PROJECT, "query_job"), - "jobReference": {"projectId": self.PROJECT, "jobId": "query_job"}, - "state": "DONE", - "configuration": { - "query": { - "query": QUERY, - "destinationTable": { - "projectId": self.PROJECT, - "datasetId": self.DS_ID, - "tableId": QUERY_DESTINATION_TABLE, - }, - "createDisposition": CreateDisposition.CREATE_IF_NEEDED, - "writeDisposition": WriteDisposition.WRITE_TRUNCATE, - } - }, - } - EXTRACT_DATA = { - "id": "%s:%s" % (self.PROJECT, "extract_job"), - "jobReference": {"projectId": self.PROJECT, "jobId": "extract_job"}, - "state": "DONE", - "configuration": { - "extract": { - "sourceTable": { - "projectId": self.PROJECT, - "datasetId": self.DS_ID, - "tableId": SOURCE_TABLE, - }, - "destinationUris": [DESTINATION_URI], - } - }, - } - COPY_DATA = { - "id": "%s:%s" % (self.PROJECT, "copy_job"), - "jobReference": {"projectId": self.PROJECT, "jobId": "copy_job"}, - "state": "DONE", - "configuration": { - "copy": { - "sourceTables": [ - { - "projectId": self.PROJECT, - "datasetId": self.DS_ID, - "tableId": SOURCE_TABLE, - } - ], - "destinationTable": { - "projectId": self.PROJECT, - "datasetId": self.DS_ID, - "tableId": DESTINATION_TABLE, - }, - } - }, - } - LOAD_DATA = { - "id": "%s:%s" % (self.PROJECT, "load_job"), - "jobReference": {"projectId": self.PROJECT, "jobId": "load_job"}, - "state": "DONE", - "configuration": { - "load": { - "destinationTable": { - "projectId": self.PROJECT, - "datasetId": self.DS_ID, - "tableId": SOURCE_TABLE, - }, - "sourceUris": [SOURCE_URI], - } - }, - } - DATA = { - "nextPageToken": TOKEN, - "jobs": [ASYNC_QUERY_DATA, EXTRACT_DATA, COPY_DATA, LOAD_DATA], - } - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_jobs() - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) - jobs = list(page) - token = iterator.next_page_token - - self.assertEqual(len(jobs), len(DATA["jobs"])) - for found, expected in zip(jobs, DATA["jobs"]): - name = expected["jobReference"]["jobId"] - self.assertIsInstance(found, JOB_TYPES[name]) - self.assertEqual(found.job_id, name) - self.assertEqual(token, TOKEN) - - conn.api_request.assert_called_once_with( - method="GET", - path="/%s" % PATH, - query_params={"projection": "full"}, - timeout=None, - ) - - def test_list_jobs_load_job_wo_sourceUris(self): - from google.cloud.bigquery.job import LoadJob - - SOURCE_TABLE = "source_table" - JOB_TYPES = {"load_job": LoadJob} - PATH = "projects/%s/jobs" % self.PROJECT - TOKEN = "TOKEN" - LOAD_DATA = { - "id": "%s:%s" % (self.PROJECT, "load_job"), - "jobReference": {"projectId": self.PROJECT, "jobId": "load_job"}, - "state": "DONE", - "configuration": { - "load": { - "destinationTable": { - "projectId": self.PROJECT, - "datasetId": self.DS_ID, - "tableId": SOURCE_TABLE, - } - } - }, - } - DATA = {"nextPageToken": TOKEN, "jobs": [LOAD_DATA]} - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_jobs() - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) - jobs = list(page) - token = iterator.next_page_token - - self.assertEqual(len(jobs), len(DATA["jobs"])) - for found, expected in zip(jobs, DATA["jobs"]): - name = expected["jobReference"]["jobId"] - self.assertIsInstance(found, JOB_TYPES[name]) - self.assertEqual(found.job_id, name) - self.assertEqual(token, TOKEN) - - conn.api_request.assert_called_once_with( - method="GET", - path="/%s" % PATH, - query_params={"projection": "full"}, - timeout=None, - ) - - def test_list_jobs_explicit_missing(self): - PATH = "projects/%s/jobs" % self.PROJECT - DATA = {} - TOKEN = "TOKEN" - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection(DATA) - - iterator = client.list_jobs( - max_results=1000, page_token=TOKEN, all_users=True, state_filter="done" - ) - with mock.patch( - "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" - ) as final_attributes: - page = next(iterator.pages) - - final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) - jobs = list(page) - token = iterator.next_page_token - - self.assertEqual(len(jobs), 0) - self.assertIsNone(token) - - conn.api_request.assert_called_once_with( - method="GET", - path="/%s" % PATH, - query_params={ - "projection": "full", - "maxResults": 1000, - "pageToken": TOKEN, - "allUsers": True, - "stateFilter": "done", - }, - timeout=None, - ) - - def test_list_jobs_w_project(self): - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection({}) - - list(client.list_jobs(project="other-project")) - - conn.api_request.assert_called_once_with( - method="GET", - path="/projects/other-project/jobs", - query_params={"projection": "full"}, - timeout=None, - ) - - def test_list_jobs_w_timeout(self): - creds = _make_credentials() - client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection({}) - - list(client.list_jobs(timeout=7.5)) - - conn.api_request.assert_called_once_with( - method="GET", - path="/projects/{}/jobs".format(self.PROJECT), - query_params={"projection": "full"}, - timeout=7.5, - ) + def test_cancel_job_hit(self): + from google.cloud.bigquery.job import QueryJob - def test_list_jobs_w_time_filter(self): + JOB_ID = "query_job" + QUERY = "SELECT * from test_dataset:test_table" + QUERY_JOB_RESOURCE = { + "id": "{}:{}".format(self.PROJECT, JOB_ID), + "jobReference": { + "projectId": "job-based-proj", + "jobId": "query_job", + "location": "asia-northeast1", + }, + "state": "RUNNING", + "configuration": {"query": {"query": QUERY}}, + } + RESOURCE = {"job": QUERY_JOB_RESOURCE} creds = _make_credentials() client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection({}) + conn = client._connection = make_connection(RESOURCE) + job_from_resource = QueryJob.from_api_repr(QUERY_JOB_RESOURCE, client) - # One millisecond after the unix epoch. - start_time = datetime.datetime(1970, 1, 1, 0, 0, 0, 1000) - # One millisecond after the the 2038 31-bit signed int rollover - end_time = datetime.datetime(2038, 1, 19, 3, 14, 7, 1000) - end_time_millis = (((2 ** 31) - 1) * 1000) + 1 + job = client.cancel_job(job_from_resource) - list(client.list_jobs(min_creation_time=start_time, max_creation_time=end_time)) + self.assertIsInstance(job, QueryJob) + self.assertEqual(job.job_id, JOB_ID) + self.assertEqual(job.project, "job-based-proj") + self.assertEqual(job.location, "asia-northeast1") + self.assertEqual(job.query, QUERY) conn.api_request.assert_called_once_with( - method="GET", - path="/projects/%s/jobs" % self.PROJECT, - query_params={ - "projection": "full", - "minCreationTime": "1", - "maxCreationTime": str(end_time_millis), - }, - timeout=None, + method="POST", + path="/projects/job-based-proj/jobs/query_job/cancel", + query_params={"projection": "full", "location": "asia-northeast1"}, + timeout=DEFAULT_TIMEOUT, ) - def test_list_jobs_w_parent_job_filter(self): - from google.cloud.bigquery import job + def test_cancel_job_w_timeout(self): + JOB_ID = "query_job" + QUERY = "SELECT * from test_dataset:test_table" + QUERY_JOB_RESOURCE = { + "id": "{}:{}".format(self.PROJECT, JOB_ID), + "jobReference": {"projectId": self.PROJECT, "jobId": "query_job"}, + "state": "RUNNING", + "configuration": {"query": {"query": QUERY}}, + } + RESOURCE = {"job": QUERY_JOB_RESOURCE} creds = _make_credentials() client = self._make_one(self.PROJECT, creds) - conn = client._connection = make_connection({}, {}) + conn = client._connection = make_connection(RESOURCE) - parent_job_args = ["parent-job-123", job._AsyncJob("parent-job-123", client)] + client.cancel_job(JOB_ID, timeout=7.5) - for parent_job in parent_job_args: - list(client.list_jobs(parent_job=parent_job)) - conn.api_request.assert_called_once_with( - method="GET", - path="/projects/%s/jobs" % self.PROJECT, - query_params={"projection": "full", "parentJobId": "parent-job-123"}, - timeout=None, - ) - conn.api_request.reset_mock() + conn.api_request.assert_called_once_with( + method="POST", + path="/projects/{}/jobs/query_job/cancel".format(self.PROJECT), + query_params={"projection": "full"}, + timeout=7.5, + ) def test_load_table_from_uri(self): from google.cloud.bigquery.job import LoadJob, LoadJobConfig @@ -3551,7 +3167,7 @@ def test_load_table_from_uri_w_explicit_project(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_load_table_from_uri_w_client_location(self): @@ -3595,7 +3211,7 @@ def test_load_table_from_uri_w_client_location(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_load_table_from_uri_w_invalid_job_config(self): @@ -3883,7 +3499,7 @@ def test_copy_table_w_multiple_sources(self): method="POST", path="/projects/%s/jobs" % self.PROJECT, data=expected_resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertIsInstance(job, CopyJob) self.assertIs(job._client, client) @@ -3945,7 +3561,7 @@ def test_copy_table_w_explicit_project(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_copy_table_w_client_location(self): @@ -3995,7 +3611,7 @@ def test_copy_table_w_client_location(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_copy_table_w_source_strings(self): @@ -4088,7 +3704,7 @@ def test_copy_table_w_valid_job_config(self): method="POST", path="/projects/%s/jobs" % self.PROJECT, data=RESOURCE, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertIsInstance(job._configuration, CopyJobConfig) @@ -4194,7 +3810,7 @@ def test_extract_table_w_explicit_project(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_extract_table_w_client_location(self): @@ -4238,7 +3854,7 @@ def test_extract_table_w_client_location(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_extract_table_generated_job_id(self): @@ -4281,7 +3897,7 @@ def test_extract_table_generated_job_id(self): self.assertEqual(req["method"], "POST") self.assertEqual(req["path"], "/projects/PROJECT/jobs") self.assertIsInstance(req["data"]["jobReference"]["jobId"], str) - self.assertIsNone(req["timeout"]) + self.assertEqual(req["timeout"], DEFAULT_TIMEOUT) # Check the job resource. self.assertIsInstance(job, ExtractJob) @@ -4326,7 +3942,7 @@ def test_extract_table_w_destination_uris(self): _, req = conn.api_request.call_args self.assertEqual(req["method"], "POST") self.assertEqual(req["path"], "/projects/PROJECT/jobs") - self.assertIsNone(req["timeout"]) + self.assertEqual(req["timeout"], DEFAULT_TIMEOUT) # Check the job resource. self.assertIsInstance(job, ExtractJob) @@ -4496,7 +4112,7 @@ def test_query_defaults(self): _, req = conn.api_request.call_args self.assertEqual(req["method"], "POST") self.assertEqual(req["path"], "/projects/PROJECT/jobs") - self.assertIsNone(req["timeout"]) + self.assertEqual(req["timeout"], DEFAULT_TIMEOUT) sent = req["data"] self.assertIsInstance(sent["jobReference"]["jobId"], str) sent_config = sent["configuration"]["query"] @@ -4549,7 +4165,7 @@ def test_query_w_explicit_project(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_query_w_explicit_job_config(self): @@ -4605,7 +4221,10 @@ def test_query_w_explicit_job_config(self): # Check that query actually starts the job. conn.api_request.assert_called_once_with( - method="POST", path="/projects/PROJECT/jobs", data=resource, timeout=None + method="POST", + path="/projects/PROJECT/jobs", + data=resource, + timeout=DEFAULT_TIMEOUT, ) # the original config object should not have been modified @@ -4649,7 +4268,10 @@ def test_query_preserving_explicit_job_config(self): # Check that query actually starts the job. conn.api_request.assert_called_once_with( - method="POST", path="/projects/PROJECT/jobs", data=resource, timeout=None + method="POST", + path="/projects/PROJECT/jobs", + data=resource, + timeout=DEFAULT_TIMEOUT, ) # the original config object should not have been modified @@ -4701,7 +4323,10 @@ def test_query_preserving_explicit_default_job_config(self): # Check that query actually starts the job. conn.api_request.assert_called_once_with( - method="POST", path="/projects/PROJECT/jobs", data=resource, timeout=None + method="POST", + path="/projects/PROJECT/jobs", + data=resource, + timeout=DEFAULT_TIMEOUT, ) # the original default config object should not have been modified @@ -4786,7 +4411,10 @@ def test_query_w_explicit_job_config_override(self): # Check that query actually starts the job. conn.api_request.assert_called_once_with( - method="POST", path="/projects/PROJECT/jobs", data=resource, timeout=None + method="POST", + path="/projects/PROJECT/jobs", + data=resource, + timeout=DEFAULT_TIMEOUT, ) def test_query_w_client_default_config_no_incoming(self): @@ -4827,7 +4455,10 @@ def test_query_w_client_default_config_no_incoming(self): # Check that query actually starts the job. conn.api_request.assert_called_once_with( - method="POST", path="/projects/PROJECT/jobs", data=resource, timeout=None + method="POST", + path="/projects/PROJECT/jobs", + data=resource, + timeout=DEFAULT_TIMEOUT, ) def test_query_w_invalid_default_job_config(self): @@ -4872,7 +4503,7 @@ def test_query_w_client_location(self): method="POST", path="/projects/other-project/jobs", data=resource, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_query_detect_location(self): @@ -4943,7 +4574,7 @@ def test_query_w_udf_resources(self): _, req = conn.api_request.call_args self.assertEqual(req["method"], "POST") self.assertEqual(req["path"], "/projects/PROJECT/jobs") - self.assertIsNone(req["timeout"]) + self.assertEqual(req["timeout"], DEFAULT_TIMEOUT) sent = req["data"] self.assertIsInstance(sent["jobReference"]["jobId"], str) sent_config = sent["configuration"]["query"] @@ -4999,7 +4630,7 @@ def test_query_w_query_parameters(self): _, req = conn.api_request.call_args self.assertEqual(req["method"], "POST") self.assertEqual(req["path"], "/projects/PROJECT/jobs") - self.assertIsNone(req["timeout"]) + self.assertEqual(req["timeout"], DEFAULT_TIMEOUT) sent = req["data"] self.assertEqual(sent["jobReference"]["jobId"], JOB) sent_config = sent["configuration"]["query"] @@ -5014,6 +4645,81 @@ def test_query_w_query_parameters(self): }, ) + def test_query_job_rpc_fail_w_random_error(self): + from google.api_core.exceptions import Unknown + from google.cloud.bigquery.job import QueryJob + + creds = _make_credentials() + http = object() + client = self._make_one(project=self.PROJECT, credentials=creds, _http=http) + + job_create_error = Unknown("Not sure what went wrong.") + job_begin_patcher = mock.patch.object( + QueryJob, "_begin", side_effect=job_create_error + ) + with job_begin_patcher: + with pytest.raises(Unknown, match="Not sure what went wrong."): + client.query("SELECT 1;", job_id="123") + + def test_query_job_rpc_fail_w_conflict_job_id_given(self): + from google.api_core.exceptions import Conflict + from google.cloud.bigquery.job import QueryJob + + creds = _make_credentials() + http = object() + client = self._make_one(project=self.PROJECT, credentials=creds, _http=http) + + job_create_error = Conflict("Job already exists.") + job_begin_patcher = mock.patch.object( + QueryJob, "_begin", side_effect=job_create_error + ) + with job_begin_patcher: + with pytest.raises(Conflict, match="Job already exists."): + client.query("SELECT 1;", job_id="123") + + def test_query_job_rpc_fail_w_conflict_random_id_job_fetch_fails(self): + from google.api_core.exceptions import Conflict + from google.api_core.exceptions import DataLoss + from google.cloud.bigquery.job import QueryJob + + creds = _make_credentials() + http = object() + client = self._make_one(project=self.PROJECT, credentials=creds, _http=http) + + job_create_error = Conflict("Job already exists.") + job_begin_patcher = mock.patch.object( + QueryJob, "_begin", side_effect=job_create_error + ) + get_job_patcher = mock.patch.object( + client, "get_job", side_effect=DataLoss("we lost yor job, sorry") + ) + + with job_begin_patcher, get_job_patcher: + # If get job request fails, the original exception should be raised. + with pytest.raises(Conflict, match="Job already exists."): + client.query("SELECT 1;", job_id=None) + + def test_query_job_rpc_fail_w_conflict_random_id_job_fetch_succeeds(self): + from google.api_core.exceptions import Conflict + from google.cloud.bigquery.job import QueryJob + + creds = _make_credentials() + http = object() + client = self._make_one(project=self.PROJECT, credentials=creds, _http=http) + + job_create_error = Conflict("Job already exists.") + job_begin_patcher = mock.patch.object( + QueryJob, "_begin", side_effect=job_create_error + ) + get_job_patcher = mock.patch.object( + client, "get_job", return_value=mock.sentinel.query_job + ) + + with job_begin_patcher, get_job_patcher: + result = client.query("SELECT 1;", job_id=None) + + assert result is mock.sentinel.query_job + def test_insert_rows_w_timeout(self): from google.cloud.bigquery.schema import SchemaField from google.cloud.bigquery.table import Table @@ -5116,7 +4822,7 @@ def _row_data(row): self.assertEqual(req["method"], "POST") self.assertEqual(req["path"], "/%s" % PATH) self.assertEqual(req["data"], SENT) - self.assertIsNone(req["timeout"]) + self.assertEqual(req["timeout"], DEFAULT_TIMEOUT) def test_insert_rows_w_list_of_dictionaries(self): import datetime @@ -5184,7 +4890,7 @@ def _row_data(row): self.assertEqual(len(errors), 0) conn.api_request.assert_called_once_with( - method="POST", path="/%s" % PATH, data=SENT, timeout=None + method="POST", path="/%s" % PATH, data=SENT, timeout=DEFAULT_TIMEOUT ) def test_insert_rows_w_list_of_Rows(self): @@ -5229,7 +4935,7 @@ def _row_data(row): self.assertEqual(len(errors), 0) conn.api_request.assert_called_once_with( - method="POST", path="/%s" % PATH, data=SENT, timeout=None + method="POST", path="/%s" % PATH, data=SENT, timeout=DEFAULT_TIMEOUT ) def test_insert_rows_w_skip_invalid_and_ignore_unknown(self): @@ -5306,7 +5012,7 @@ def _row_data(row): errors[0]["errors"][0], RESPONSE["insertErrors"][0]["errors"][0] ) conn.api_request.assert_called_once_with( - method="POST", path="/%s" % PATH, data=SENT, timeout=None + method="POST", path="/%s" % PATH, data=SENT, timeout=DEFAULT_TIMEOUT ) def test_insert_rows_w_repeated_fields(self): @@ -5339,16 +5045,24 @@ def test_insert_rows_w_repeated_fields(self): ( 12, [ - datetime.datetime(2018, 12, 1, 12, 0, 0, tzinfo=pytz.utc), - datetime.datetime(2018, 12, 1, 13, 0, 0, tzinfo=pytz.utc), + datetime.datetime( + 2018, 12, 1, 12, 0, 0, tzinfo=datetime.timezone.utc + ), + datetime.datetime( + 2018, 12, 1, 13, 0, 0, tzinfo=datetime.timezone.utc + ), ], [1.25, 2.5], ), { "score": 13, "times": [ - datetime.datetime(2018, 12, 2, 12, 0, 0, tzinfo=pytz.utc), - datetime.datetime(2018, 12, 2, 13, 0, 0, tzinfo=pytz.utc), + datetime.datetime( + 2018, 12, 2, 12, 0, 0, tzinfo=datetime.timezone.utc + ), + datetime.datetime( + 2018, 12, 2, 13, 0, 0, tzinfo=datetime.timezone.utc + ), ], "distances": [-1.25, -2.5], }, @@ -5399,7 +5113,7 @@ def test_insert_rows_w_repeated_fields(self): self.assertEqual(len(errors), 0) conn.api_request.assert_called_once_with( - method="POST", path="/%s" % PATH, data=SENT, timeout=None, + method="POST", path="/%s" % PATH, data=SENT, timeout=DEFAULT_TIMEOUT, ) def test_insert_rows_w_record_schema(self): @@ -5465,7 +5179,7 @@ def test_insert_rows_w_record_schema(self): self.assertEqual(len(errors), 0) conn.api_request.assert_called_once_with( - method="POST", path="/%s" % PATH, data=SENT, timeout=None + method="POST", path="/%s" % PATH, data=SENT, timeout=DEFAULT_TIMEOUT ) def test_insert_rows_w_explicit_none_insert_ids(self): @@ -5499,7 +5213,7 @@ def _row_data(row): self.assertEqual(len(errors), 0) conn.api_request.assert_called_once_with( - method="POST", path="/{}".format(PATH), data=SENT, timeout=None, + method="POST", path="/{}".format(PATH), data=SENT, timeout=DEFAULT_TIMEOUT, ) def test_insert_rows_errors(self): @@ -5583,7 +5297,7 @@ def test_insert_rows_w_numeric(self): project, ds_id, table_id ), data=sent, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @unittest.skipIf(pandas is None, "Requires `pandas`") @@ -5775,7 +5489,10 @@ def test_insert_rows_from_dataframe_many_columns(self): ] } expected_call = mock.call( - method="POST", path=API_PATH, data=EXPECTED_SENT_DATA, timeout=None + method="POST", + path=API_PATH, + data=EXPECTED_SENT_DATA, + timeout=DEFAULT_TIMEOUT, ) actual_calls = conn.api_request.call_args_list @@ -5828,10 +5545,13 @@ def test_insert_rows_from_dataframe_w_explicit_none_insert_ids(self): actual_calls = conn.api_request.call_args_list assert len(actual_calls) == 1 assert actual_calls[0] == mock.call( - method="POST", path=API_PATH, data=EXPECTED_SENT_DATA, timeout=None + method="POST", + path=API_PATH, + data=EXPECTED_SENT_DATA, + timeout=DEFAULT_TIMEOUT, ) - def test_insert_rows_json(self): + def test_insert_rows_json_default_behavior(self): from google.cloud.bigquery.dataset import DatasetReference from google.cloud.bigquery.schema import SchemaField from google.cloud.bigquery.table import Table @@ -5878,8 +5598,10 @@ def test_insert_rows_json(self): method="POST", path="/%s" % PATH, data=SENT, timeout=7.5, ) - def test_insert_rows_json_with_string_id(self): - rows = [{"col1": "val1"}] + def test_insert_rows_json_w_explicitly_requested_autogenerated_insert_ids(self): + from google.cloud.bigquery import AutoRowIDs + + rows = [{"col1": "val1"}, {"col2": "val2"}] creds = _make_credentials() http = object() client = self._make_one( @@ -5887,19 +5609,115 @@ def test_insert_rows_json_with_string_id(self): ) conn = client._connection = make_connection({}) - with mock.patch("uuid.uuid4", side_effect=map(str, range(len(rows)))): - errors = client.insert_rows_json("proj.dset.tbl", rows) + uuid_patcher = mock.patch("uuid.uuid4", side_effect=map(str, range(len(rows)))) + with uuid_patcher: + errors = client.insert_rows_json( + "proj.dset.tbl", rows, row_ids=AutoRowIDs.GENERATE_UUID + ) self.assertEqual(len(errors), 0) - expected = { - "rows": [{"json": row, "insertId": str(i)} for i, row in enumerate(rows)] + + # Check row data sent to the backend. + expected_row_data = { + "rows": [ + {"json": {"col1": "val1"}, "insertId": "0"}, + {"json": {"col2": "val2"}, "insertId": "1"}, + ] } conn.api_request.assert_called_once_with( method="POST", path="/projects/proj/datasets/dset/tables/tbl/insertAll", - data=expected, - timeout=None, + data=expected_row_data, + timeout=DEFAULT_TIMEOUT, + ) + + def test_insert_rows_json_w_explicitly_disabled_insert_ids(self): + from google.cloud.bigquery import AutoRowIDs + + rows = [{"col1": "val1"}, {"col2": "val2"}] + creds = _make_credentials() + http = object() + client = self._make_one( + project="default-project", credentials=creds, _http=http + ) + conn = client._connection = make_connection({}) + + errors = client.insert_rows_json( + "proj.dset.tbl", rows, row_ids=AutoRowIDs.DISABLED, + ) + + self.assertEqual(len(errors), 0) + + expected_row_data = { + "rows": [ + {"json": {"col1": "val1"}, "insertId": None}, + {"json": {"col2": "val2"}, "insertId": None}, + ] + } + conn.api_request.assert_called_once_with( + method="POST", + path="/projects/proj/datasets/dset/tables/tbl/insertAll", + data=expected_row_data, + timeout=DEFAULT_TIMEOUT, + ) + + def test_insert_rows_json_with_iterator_row_ids(self): + rows = [{"col1": "val1"}, {"col2": "val2"}, {"col3": "val3"}] + creds = _make_credentials() + http = object() + client = self._make_one( + project="default-project", credentials=creds, _http=http + ) + conn = client._connection = make_connection({}) + + row_ids_iter = map(str, itertools.count(42)) + errors = client.insert_rows_json("proj.dset.tbl", rows, row_ids=row_ids_iter) + + self.assertEqual(len(errors), 0) + expected_row_data = { + "rows": [ + {"json": {"col1": "val1"}, "insertId": "42"}, + {"json": {"col2": "val2"}, "insertId": "43"}, + {"json": {"col3": "val3"}, "insertId": "44"}, + ] + } + conn.api_request.assert_called_once_with( + method="POST", + path="/projects/proj/datasets/dset/tables/tbl/insertAll", + data=expected_row_data, + timeout=DEFAULT_TIMEOUT, + ) + + def test_insert_rows_json_with_non_iterable_row_ids(self): + rows = [{"col1": "val1"}] + creds = _make_credentials() + http = object() + client = self._make_one( + project="default-project", credentials=creds, _http=http + ) + client._connection = make_connection({}) + + with self.assertRaises(TypeError) as exc: + client.insert_rows_json("proj.dset.tbl", rows, row_ids=object()) + + err_msg = str(exc.exception) + self.assertIn("row_ids", err_msg) + self.assertIn("iterable", err_msg) + + def test_insert_rows_json_with_too_few_row_ids(self): + rows = [{"col1": "val1"}, {"col2": "val2"}, {"col3": "val3"}] + creds = _make_credentials() + http = object() + client = self._make_one( + project="default-project", credentials=creds, _http=http ) + client._connection = make_connection({}) + + insert_ids = ["10", "20"] + + error_msg_pattern = "row_ids did not generate enough IDs.*index 2" + with self.assertRaisesRegex(ValueError, error_msg_pattern): + client.insert_rows_json("proj.dset.tbl", rows, row_ids=insert_ids) def test_insert_rows_json_w_explicit_none_insert_ids(self): rows = [{"col1": "val1"}, {"col2": "val2"}] @@ -5920,7 +5738,46 @@ def test_insert_rows_json_w_explicit_none_insert_ids(self): method="POST", path="/projects/proj/datasets/dset/tables/tbl/insertAll", data=expected, - timeout=None, + timeout=DEFAULT_TIMEOUT, + ) + + def test_insert_rows_json_w_none_insert_ids_sequence(self): + rows = [{"col1": "val1"}, {"col2": "val2"}] + creds = _make_credentials() + http = object() + client = self._make_one( + project="default-project", credentials=creds, _http=http + ) + conn = client._connection = make_connection({}) + + uuid_patcher = mock.patch("uuid.uuid4", side_effect=map(str, range(len(rows)))) + with warnings.catch_warnings(record=True) as warned, uuid_patcher: + errors = client.insert_rows_json("proj.dset.tbl", rows, row_ids=None) + + self.assertEqual(len(errors), 0) + + # Passing row_ids=None should have resulted in a deprecation warning. + matches = [ + warning + for warning in warned + if issubclass(warning.category, DeprecationWarning) + and "row_ids" in str(warning) + and "AutoRowIDs.GENERATE_UUID" in str(warning) + ] + assert matches, "The expected deprecation warning was not raised." + + # Check row data sent to the backend. + expected_row_data = { + "rows": [ + {"json": {"col1": "val1"}, "insertId": "0"}, + {"json": {"col2": "val2"}, "insertId": "1"}, + ] + } + conn.api_request.assert_called_once_with( + method="POST", + path="/projects/proj/datasets/dset/tables/tbl/insertAll", + data=expected_row_data, + timeout=DEFAULT_TIMEOUT, ) def test_insert_rows_w_wrong_arg(self): @@ -6115,7 +5972,7 @@ def test_list_rows_w_start_index_w_page_size(self): "maxResults": 2, "formatOptions.useInt64Timestamp": True, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ), mock.call( method="GET", @@ -6125,7 +5982,7 @@ def test_list_rows_w_start_index_w_page_size(self): "maxResults": 2, "formatOptions.useInt64Timestamp": True, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ), ] ) @@ -6276,7 +6133,7 @@ def test_list_rows_repeated_fields(self): "selectedFields": "color,struct", "formatOptions.useInt64Timestamp": True, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_list_rows_w_record_schema(self): @@ -6346,7 +6203,7 @@ def test_list_rows_w_record_schema(self): method="GET", path="/%s" % PATH, query_params={"formatOptions.useInt64Timestamp": True}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_list_rows_with_missing_schema(self): @@ -6401,7 +6258,7 @@ def test_list_rows_with_missing_schema(self): row_iter = client.list_rows(table) conn.api_request.assert_called_once_with( - method="GET", path=table_path, timeout=None + method="GET", path=table_path, timeout=DEFAULT_TIMEOUT ) conn.api_request.reset_mock() self.assertEqual(row_iter.total_rows, 2, msg=repr(table)) @@ -6411,7 +6268,7 @@ def test_list_rows_with_missing_schema(self): method="GET", path=tabledata_path, query_params={"formatOptions.useInt64Timestamp": True}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) self.assertEqual(row_iter.total_rows, 3, msg=repr(table)) self.assertEqual(rows[0].name, "Phred Phlyntstone", msg=repr(table)) @@ -6584,7 +6441,7 @@ def test_load_table_from_file_resumable(self): file_obj, self.EXPECTED_CONFIGURATION, _DEFAULT_NUM_RETRIES, - None, + DEFAULT_TIMEOUT, project=self.EXPECTED_CONFIGURATION["jobReference"]["projectId"], ) @@ -6617,7 +6474,7 @@ def test_load_table_from_file_w_explicit_project(self): file_obj, expected_resource, _DEFAULT_NUM_RETRIES, - None, + DEFAULT_TIMEOUT, project="other-project", ) @@ -6651,7 +6508,7 @@ def test_load_table_from_file_w_client_location(self): file_obj, expected_resource, _DEFAULT_NUM_RETRIES, - None, + DEFAULT_TIMEOUT, project="other-project", ) @@ -6713,7 +6570,7 @@ def test_load_table_from_file_resumable_metadata(self): file_obj, expected_config, _DEFAULT_NUM_RETRIES, - None, + DEFAULT_TIMEOUT, project=self.EXPECTED_CONFIGURATION["jobReference"]["projectId"], ) @@ -6742,7 +6599,7 @@ def test_load_table_from_file_multipart(self): self.EXPECTED_CONFIGURATION, file_obj_size, _DEFAULT_NUM_RETRIES, - None, + DEFAULT_TIMEOUT, project=self.PROJECT, ) @@ -6767,7 +6624,7 @@ def test_load_table_from_file_with_retries(self): file_obj, self.EXPECTED_CONFIGURATION, num_retries, - None, + DEFAULT_TIMEOUT, project=self.EXPECTED_CONFIGURATION["jobReference"]["projectId"], ) @@ -6804,7 +6661,7 @@ def test_load_table_from_file_with_readable_gzip(self): gzip_file, self.EXPECTED_CONFIGURATION, _DEFAULT_NUM_RETRIES, - None, + DEFAULT_TIMEOUT, project=self.EXPECTED_CONFIGURATION["jobReference"]["projectId"], ) @@ -6927,7 +6784,7 @@ def test_load_table_from_dataframe(self): location=None, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_file = load_table_from_file.mock_calls[0][1][1] @@ -6944,10 +6801,10 @@ def test_load_table_from_dataframe(self): assert field["type"] == table_field.field_type assert field["mode"] == table_field.mode assert len(field.get("fields", [])) == len(table_field.fields) + assert field["policyTags"]["names"] == [] # Omit unnecessary fields when they come from getting the table # (not passed in via job_config) assert "description" not in field - assert "policyTags" not in field @unittest.skipIf(pandas is None, "Requires `pandas`") @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") @@ -6985,7 +6842,7 @@ def test_load_table_from_dataframe_w_client_location(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_file = load_table_from_file.mock_calls[0][1][1] @@ -7039,7 +6896,7 @@ def test_load_table_from_dataframe_w_custom_job_config_wihtout_source_format(sel location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7095,7 +6952,7 @@ def test_load_table_from_dataframe_w_custom_job_config_w_source_format(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7158,7 +7015,7 @@ def test_load_table_from_dataframe_w_automatic_schema(self): datetime.datetime(2012, 3, 14, 15, 16), ], dtype="datetime64[ns]", - ).dt.tz_localize(pytz.utc), + ).dt.tz_localize(datetime.timezone.utc), ), ] ) @@ -7189,7 +7046,7 @@ def test_load_table_from_dataframe_w_automatic_schema(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7250,7 +7107,7 @@ def test_load_table_from_dataframe_w_index_and_auto_schema(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7297,7 +7154,7 @@ def test_load_table_from_dataframe_unknown_table(self): location=None, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @unittest.skipIf( @@ -7339,7 +7196,7 @@ def test_load_table_from_dataframe_w_nullable_int64_datatype(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7387,7 +7244,7 @@ def test_load_table_from_dataframe_w_nullable_int64_datatype_automatic_schema(se location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7449,7 +7306,7 @@ def test_load_table_from_dataframe_struct_fields(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7490,7 +7347,7 @@ def test_load_table_from_dataframe_w_partial_schema(self): datetime.datetime(2012, 3, 14, 15, 16), ], dtype="datetime64[ns]", - ).dt.tz_localize(pytz.utc), + ).dt.tz_localize(datetime.timezone.utc), ), ("string_col", ["abc", None, "def"]), ("bytes_col", [b"abc", b"def", None]), @@ -7524,7 +7381,7 @@ def test_load_table_from_dataframe_w_partial_schema(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7619,7 +7476,7 @@ def test_load_table_from_dataframe_w_partial_schema_missing_types(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) assert warned # there should be at least one warning @@ -7695,6 +7552,42 @@ def test_load_table_from_dataframe_wo_pyarrow_raises_error(self): parquet_compression="gzip", ) + def test_load_table_from_dataframe_w_bad_pyarrow_issues_warning(self): + pytest.importorskip("pandas", reason="Requires `pandas`") + pytest.importorskip("pyarrow", reason="Requires `pyarrow`") + + client = self._make_client() + records = [{"id": 1, "age": 100}, {"id": 2, "age": 60}] + dataframe = pandas.DataFrame(records) + + pyarrow_version_patch = mock.patch( + "google.cloud.bigquery.client._PYARROW_VERSION", + packaging.version.parse("2.0.0"), # A known bad version of pyarrow. + ) + get_table_patch = mock.patch( + "google.cloud.bigquery.client.Client.get_table", + autospec=True, + side_effect=google.api_core.exceptions.NotFound("Table not found"), + ) + load_patch = mock.patch( + "google.cloud.bigquery.client.Client.load_table_from_file", autospec=True + ) + + with load_patch, get_table_patch, pyarrow_version_patch: + with warnings.catch_warnings(record=True) as warned: + client.load_table_from_dataframe( + dataframe, self.TABLE_REF, location=self.LOCATION, + ) + + expected_warnings = [ + warning for warning in warned if "pyarrow" in str(warning).lower() + ] + assert len(expected_warnings) == 1 + assert issubclass(expected_warnings[0].category, RuntimeWarning) + msg = str(expected_warnings[0].message) + assert "pyarrow 2.0.0" in msg + assert "data corruption" in msg + @unittest.skipIf(pandas is None, "Requires `pandas`") @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") def test_load_table_from_dataframe_w_nulls(self): @@ -7733,7 +7626,7 @@ def test_load_table_from_dataframe_w_nulls(self): location=self.LOCATION, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7799,7 +7692,7 @@ def test_load_table_from_dataframe_with_csv_source_format(self): location=None, project=None, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_file = load_table_from_file.mock_calls[0][1][1] @@ -7837,7 +7730,7 @@ def test_load_table_from_json_basic_use(self): location=client.location, project=client.project, job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7890,7 +7783,7 @@ def test_load_table_from_json_non_default_args(self): location="EU", project="project-x", job_config=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) sent_config = load_table_from_file.mock_calls[0][2]["job_config"] @@ -7923,6 +7816,42 @@ def test_load_table_from_json_w_invalid_job_config(self): err_msg = str(exc.value) assert "Expected an instance of LoadJobConfig" in err_msg + def test_load_table_from_json_unicode_emoji_data_case(self): + from google.cloud.bigquery.client import _DEFAULT_NUM_RETRIES + + client = self._make_client() + + emoji = "\U0001F3E6" + json_row = {"emoji": emoji} + json_rows = [json_row] + + load_patch = mock.patch( + "google.cloud.bigquery.client.Client.load_table_from_file", autospec=True + ) + + with load_patch as load_table_from_file: + client.load_table_from_json(json_rows, self.TABLE_REF) + + load_table_from_file.assert_called_once_with( + client, + mock.ANY, + self.TABLE_REF, + size=mock.ANY, + num_retries=_DEFAULT_NUM_RETRIES, + job_id=mock.ANY, + job_id_prefix=None, + location=client.location, + project=client.project, + job_config=mock.ANY, + timeout=DEFAULT_TIMEOUT, + ) + + sent_data_file = load_table_from_file.mock_calls[0][1][1] + + # make sure json_row's unicode characters are only encoded one time + expected_bytes = b'{"emoji": "' + emoji.encode("utf8") + b'"}' + assert sent_data_file.getvalue() == expected_bytes + # Low-level tests @classmethod @@ -8146,18 +8075,21 @@ def test_schema_to_json_with_file_path(self): "description": "quarter", "mode": "REQUIRED", "name": "qtr", + "policyTags": {"names": []}, "type": "STRING", }, { "description": "sales representative", "mode": "NULLABLE", "name": "rep", + "policyTags": {"names": []}, "type": "STRING", }, { "description": "total sales", "mode": "NULLABLE", "name": "sales", + "policyTags": {"names": []}, "type": "FLOAT", }, ] @@ -8190,18 +8122,21 @@ def test_schema_to_json_with_file_object(self): "description": "quarter", "mode": "REQUIRED", "name": "qtr", + "policyTags": {"names": []}, "type": "STRING", }, { "description": "sales representative", "mode": "NULLABLE", "name": "rep", + "policyTags": {"names": []}, "type": "STRING", }, { "description": "total sales", "mode": "NULLABLE", "name": "sales", + "policyTags": {"names": []}, "type": "FLOAT", }, ] @@ -8218,3 +8153,23 @@ def test_schema_to_json_with_file_object(self): client.schema_to_json(schema_list, fake_file) assert file_content == json.loads(fake_file.getvalue()) + + +def test_upload_chunksize(client): + with mock.patch("google.cloud.bigquery.client.ResumableUpload") as RU: + upload = RU.return_value + + upload.finished = False + + def transmit_next_chunk(transport): + upload.finished = True + result = mock.MagicMock() + result.json.return_value = {} + return result + + upload.transmit_next_chunk = transmit_next_chunk + f = io.BytesIO() + client.load_table_from_file(f, "foo.bar") + + chunk_size = RU.call_args_list[0][0][1] + assert chunk_size == 100 * (1 << 20) diff --git a/tests/unit/test_create_dataset.py b/tests/unit/test_create_dataset.py index d07aaed4f..67b21225d 100644 --- a/tests/unit/test_create_dataset.py +++ b/tests/unit/test_create_dataset.py @@ -15,6 +15,7 @@ from google.cloud.bigquery.dataset import Dataset, DatasetReference from .helpers import make_connection, dataset_polymorphic, make_client import google.cloud.bigquery.dataset +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT import mock import pytest @@ -111,7 +112,7 @@ def test_create_dataset_w_attrs(client, PROJECT, DS_ID): "access": [{"role": "OWNER", "userByEmail": USER_EMAIL}, {"view": VIEW}], "labels": LABELS, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -143,7 +144,7 @@ def test_create_dataset_w_custom_property(client, PROJECT, DS_ID): "newAlphaProperty": "unreleased property", "labels": {}, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -176,7 +177,7 @@ def test_create_dataset_w_client_location_wo_dataset_location(PROJECT, DS_ID, LO "labels": {}, "location": LOCATION, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -211,7 +212,7 @@ def test_create_dataset_w_client_location_w_dataset_location(PROJECT, DS_ID, LOC "labels": {}, "location": OTHER_LOCATION, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -241,7 +242,7 @@ def test_create_dataset_w_reference(PROJECT, DS_ID, LOCATION): "labels": {}, "location": LOCATION, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -271,7 +272,7 @@ def test_create_dataset_w_fully_qualified_string(PROJECT, DS_ID, LOCATION): "labels": {}, "location": LOCATION, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -306,7 +307,7 @@ def test_create_dataset_w_string(PROJECT, DS_ID, LOCATION): "labels": {}, "location": LOCATION, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -356,8 +357,8 @@ def test_create_dataset_alreadyexists_w_exists_ok_true(PROJECT, DS_ID, LOCATION) "labels": {}, "location": LOCATION, }, - timeout=None, + timeout=DEFAULT_TIMEOUT, ), - mock.call(method="GET", path=get_path, timeout=None), + mock.call(method="GET", path=get_path, timeout=DEFAULT_TIMEOUT), ] ) diff --git a/tests/unit/test_dbapi__helpers.py b/tests/unit/test_dbapi__helpers.py index 250ba46d9..b33203354 100644 --- a/tests/unit/test_dbapi__helpers.py +++ b/tests/unit/test_dbapi__helpers.py @@ -16,6 +16,7 @@ import decimal import math import operator as op +import re import unittest import pytest @@ -394,11 +395,13 @@ def test_to_query_parameters_dict_w_types(): assert sorted( _helpers.to_query_parameters( - dict(i=1, x=1.2, y=None, z=[]), dict(x="numeric", y="string", z="float64") + dict(i=1, x=1.2, y=None, q="hi", z=[]), + dict(x="numeric", y="string", q="string(9)", z="float64"), ), key=lambda p: p.name, ) == [ bigquery.ScalarQueryParameter("i", "INT64", 1), + bigquery.ScalarQueryParameter("q", "STRING", "hi"), bigquery.ScalarQueryParameter("x", "NUMERIC", 1.2), bigquery.ScalarQueryParameter("y", "STRING", None), bigquery.ArrayQueryParameter("z", "FLOAT64", []), @@ -409,10 +412,285 @@ def test_to_query_parameters_list_w_types(): from google.cloud import bigquery assert _helpers.to_query_parameters( - [1, 1.2, None, []], [None, "numeric", "string", "float64"] + [1, 1.2, None, "hi", []], [None, "numeric", "string", "string(9)", "float64"] ) == [ bigquery.ScalarQueryParameter(None, "INT64", 1), bigquery.ScalarQueryParameter(None, "NUMERIC", 1.2), bigquery.ScalarQueryParameter(None, "STRING", None), + bigquery.ScalarQueryParameter(None, "STRING", "hi"), bigquery.ArrayQueryParameter(None, "FLOAT64", []), ] + + +@pytest.mark.parametrize( + "value,type_,expect", + [ + ( + [], + "ARRAY", + { + "parameterType": {"type": "ARRAY", "arrayType": {"type": "INT64"}}, + "parameterValue": {"arrayValues": []}, + }, + ), + ( + [1, 2], + "ARRAY", + { + "parameterType": {"type": "ARRAY", "arrayType": {"type": "INT64"}}, + "parameterValue": {"arrayValues": [{"value": "1"}, {"value": "2"}]}, + }, + ), + ( + dict( + name="par", + children=[ + dict(name="ch1", bdate=datetime.date(2021, 1, 1)), + dict(name="ch2", bdate=datetime.date(2021, 1, 2)), + ], + ), + "struct>>", + { + "parameterType": { + "structTypes": [ + {"name": "name", "type": {"type": "STRING"}}, + { + "name": "children", + "type": { + "arrayType": { + "structTypes": [ + {"name": "name", "type": {"type": "STRING"}}, + {"name": "bdate", "type": {"type": "DATE"}}, + ], + "type": "STRUCT", + }, + "type": "ARRAY", + }, + }, + ], + "type": "STRUCT", + }, + "parameterValue": { + "structValues": { + "children": { + "arrayValues": [ + { + "structValues": { + "bdate": {"value": "2021-01-01"}, + "name": {"value": "ch1"}, + } + }, + { + "structValues": { + "bdate": {"value": "2021-01-02"}, + "name": {"value": "ch2"}, + } + }, + ] + }, + "name": {"value": "par"}, + } + }, + }, + ), + ( + dict( + name="par", + children=[ + dict(name="ch1", bdate=datetime.date(2021, 1, 1)), + dict(name="ch2", bdate=datetime.date(2021, 1, 2)), + ], + ), + "struct>>", + { + "parameterType": { + "structTypes": [ + {"name": "name", "type": {"type": "STRING"}}, + { + "name": "children", + "type": { + "arrayType": { + "structTypes": [ + {"name": "name", "type": {"type": "STRING"}}, + {"name": "bdate", "type": {"type": "DATE"}}, + ], + "type": "STRUCT", + }, + "type": "ARRAY", + }, + }, + ], + "type": "STRUCT", + }, + "parameterValue": { + "structValues": { + "children": { + "arrayValues": [ + { + "structValues": { + "bdate": {"value": "2021-01-01"}, + "name": {"value": "ch1"}, + } + }, + { + "structValues": { + "bdate": {"value": "2021-01-02"}, + "name": {"value": "ch2"}, + } + }, + ] + }, + "name": {"value": "par"}, + } + }, + }, + ), + ( + ["1", "hi"], + "ARRAY", + { + "parameterType": {"type": "ARRAY", "arrayType": {"type": "STRING"}}, + "parameterValue": {"arrayValues": [{"value": "1"}, {"value": "hi"}]}, + }, + ), + ], +) +def test_complex_query_parameter_type(type_, value, expect): + from google.cloud.bigquery.dbapi._helpers import complex_query_parameter + + param = complex_query_parameter("test", value, type_).to_api_repr() + assert param.pop("name") == "test" + assert param == expect + + +def _expected_error_match(expect): + return "^" + re.escape(expect) + "$" + + +@pytest.mark.parametrize( + "value,type_,expect", + [ + ( + [], + "ARRAY", + "The given parameter type, INT," + " is not a valid BigQuery scalar type, in ARRAY.", + ), + ([], "x", "Invalid parameter type, x"), + ({}, "struct", "Invalid struct field, int, in struct"), + ( + {"x": 1}, + "struct", + "The given parameter type, int," + " for x is not a valid BigQuery scalar type, in struct.", + ), + ([], "x<", "Invalid parameter type, x<"), + (0, "ARRAY", "Array type with non-array-like value with type int"), + ( + [], + "ARRAY>", + "Array can't contain an array in ARRAY>", + ), + ([], "struct", "Non-mapping value for type struct"), + ({}, "struct", "No field value for x in struct"), + ({"x": 1, "y": 1}, "struct", "Extra data keys for struct"), + ([], "array>", "Invalid struct field, xxx, in array>"), + ([], "array<<>>", "Invalid parameter type, <>"), + ], +) +def test_complex_query_parameter_type_errors(type_, value, expect): + from google.cloud.bigquery.dbapi._helpers import complex_query_parameter + from google.cloud.bigquery.dbapi import exceptions + + with pytest.raises( + exceptions.ProgrammingError, match=_expected_error_match(expect), + ): + complex_query_parameter("test", value, type_) + + +@pytest.mark.parametrize( + "parameters,parameter_types,expect", + [ + ( + [[], dict(name="ch1", bdate=datetime.date(2021, 1, 1))], + ["ARRAY", "struct"], + [ + { + "parameterType": {"arrayType": {"type": "INT64"}, "type": "ARRAY"}, + "parameterValue": {"arrayValues": []}, + }, + { + "parameterType": { + "structTypes": [ + {"name": "name", "type": {"type": "STRING"}}, + {"name": "bdate", "type": {"type": "DATE"}}, + ], + "type": "STRUCT", + }, + "parameterValue": { + "structValues": { + "bdate": {"value": "2021-01-01"}, + "name": {"value": "ch1"}, + } + }, + }, + ], + ), + ( + dict(ids=[], child=dict(name="ch1", bdate=datetime.date(2021, 1, 1))), + dict(ids="ARRAY", child="struct"), + [ + { + "name": "ids", + "parameterType": {"arrayType": {"type": "INT64"}, "type": "ARRAY"}, + "parameterValue": {"arrayValues": []}, + }, + { + "name": "child", + "parameterType": { + "structTypes": [ + {"name": "name", "type": {"type": "STRING"}}, + {"name": "bdate", "type": {"type": "DATE"}}, + ], + "type": "STRUCT", + }, + "parameterValue": { + "structValues": { + "bdate": {"value": "2021-01-01"}, + "name": {"value": "ch1"}, + } + }, + }, + ], + ), + ], +) +def test_to_query_parameters_complex_types(parameters, parameter_types, expect): + from google.cloud.bigquery.dbapi._helpers import to_query_parameters + + result = [p.to_api_repr() for p in to_query_parameters(parameters, parameter_types)] + assert result == expect + + +def test_to_query_parameters_struct_error(): + from google.cloud.bigquery.dbapi._helpers import to_query_parameters + + with pytest.raises( + NotImplementedError, + match=_expected_error_match( + "STRUCT-like parameter values are not supported, " + "unless an explicit type is give in the parameter placeholder " + "(e.g. '%(:struct<...>)s')." + ), + ): + to_query_parameters([dict(x=1)], [None]) + + with pytest.raises( + NotImplementedError, + match=_expected_error_match( + "STRUCT-like parameter values are not supported (parameter foo), " + "unless an explicit type is give in the parameter placeholder " + "(e.g. '%(foo:struct<...>)s')." + ), + ): + to_query_parameters(dict(foo=dict(x=1)), {}) diff --git a/tests/unit/test_dbapi_connection.py b/tests/unit/test_dbapi_connection.py index 74da318bf..0576cad38 100644 --- a/tests/unit/test_dbapi_connection.py +++ b/tests/unit/test_dbapi_connection.py @@ -51,7 +51,7 @@ def test_ctor_wo_bqstorage_client(self): from google.cloud.bigquery.dbapi import Connection mock_client = self._mock_client() - mock_client._create_bqstorage_client.return_value = None + mock_client._ensure_bqstorage_client.return_value = None connection = self._make_one(client=mock_client) self.assertIsInstance(connection, Connection) @@ -66,9 +66,15 @@ def test_ctor_w_bqstorage_client(self): mock_client = self._mock_client() mock_bqstorage_client = self._mock_bqstorage_client() + mock_client._ensure_bqstorage_client.return_value = mock_bqstorage_client + connection = self._make_one( client=mock_client, bqstorage_client=mock_bqstorage_client, ) + + mock_client._ensure_bqstorage_client.assert_called_once_with( + mock_bqstorage_client + ) self.assertIsInstance(connection, Connection) self.assertIs(connection._client, mock_client) self.assertIs(connection._bqstorage_client, mock_bqstorage_client) @@ -92,9 +98,11 @@ def test_connect_w_client(self): mock_client = self._mock_client() mock_bqstorage_client = self._mock_bqstorage_client() - mock_client._create_bqstorage_client.return_value = mock_bqstorage_client + mock_client._ensure_bqstorage_client.return_value = mock_bqstorage_client connection = connect(client=mock_client) + + mock_client._ensure_bqstorage_client.assert_called_once_with() self.assertIsInstance(connection, Connection) self.assertIs(connection._client, mock_client) self.assertIs(connection._bqstorage_client, mock_bqstorage_client) @@ -108,9 +116,15 @@ def test_connect_w_both_clients(self): mock_client = self._mock_client() mock_bqstorage_client = self._mock_bqstorage_client() + mock_client._ensure_bqstorage_client.return_value = mock_bqstorage_client + connection = connect( client=mock_client, bqstorage_client=mock_bqstorage_client, ) + + mock_client._ensure_bqstorage_client.assert_called_once_with( + mock_bqstorage_client + ) self.assertIsInstance(connection, Connection) self.assertIs(connection._client, mock_client) self.assertIs(connection._bqstorage_client, mock_bqstorage_client) @@ -140,7 +154,7 @@ def test_close_closes_all_created_bigquery_clients(self): return_value=client, ) bqstorage_client_patcher = mock.patch.object( - client, "_create_bqstorage_client", return_value=bqstorage_client, + client, "_ensure_bqstorage_client", return_value=bqstorage_client, ) with client_patcher, bqstorage_client_patcher: diff --git a/tests/unit/test_dbapi_cursor.py b/tests/unit/test_dbapi_cursor.py index 55e453254..026810aaf 100644 --- a/tests/unit/test_dbapi_cursor.py +++ b/tests/unit/test_dbapi_cursor.py @@ -72,7 +72,7 @@ def _mock_client( mock_client._default_query_job_config = default_query_job_config # Assure that the REST client gets used, not the BQ Storage client. - mock_client._create_bqstorage_client.return_value = None + mock_client._ensure_bqstorage_client.return_value = None return mock_client @@ -311,6 +311,7 @@ def test_fetchall_w_bqstorage_client_fetch_success(self): mock_bqstorage_client = self._mock_bqstorage_client( stream_count=1, rows=bqstorage_streamed_rows, ) + mock_client._ensure_bqstorage_client.return_value = mock_bqstorage_client connection = dbapi.connect( client=mock_client, bqstorage_client=mock_bqstorage_client, @@ -341,6 +342,7 @@ def test_fetchall_w_bqstorage_client_fetch_no_rows(self): mock_client = self._mock_client(rows=[]) mock_bqstorage_client = self._mock_bqstorage_client(stream_count=0) + mock_client._ensure_bqstorage_client.return_value = mock_bqstorage_client connection = dbapi.connect( client=mock_client, bqstorage_client=mock_bqstorage_client, @@ -365,7 +367,11 @@ def test_fetchall_w_bqstorage_client_fetch_error_no_fallback(self): row_data = [table.Row([1.1, 1.2], {"foo": 0, "bar": 1})] + def fake_ensure_bqstorage_client(bqstorage_client=None, **kwargs): + return bqstorage_client + mock_client = self._mock_client(rows=row_data) + mock_client._ensure_bqstorage_client.side_effect = fake_ensure_bqstorage_client mock_bqstorage_client = self._mock_bqstorage_client( stream_count=1, rows=row_data, ) @@ -396,7 +402,11 @@ def test_fetchall_w_bqstorage_client_no_arrow_compression(self): row_data = [table.Row([1.2, 1.1], {"bar": 1, "foo": 0})] bqstorage_streamed_rows = [{"bar": _to_pyarrow(1.2), "foo": _to_pyarrow(1.1)}] + def fake_ensure_bqstorage_client(bqstorage_client=None, **kwargs): + return bqstorage_client + mock_client = self._mock_client(rows=row_data) + mock_client._ensure_bqstorage_client.side_effect = fake_ensure_bqstorage_client mock_bqstorage_client = self._mock_bqstorage_client( stream_count=1, rows=bqstorage_streamed_rows, ) @@ -799,6 +809,32 @@ def test__format_operation_no_placeholders(self): "values(%%%%%(foo:INT64)s, %(bar)s)", ("values(%%%%%(foo)s, %(bar)s)", dict(foo="INT64")), ), + ( + "values(%%%%%(foo:struct)s, %(bar)s)", + ("values(%%%%%(foo)s, %(bar)s)", dict(foo="struct")), + ), + ( + "values(%%%%%(foo:struct)s, %(bar)s)", + ("values(%%%%%(foo)s, %(bar)s)", dict(foo="struct")), + ), + ( + "values(%(foo:struct)s, %(bar)s)", + ( + "values(%(foo)s, %(bar)s)", + dict(foo="struct"), + ), + ), + ( + "values(%(foo:struct)s, %(bar)s)", + ( + "values(%(foo)s, %(bar)s)", + dict(foo="struct"), + ), + ), + ( + "values(%(foo:string(10))s, %(bar)s)", + ("values(%(foo)s, %(bar)s)", dict(foo="string(10)")), + ), ], ) def test__extract_types(inp, expect): diff --git a/tests/unit/test_delete_dataset.py b/tests/unit/test_delete_dataset.py index 3a65e031c..b48beb147 100644 --- a/tests/unit/test_delete_dataset.py +++ b/tests/unit/test_delete_dataset.py @@ -14,6 +14,7 @@ from .helpers import make_connection, make_client, dataset_polymorphic import google.api_core.exceptions +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT import pytest @@ -40,7 +41,7 @@ def test_delete_dataset_delete_contents( method="DELETE", path="/%s" % PATH, query_params={"deleteContents": "true"}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) @@ -61,7 +62,7 @@ def test_delete_dataset_w_not_found_ok_false(PROJECT, DS_ID): client.delete_dataset(DS_ID) conn.api_request.assert_called_with( - method="DELETE", path=path, query_params={}, timeout=None + method="DELETE", path=path, query_params={}, timeout=DEFAULT_TIMEOUT ) @@ -74,5 +75,5 @@ def test_delete_dataset_w_not_found_ok_true(PROJECT, DS_ID): ) client.delete_dataset(DS_ID, not_found_ok=True) conn.api_request.assert_called_with( - method="DELETE", path=path, query_params={}, timeout=None + method="DELETE", path=path, query_params={}, timeout=DEFAULT_TIMEOUT ) diff --git a/tests/unit/test_external_config.py b/tests/unit/test_external_config.py index 648a8717e..1f49dba5d 100644 --- a/tests/unit/test_external_config.py +++ b/tests/unit/test_external_config.py @@ -78,7 +78,14 @@ def test_to_api_repr_base(self): ec.schema = [schema.SchemaField("full_name", "STRING", mode="REQUIRED")] exp_schema = { - "fields": [{"name": "full_name", "type": "STRING", "mode": "REQUIRED"}] + "fields": [ + { + "name": "full_name", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + } + ] } got_resource = ec.to_api_repr() exp_resource = { @@ -425,6 +432,164 @@ def test_to_api_repr_bigtable(self): self.assertEqual(got_resource, exp_resource) + def test_parquet_options_getter(self): + from google.cloud.bigquery.format_options import ParquetOptions + + parquet_options = ParquetOptions.from_api_repr( + {"enumAsString": True, "enableListInference": False} + ) + ec = external_config.ExternalConfig( + external_config.ExternalSourceFormat.PARQUET + ) + + self.assertIsNone(ec.parquet_options.enum_as_string) + self.assertIsNone(ec.parquet_options.enable_list_inference) + + ec._options = parquet_options + + self.assertTrue(ec.parquet_options.enum_as_string) + self.assertFalse(ec.parquet_options.enable_list_inference) + + self.assertIs(ec.parquet_options, ec.options) + + def test_parquet_options_getter_non_parquet_format(self): + ec = external_config.ExternalConfig(external_config.ExternalSourceFormat.CSV) + self.assertIsNone(ec.parquet_options) + + def test_parquet_options_setter(self): + from google.cloud.bigquery.format_options import ParquetOptions + + parquet_options = ParquetOptions.from_api_repr( + {"enumAsString": False, "enableListInference": True} + ) + ec = external_config.ExternalConfig( + external_config.ExternalSourceFormat.PARQUET + ) + + ec.parquet_options = parquet_options + + # Setting Parquet options should be reflected in the generic options attribute. + self.assertFalse(ec.options.enum_as_string) + self.assertTrue(ec.options.enable_list_inference) + + def test_parquet_options_setter_non_parquet_format(self): + from google.cloud.bigquery.format_options import ParquetOptions + + parquet_options = ParquetOptions.from_api_repr( + {"enumAsString": False, "enableListInference": True} + ) + ec = external_config.ExternalConfig(external_config.ExternalSourceFormat.CSV) + + with self.assertRaisesRegex(TypeError, "Cannot set.*source format is CSV"): + ec.parquet_options = parquet_options + + def test_from_api_repr_parquet(self): + from google.cloud.bigquery.format_options import ParquetOptions + + resource = _copy_and_update( + self.BASE_RESOURCE, + { + "sourceFormat": "PARQUET", + "parquetOptions": {"enumAsString": True, "enableListInference": False}, + }, + ) + + ec = external_config.ExternalConfig.from_api_repr(resource) + + self._verify_base(ec) + self.assertEqual(ec.source_format, external_config.ExternalSourceFormat.PARQUET) + self.assertIsInstance(ec.options, ParquetOptions) + self.assertTrue(ec.parquet_options.enum_as_string) + self.assertFalse(ec.parquet_options.enable_list_inference) + + got_resource = ec.to_api_repr() + + self.assertEqual(got_resource, resource) + + del resource["parquetOptions"]["enableListInference"] + ec = external_config.ExternalConfig.from_api_repr(resource) + self.assertIsNone(ec.options.enable_list_inference) + got_resource = ec.to_api_repr() + self.assertEqual(got_resource, resource) + + def test_to_api_repr_parquet(self): + from google.cloud.bigquery.format_options import ParquetOptions + + ec = external_config.ExternalConfig( + external_config.ExternalSourceFormat.PARQUET + ) + options = ParquetOptions.from_api_repr( + dict(enumAsString=False, enableListInference=True) + ) + ec._options = options + + exp_resource = { + "sourceFormat": external_config.ExternalSourceFormat.PARQUET, + "parquetOptions": {"enumAsString": False, "enableListInference": True}, + } + + got_resource = ec.to_api_repr() + + self.assertEqual(got_resource, exp_resource) + + def test_from_api_repr_decimal_target_types(self): + from google.cloud.bigquery.enums import DecimalTargetType + + resource = _copy_and_update( + self.BASE_RESOURCE, + { + "sourceFormat": "FORMAT_FOO", + "decimalTargetTypes": [DecimalTargetType.NUMERIC], + }, + ) + + ec = external_config.ExternalConfig.from_api_repr(resource) + + self._verify_base(ec) + self.assertEqual(ec.source_format, "FORMAT_FOO") + self.assertEqual( + ec.decimal_target_types, frozenset([DecimalTargetType.NUMERIC]) + ) + + # converting back to API representation should yield the same result + got_resource = ec.to_api_repr() + self.assertEqual(got_resource, resource) + + del resource["decimalTargetTypes"] + ec = external_config.ExternalConfig.from_api_repr(resource) + self.assertIsNone(ec.decimal_target_types) + + got_resource = ec.to_api_repr() + self.assertEqual(got_resource, resource) + + def test_to_api_repr_decimal_target_types(self): + from google.cloud.bigquery.enums import DecimalTargetType + + ec = external_config.ExternalConfig("FORMAT_FOO") + ec.decimal_target_types = [DecimalTargetType.NUMERIC, DecimalTargetType.STRING] + + got_resource = ec.to_api_repr() + + expected_resource = { + "sourceFormat": "FORMAT_FOO", + "decimalTargetTypes": [DecimalTargetType.NUMERIC, DecimalTargetType.STRING], + } + self.assertEqual(got_resource, expected_resource) + + def test_to_api_repr_decimal_target_types_unset(self): + from google.cloud.bigquery.enums import DecimalTargetType + + ec = external_config.ExternalConfig("FORMAT_FOO") + ec._properties["decimalTargetTypes"] = [DecimalTargetType.NUMERIC] + ec.decimal_target_types = None + + got_resource = ec.to_api_repr() + + expected_resource = {"sourceFormat": "FORMAT_FOO"} + self.assertEqual(got_resource, expected_resource) + + ec.decimal_target_types = None # No error if unsetting when already unset. + def _copy_and_update(d, u): d = copy.deepcopy(d) diff --git a/tests/unit/test_format_options.py b/tests/unit/test_format_options.py new file mode 100644 index 000000000..ab5f9e05c --- /dev/null +++ b/tests/unit/test_format_options.py @@ -0,0 +1,41 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + + +class TestParquetOptions: + @staticmethod + def _get_target_class(): + from google.cloud.bigquery.format_options import ParquetOptions + + return ParquetOptions + + def test_ctor(self): + config = self._get_target_class()() + assert config.enum_as_string is None + assert config.enable_list_inference is None + + def test_from_api_repr(self): + config = self._get_target_class().from_api_repr( + {"enumAsString": False, "enableListInference": True} + ) + assert not config.enum_as_string + assert config.enable_list_inference + + def test_to_api_repr(self): + config = self._get_target_class()() + config.enum_as_string = True + config.enable_list_inference = False + + result = config.to_api_repr() + assert result == {"enumAsString": True, "enableListInference": False} diff --git a/tests/unit/test_job_retry.py b/tests/unit/test_job_retry.py new file mode 100644 index 000000000..b2095d2f2 --- /dev/null +++ b/tests/unit/test_job_retry.py @@ -0,0 +1,247 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import datetime +import re + +import mock +import pytest + +import google.api_core.exceptions +import google.api_core.retry + +from .helpers import make_connection + + +# With job_retry_on_query, we're testing 4 scenarios: +# - No `job_retry` passed, retry on default rateLimitExceeded. +# - Pass NotFound retry to `query`. +# - Pass NotFound retry to `result`. +# - Pass BadRequest retry to query, with the value passed to `result` overriding. +@pytest.mark.parametrize("job_retry_on_query", [None, "Query", "Result", "Both"]) +@mock.patch("time.sleep") +def test_retry_failed_jobs(sleep, client, job_retry_on_query): + """ + Test retry of job failures, as opposed to API-invocation failures. + """ + + retry_notfound = google.api_core.retry.Retry( + predicate=google.api_core.retry.if_exception_type( + google.api_core.exceptions.NotFound + ) + ) + retry_badrequest = google.api_core.retry.Retry( + predicate=google.api_core.retry.if_exception_type( + google.api_core.exceptions.BadRequest + ) + ) + + if job_retry_on_query is None: + reason = "rateLimitExceeded" + else: + reason = "notFound" + + err = dict(reason=reason) + responses = [ + dict(status=dict(state="DONE", errors=[err], errorResult=err)), + dict(status=dict(state="DONE", errors=[err], errorResult=err)), + dict(status=dict(state="DONE", errors=[err], errorResult=err)), + dict(status=dict(state="DONE")), + dict(rows=[{"f": [{"v": "1"}]}], totalRows="1"), + ] + + def api_request(method, path, query_params=None, data=None, **kw): + response = responses.pop(0) + if data: + response["jobReference"] = data["jobReference"] + else: + response["jobReference"] = dict( + jobId=path.split("/")[-1], projectId="PROJECT" + ) + return response + + conn = client._connection = make_connection() + conn.api_request.side_effect = api_request + + if job_retry_on_query == "Query": + job_retry = dict(job_retry=retry_notfound) + elif job_retry_on_query == "Both": + # This will be overridden in `result` + job_retry = dict(job_retry=retry_badrequest) + else: + job_retry = {} + job = client.query("select 1", **job_retry) + + orig_job_id = job.job_id + job_retry = ( + dict(job_retry=retry_notfound) + if job_retry_on_query in ("Result", "Both") + else {} + ) + result = job.result(**job_retry) + assert result.total_rows == 1 + assert not responses # We made all the calls we expected to. + + # The job adjusts it's job id based on the id of the last attempt. + assert job.job_id != orig_job_id + assert job.job_id == conn.mock_calls[3][2]["data"]["jobReference"]["jobId"] + + # We had to sleep three times + assert len(sleep.mock_calls) == 3 + + # Sleeps are random, however they're more than 0 + assert min(c[1][0] for c in sleep.mock_calls) > 0 + + # They're at most 2 * (multiplier**(number of sleeps - 1)) * initial + # The default multiplier is 2 + assert max(c[1][0] for c in sleep.mock_calls) <= 8 + + # We can ask for the result again: + responses = [ + dict(rows=[{"f": [{"v": "1"}]}], totalRows="1"), + ] + orig_job_id = job.job_id + result = job.result() + assert result.total_rows == 1 + assert not responses # We made all the calls we expected to. + + # We wouldn't (and didn't) fail, because we're dealing with a successful job. + # So the job id hasn't changed. + assert job.job_id == orig_job_id + + +# With job_retry_on_query, we're testing 4 scenarios: +# - Pass None retry to `query`. +# - Pass None retry to `result`. +@pytest.mark.parametrize("job_retry_on_query", ["Query", "Result"]) +@mock.patch("time.sleep") +def test_disable_retry_failed_jobs(sleep, client, job_retry_on_query): + """ + Test retry of job failures, as opposed to API-invocation failures. + """ + err = dict(reason="rateLimitExceeded") + responses = [dict(status=dict(state="DONE", errors=[err], errorResult=err))] * 3 + + def api_request(method, path, query_params=None, data=None, **kw): + response = responses.pop(0) + response["jobReference"] = data["jobReference"] + return response + + conn = client._connection = make_connection() + conn.api_request.side_effect = api_request + + if job_retry_on_query == "Query": + job_retry = dict(job_retry=None) + else: + job_retry = {} + job = client.query("select 1", **job_retry) + + orig_job_id = job.job_id + job_retry = dict(job_retry=None) if job_retry_on_query == "Result" else {} + with pytest.raises(google.api_core.exceptions.Forbidden): + job.result(**job_retry) + + assert job.job_id == orig_job_id + assert len(sleep.mock_calls) == 0 + + +@mock.patch("google.api_core.retry.datetime_helpers") +@mock.patch("time.sleep") +def test_retry_failed_jobs_after_retry_failed(sleep, datetime_helpers, client): + """ + If at first you don't succeed, maybe you will later. :) + """ + conn = client._connection = make_connection() + + datetime_helpers.utcnow.return_value = datetime.datetime(2021, 7, 29, 10, 43, 2) + + err = dict(reason="rateLimitExceeded") + + def api_request(method, path, query_params=None, data=None, **kw): + calls = sleep.mock_calls + if calls: + datetime_helpers.utcnow.return_value += datetime.timedelta( + seconds=calls[-1][1][0] + ) + response = dict(status=dict(state="DONE", errors=[err], errorResult=err)) + response["jobReference"] = data["jobReference"] + return response + + conn.api_request.side_effect = api_request + + job = client.query("select 1") + orig_job_id = job.job_id + + with pytest.raises(google.api_core.exceptions.RetryError): + job.result() + + # We never got a successful job, so the job id never changed: + assert job.job_id == orig_job_id + + # We failed because we couldn't succeed after 120 seconds. + # But we can try again: + err2 = dict(reason="backendError") # We also retry on this + responses = [ + dict(status=dict(state="DONE", errors=[err2], errorResult=err2)), + dict(status=dict(state="DONE", errors=[err], errorResult=err)), + dict(status=dict(state="DONE", errors=[err2], errorResult=err2)), + dict(status=dict(state="DONE")), + dict(rows=[{"f": [{"v": "1"}]}], totalRows="1"), + ] + + def api_request(method, path, query_params=None, data=None, **kw): + calls = sleep.mock_calls + datetime_helpers.utcnow.return_value += datetime.timedelta( + seconds=calls[-1][1][0] + ) + response = responses.pop(0) + if data: + response["jobReference"] = data["jobReference"] + else: + response["jobReference"] = dict( + jobId=path.split("/")[-1], projectId="PROJECT" + ) + return response + + conn.api_request.side_effect = api_request + result = job.result() + assert result.total_rows == 1 + assert not responses # We made all the calls we expected to. + assert job.job_id != orig_job_id + + +def test_raises_on_job_retry_on_query_with_non_retryable_jobs(client): + with pytest.raises( + TypeError, + match=re.escape( + "`job_retry` was provided, but the returned job is" + " not retryable, because a custom `job_id` was" + " provided." + ), + ): + client.query("select 42", job_id=42, job_retry=google.api_core.retry.Retry()) + + +def test_raises_on_job_retry_on_result_with_non_retryable_jobs(client): + client._connection = make_connection({}) + job = client.query("select 42", job_id=42) + with pytest.raises( + TypeError, + match=re.escape( + "`job_retry` was provided, but this job is" + " not retryable, because a custom `job_id` was" + " provided to the query that created this job." + ), + ): + job.result(job_retry=google.api_core.retry.Retry()) diff --git a/tests/unit/test_list_datasets.py b/tests/unit/test_list_datasets.py new file mode 100644 index 000000000..6f0b55c5e --- /dev/null +++ b/tests/unit/test_list_datasets.py @@ -0,0 +1,125 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import mock +import pytest + +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT +from .helpers import make_connection + + +@pytest.mark.parametrize( + "extra,query", [({}, {}), (dict(page_size=42), dict(maxResults=42))] +) +def test_list_datasets_defaults(client, PROJECT, extra, query): + from google.cloud.bigquery.dataset import DatasetListItem + + DATASET_1 = "dataset_one" + DATASET_2 = "dataset_two" + PATH = "projects/%s/datasets" % PROJECT + TOKEN = "TOKEN" + DATA = { + "nextPageToken": TOKEN, + "datasets": [ + { + "kind": "bigquery#dataset", + "id": "%s:%s" % (PROJECT, DATASET_1), + "datasetReference": {"datasetId": DATASET_1, "projectId": PROJECT}, + "friendlyName": None, + }, + { + "kind": "bigquery#dataset", + "id": "%s:%s" % (PROJECT, DATASET_2), + "datasetReference": {"datasetId": DATASET_2, "projectId": PROJECT}, + "friendlyName": "Two", + }, + ], + } + conn = client._connection = make_connection(DATA) + + iterator = client.list_datasets(**extra) + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) + datasets = list(page) + token = iterator.next_page_token + + assert len(datasets) == len(DATA["datasets"]) + for found, expected in zip(datasets, DATA["datasets"]): + assert isinstance(found, DatasetListItem) + assert found.full_dataset_id == expected["id"] + assert found.friendly_name == expected["friendlyName"] + assert token == TOKEN + + conn.api_request.assert_called_once_with( + method="GET", path="/%s" % PATH, query_params=query, timeout=DEFAULT_TIMEOUT + ) + + +def test_list_datasets_w_project_and_timeout(client, PROJECT): + conn = client._connection = make_connection({}) + + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + list(client.list_datasets(project="other-project", timeout=7.5)) + + final_attributes.assert_called_once_with( + {"path": "/projects/other-project/datasets"}, client, None + ) + + conn.api_request.assert_called_once_with( + method="GET", + path="/projects/other-project/datasets", + query_params={}, + timeout=7.5, + ) + + +def test_list_datasets_explicit_response_missing_datasets_key(client, PROJECT): + PATH = "projects/%s/datasets" % PROJECT + TOKEN = "TOKEN" + FILTER = "FILTER" + DATA = {} + conn = client._connection = make_connection(DATA) + + iterator = client.list_datasets( + include_all=True, filter=FILTER, max_results=3, page_token=TOKEN + ) + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) + datasets = list(page) + token = iterator.next_page_token + + assert len(datasets) == 0 + assert token is None + + conn.api_request.assert_called_once_with( + method="GET", + path="/%s" % PATH, + query_params={ + "all": True, + "filter": FILTER, + "maxResults": 3, + "pageToken": TOKEN, + }, + timeout=DEFAULT_TIMEOUT, + ) diff --git a/tests/unit/test_list_jobs.py b/tests/unit/test_list_jobs.py new file mode 100644 index 000000000..1fb40d446 --- /dev/null +++ b/tests/unit/test_list_jobs.py @@ -0,0 +1,292 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import datetime + +import mock +import pytest + +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT +from .helpers import make_connection + + +@pytest.mark.parametrize( + "extra,query", [({}, {}), (dict(page_size=42), dict(maxResults=42))] +) +def test_list_jobs_defaults(client, PROJECT, DS_ID, extra, query): + from google.cloud.bigquery.job import CopyJob + from google.cloud.bigquery.job import CreateDisposition + from google.cloud.bigquery.job import ExtractJob + from google.cloud.bigquery.job import LoadJob + from google.cloud.bigquery.job import QueryJob + from google.cloud.bigquery.job import WriteDisposition + + SOURCE_TABLE = "source_table" + DESTINATION_TABLE = "destination_table" + QUERY_DESTINATION_TABLE = "query_destination_table" + SOURCE_URI = "gs://test_bucket/src_object*" + DESTINATION_URI = "gs://test_bucket/dst_object*" + JOB_TYPES = { + "load_job": LoadJob, + "copy_job": CopyJob, + "extract_job": ExtractJob, + "query_job": QueryJob, + } + PATH = "projects/%s/jobs" % PROJECT + TOKEN = "TOKEN" + QUERY = "SELECT * from test_dataset:test_table" + ASYNC_QUERY_DATA = { + "id": "%s:%s" % (PROJECT, "query_job"), + "jobReference": {"projectId": PROJECT, "jobId": "query_job"}, + "state": "DONE", + "configuration": { + "query": { + "query": QUERY, + "destinationTable": { + "projectId": PROJECT, + "datasetId": DS_ID, + "tableId": QUERY_DESTINATION_TABLE, + }, + "createDisposition": CreateDisposition.CREATE_IF_NEEDED, + "writeDisposition": WriteDisposition.WRITE_TRUNCATE, + } + }, + } + EXTRACT_DATA = { + "id": "%s:%s" % (PROJECT, "extract_job"), + "jobReference": {"projectId": PROJECT, "jobId": "extract_job"}, + "state": "DONE", + "configuration": { + "extract": { + "sourceTable": { + "projectId": PROJECT, + "datasetId": DS_ID, + "tableId": SOURCE_TABLE, + }, + "destinationUris": [DESTINATION_URI], + } + }, + } + COPY_DATA = { + "id": "%s:%s" % (PROJECT, "copy_job"), + "jobReference": {"projectId": PROJECT, "jobId": "copy_job"}, + "state": "DONE", + "configuration": { + "copy": { + "sourceTables": [ + {"projectId": PROJECT, "datasetId": DS_ID, "tableId": SOURCE_TABLE} + ], + "destinationTable": { + "projectId": PROJECT, + "datasetId": DS_ID, + "tableId": DESTINATION_TABLE, + }, + } + }, + } + LOAD_DATA = { + "id": "%s:%s" % (PROJECT, "load_job"), + "jobReference": {"projectId": PROJECT, "jobId": "load_job"}, + "state": "DONE", + "configuration": { + "load": { + "destinationTable": { + "projectId": PROJECT, + "datasetId": DS_ID, + "tableId": SOURCE_TABLE, + }, + "sourceUris": [SOURCE_URI], + } + }, + } + DATA = { + "nextPageToken": TOKEN, + "jobs": [ASYNC_QUERY_DATA, EXTRACT_DATA, COPY_DATA, LOAD_DATA], + } + conn = client._connection = make_connection(DATA) + + iterator = client.list_jobs(**extra) + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) + jobs = list(page) + token = iterator.next_page_token + + assert len(jobs) == len(DATA["jobs"]) + for found, expected in zip(jobs, DATA["jobs"]): + name = expected["jobReference"]["jobId"] + assert isinstance(found, JOB_TYPES[name]) + assert found.job_id == name + assert token == TOKEN + + conn.api_request.assert_called_once_with( + method="GET", + path="/%s" % PATH, + query_params=dict({"projection": "full"}, **query), + timeout=DEFAULT_TIMEOUT, + ) + + +def test_list_jobs_load_job_wo_sourceUris(client, PROJECT, DS_ID): + from google.cloud.bigquery.job import LoadJob + + SOURCE_TABLE = "source_table" + JOB_TYPES = {"load_job": LoadJob} + PATH = "projects/%s/jobs" % PROJECT + TOKEN = "TOKEN" + LOAD_DATA = { + "id": "%s:%s" % (PROJECT, "load_job"), + "jobReference": {"projectId": PROJECT, "jobId": "load_job"}, + "state": "DONE", + "configuration": { + "load": { + "destinationTable": { + "projectId": PROJECT, + "datasetId": DS_ID, + "tableId": SOURCE_TABLE, + } + } + }, + } + DATA = {"nextPageToken": TOKEN, "jobs": [LOAD_DATA]} + conn = client._connection = make_connection(DATA) + + iterator = client.list_jobs() + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) + jobs = list(page) + token = iterator.next_page_token + + assert len(jobs) == len(DATA["jobs"]) + for found, expected in zip(jobs, DATA["jobs"]): + name = expected["jobReference"]["jobId"] + assert isinstance(found, JOB_TYPES[name]) + assert found.job_id == name + assert token == TOKEN + + conn.api_request.assert_called_once_with( + method="GET", + path="/%s" % PATH, + query_params={"projection": "full"}, + timeout=DEFAULT_TIMEOUT, + ) + + +def test_list_jobs_explicit_missing(client, PROJECT): + PATH = "projects/%s/jobs" % PROJECT + DATA = {} + TOKEN = "TOKEN" + conn = client._connection = make_connection(DATA) + + iterator = client.list_jobs( + max_results=1000, page_token=TOKEN, all_users=True, state_filter="done" + ) + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/%s" % PATH}, client, None) + jobs = list(page) + token = iterator.next_page_token + + assert len(jobs) == 0 + assert token is None + + conn.api_request.assert_called_once_with( + method="GET", + path="/%s" % PATH, + query_params={ + "projection": "full", + "maxResults": 1000, + "pageToken": TOKEN, + "allUsers": True, + "stateFilter": "done", + }, + timeout=DEFAULT_TIMEOUT, + ) + + +def test_list_jobs_w_project(client, PROJECT): + conn = client._connection = make_connection({}) + + list(client.list_jobs(project="other-project")) + + conn.api_request.assert_called_once_with( + method="GET", + path="/projects/other-project/jobs", + query_params={"projection": "full"}, + timeout=DEFAULT_TIMEOUT, + ) + + +def test_list_jobs_w_timeout(client, PROJECT): + conn = client._connection = make_connection({}) + + list(client.list_jobs(timeout=7.5)) + + conn.api_request.assert_called_once_with( + method="GET", + path="/projects/{}/jobs".format(PROJECT), + query_params={"projection": "full"}, + timeout=7.5, + ) + + +def test_list_jobs_w_time_filter(client, PROJECT): + conn = client._connection = make_connection({}) + + # One millisecond after the unix epoch. + start_time = datetime.datetime(1970, 1, 1, 0, 0, 0, 1000) + # One millisecond after the the 2038 31-bit signed int rollover + end_time = datetime.datetime(2038, 1, 19, 3, 14, 7, 1000) + end_time_millis = (((2 ** 31) - 1) * 1000) + 1 + + list(client.list_jobs(min_creation_time=start_time, max_creation_time=end_time)) + + conn.api_request.assert_called_once_with( + method="GET", + path="/projects/%s/jobs" % PROJECT, + query_params={ + "projection": "full", + "minCreationTime": "1", + "maxCreationTime": str(end_time_millis), + }, + timeout=DEFAULT_TIMEOUT, + ) + + +def test_list_jobs_w_parent_job_filter(client, PROJECT): + from google.cloud.bigquery import job + + conn = client._connection = make_connection({}, {}) + + parent_job_args = ["parent-job-123", job._AsyncJob("parent-job-123", client)] + + for parent_job in parent_job_args: + list(client.list_jobs(parent_job=parent_job)) + conn.api_request.assert_called_once_with( + method="GET", + path="/projects/%s/jobs" % PROJECT, + query_params={"projection": "full", "parentJobId": "parent-job-123"}, + timeout=DEFAULT_TIMEOUT, + ) + conn.api_request.reset_mock() diff --git a/tests/unit/test_list_models.py b/tests/unit/test_list_models.py index 56aa66126..b14852338 100644 --- a/tests/unit/test_list_models.py +++ b/tests/unit/test_list_models.py @@ -1,20 +1,22 @@ # Copyright 2021 Google LLC - +# # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at - +# # https://www.apache.org/licenses/LICENSE-2.0 - +# # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from .helpers import make_connection, dataset_polymorphic import pytest +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT +from .helpers import make_connection, dataset_polymorphic + def test_list_models_empty_w_timeout(client, PROJECT, DS_ID): path = "/projects/{}/datasets/{}/models".format(PROJECT, DS_ID) @@ -33,8 +35,13 @@ def test_list_models_empty_w_timeout(client, PROJECT, DS_ID): ) +@pytest.mark.parametrize( + "extra,query", [({}, {}), (dict(page_size=42), dict(maxResults=42))] +) @dataset_polymorphic -def test_list_models_defaults(make_dataset, get_reference, client, PROJECT, DS_ID): +def test_list_models_defaults( + make_dataset, get_reference, client, PROJECT, DS_ID, extra, query, +): from google.cloud.bigquery.model import Model MODEL_1 = "model_one" @@ -64,7 +71,7 @@ def test_list_models_defaults(make_dataset, get_reference, client, PROJECT, DS_I conn = client._connection = make_connection(DATA) dataset = make_dataset(PROJECT, DS_ID) - iterator = client.list_models(dataset) + iterator = client.list_models(dataset, **extra) assert iterator.dataset == get_reference(dataset) page = next(iterator.pages) models = list(page) @@ -77,7 +84,7 @@ def test_list_models_defaults(make_dataset, get_reference, client, PROJECT, DS_I assert token == TOKEN conn.api_request.assert_called_once_with( - method="GET", path="/%s" % PATH, query_params={}, timeout=None + method="GET", path="/%s" % PATH, query_params=query, timeout=DEFAULT_TIMEOUT ) diff --git a/tests/unit/test_list_projects.py b/tests/unit/test_list_projects.py new file mode 100644 index 000000000..190612b44 --- /dev/null +++ b/tests/unit/test_list_projects.py @@ -0,0 +1,120 @@ +# Copyright 2021 Google LLC +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# https://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +import mock +import pytest + +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT +from .helpers import make_connection + + +@pytest.mark.parametrize( + "extra,query", [({}, {}), (dict(page_size=42), dict(maxResults=42))] +) +def test_list_projects_defaults(client, PROJECT, extra, query): + from google.cloud.bigquery.client import Project + + PROJECT_2 = "PROJECT_TWO" + TOKEN = "TOKEN" + DATA = { + "nextPageToken": TOKEN, + "projects": [ + { + "kind": "bigquery#project", + "id": PROJECT, + "numericId": 1, + "projectReference": {"projectId": PROJECT}, + "friendlyName": "One", + }, + { + "kind": "bigquery#project", + "id": PROJECT_2, + "numericId": 2, + "projectReference": {"projectId": PROJECT_2}, + "friendlyName": "Two", + }, + ], + } + conn = client._connection = make_connection(DATA) + iterator = client.list_projects(**extra) + + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/projects"}, client, None) + projects = list(page) + token = iterator.next_page_token + + assert len(projects) == len(DATA["projects"]) + for found, expected in zip(projects, DATA["projects"]): + assert isinstance(found, Project) + assert found.project_id == expected["id"] + assert found.numeric_id == expected["numericId"] + assert found.friendly_name == expected["friendlyName"] + assert token == TOKEN + + conn.api_request.assert_called_once_with( + method="GET", path="/projects", query_params=query, timeout=DEFAULT_TIMEOUT + ) + + +def test_list_projects_w_timeout(client): + TOKEN = "TOKEN" + DATA = { + "nextPageToken": TOKEN, + "projects": [], + } + conn = client._connection = make_connection(DATA) + + iterator = client.list_projects(timeout=7.5) + + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/projects"}, client, None) + + conn.api_request.assert_called_once_with( + method="GET", path="/projects", query_params={}, timeout=7.5 + ) + + +def test_list_projects_explicit_response_missing_projects_key(client): + TOKEN = "TOKEN" + DATA = {} + conn = client._connection = make_connection(DATA) + + iterator = client.list_projects(max_results=3, page_token=TOKEN) + + with mock.patch( + "google.cloud.bigquery.opentelemetry_tracing._get_final_span_attributes" + ) as final_attributes: + page = next(iterator.pages) + + final_attributes.assert_called_once_with({"path": "/projects"}, client, None) + projects = list(page) + token = iterator.next_page_token + + assert len(projects) == 0 + assert token is None + + conn.api_request.assert_called_once_with( + method="GET", + path="/projects", + query_params={"maxResults": 3, "pageToken": TOKEN}, + timeout=DEFAULT_TIMEOUT, + ) diff --git a/tests/unit/test_list_routines.py b/tests/unit/test_list_routines.py index 714ede0d4..80e62d6bd 100644 --- a/tests/unit/test_list_routines.py +++ b/tests/unit/test_list_routines.py @@ -1,20 +1,22 @@ # Copyright 2021 Google LLC - +# # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at - +# # https://www.apache.org/licenses/LICENSE-2.0 - +# # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from .helpers import make_connection, dataset_polymorphic import pytest +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT +from .helpers import make_connection, dataset_polymorphic + def test_list_routines_empty_w_timeout(client): conn = client._connection = make_connection({}) @@ -34,8 +36,13 @@ def test_list_routines_empty_w_timeout(client): ) +@pytest.mark.parametrize( + "extra,query", [({}, {}), (dict(page_size=42), dict(maxResults=42))] +) @dataset_polymorphic -def test_list_routines_defaults(make_dataset, get_reference, client, PROJECT): +def test_list_routines_defaults( + make_dataset, get_reference, client, PROJECT, extra, query +): from google.cloud.bigquery.routine import Routine project_id = PROJECT @@ -67,7 +74,7 @@ def test_list_routines_defaults(make_dataset, get_reference, client, PROJECT): conn = client._connection = make_connection(resource) dataset = make_dataset(client.project, dataset_id) - iterator = client.list_routines(dataset) + iterator = client.list_routines(dataset, **extra) assert iterator.dataset == get_reference(dataset) page = next(iterator.pages) routines = list(page) @@ -80,7 +87,7 @@ def test_list_routines_defaults(make_dataset, get_reference, client, PROJECT): assert actual_token == token conn.api_request.assert_called_once_with( - method="GET", path=path, query_params={}, timeout=None + method="GET", path=path, query_params=query, timeout=DEFAULT_TIMEOUT ) diff --git a/tests/unit/test_list_tables.py b/tests/unit/test_list_tables.py index 9acee9580..8360f6605 100644 --- a/tests/unit/test_list_tables.py +++ b/tests/unit/test_list_tables.py @@ -1,21 +1,23 @@ # Copyright 2021 Google LLC - +# # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at - +# # https://www.apache.org/licenses/LICENSE-2.0 - +# # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -from .helpers import make_connection, dataset_polymorphic -import google.cloud.bigquery.dataset import pytest +import google.cloud.bigquery.dataset +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT +from .helpers import make_connection, dataset_polymorphic + @dataset_polymorphic def test_list_tables_empty_w_timeout( @@ -89,7 +91,7 @@ def test_list_tables_defaults(make_dataset, get_reference, client, PROJECT, DS_I assert token == TOKEN conn.api_request.assert_called_once_with( - method="GET", path="/%s" % PATH, query_params={}, timeout=None + method="GET", path="/%s" % PATH, query_params={}, timeout=DEFAULT_TIMEOUT ) @@ -150,10 +152,29 @@ def test_list_tables_explicit(client, PROJECT, DS_ID): method="GET", path="/%s" % PATH, query_params={"maxResults": 3, "pageToken": TOKEN}, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) def test_list_tables_wrong_type(client): with pytest.raises(TypeError): client.list_tables(42) + + +@dataset_polymorphic +def test_list_tables_page_size(make_dataset, get_reference, client, PROJECT, DS_ID): + path = "/projects/{}/datasets/{}/tables".format(PROJECT, DS_ID) + conn = client._connection = make_connection({}) + + dataset = make_dataset(PROJECT, DS_ID) + iterator = client.list_tables(dataset, timeout=7.5, page_size=42) + assert iterator.dataset == get_reference(dataset) + page = next(iterator.pages) + tables = list(page) + token = iterator.next_page_token + + assert tables == [] + assert token is None + conn.api_request.assert_called_once_with( + method="GET", path=path, query_params=dict(maxResults=42), timeout=7.5 + ) diff --git a/tests/unit/test_magics.py b/tests/unit/test_magics.py index ff41fe720..36cbf4993 100644 --- a/tests/unit/test_magics.py +++ b/tests/unit/test_magics.py @@ -32,6 +32,7 @@ from google.cloud.bigquery import job from google.cloud.bigquery import table from google.cloud.bigquery.magics import magics +from google.cloud.bigquery.retry import DEFAULT_TIMEOUT from tests.unit.helpers import make_connection from test_utils.imports import maybe_fail_import @@ -185,7 +186,7 @@ def test_context_with_default_connection(): method="POST", path="/projects/project-from-env/jobs", data=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) query_results_call = mock.call( method="GET", @@ -249,7 +250,7 @@ def test_context_with_custom_connection(): method="POST", path="/projects/project-from-env/jobs", data=mock.ANY, - timeout=None, + timeout=DEFAULT_TIMEOUT, ) query_results_call = mock.call( method="GET", @@ -317,7 +318,10 @@ def test__make_bqstorage_client_false(): credentials_mock = mock.create_autospec( google.auth.credentials.Credentials, instance=True ) - got = magics._make_bqstorage_client(False, credentials_mock, {}) + test_client = bigquery.Client( + project="test_project", credentials=credentials_mock, location="test_location" + ) + got = magics._make_bqstorage_client(test_client, False, {}) assert got is None @@ -328,7 +332,10 @@ def test__make_bqstorage_client_true(): credentials_mock = mock.create_autospec( google.auth.credentials.Credentials, instance=True ) - got = magics._make_bqstorage_client(True, credentials_mock, {}) + test_client = bigquery.Client( + project="test_project", credentials=credentials_mock, location="test_location" + ) + got = magics._make_bqstorage_client(test_client, True, {}) assert isinstance(got, bigquery_storage.BigQueryReadClient) @@ -336,15 +343,46 @@ def test__make_bqstorage_client_true_raises_import_error(missing_bq_storage): credentials_mock = mock.create_autospec( google.auth.credentials.Credentials, instance=True ) + test_client = bigquery.Client( + project="test_project", credentials=credentials_mock, location="test_location" + ) with pytest.raises(ImportError) as exc_context, missing_bq_storage: - magics._make_bqstorage_client(True, credentials_mock, {}) + magics._make_bqstorage_client(test_client, True, {}) error_msg = str(exc_context.value) assert "google-cloud-bigquery-storage" in error_msg assert "pyarrow" in error_msg +@pytest.mark.skipif( + bigquery_storage is None, reason="Requires `google-cloud-bigquery-storage`" +) +def test__make_bqstorage_client_true_obsolete_dependency(): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + credentials_mock = mock.create_autospec( + google.auth.credentials.Credentials, instance=True + ) + test_client = bigquery.Client( + project="test_project", credentials=credentials_mock, location="test_location" + ) + + patcher = mock.patch( + "google.cloud.bigquery.client.BQ_STORAGE_VERSIONS.verify_version", + side_effect=LegacyBigQueryStorageError("BQ Storage too old"), + ) + with patcher, warnings.catch_warnings(record=True) as warned: + got = magics._make_bqstorage_client(test_client, True, {}) + + assert got is None + + matching_warnings = [ + warning for warning in warned if "BQ Storage too old" in str(warning) + ] + assert matching_warnings, "Obsolete dependency warning not raised." + + @pytest.mark.skipif( bigquery_storage is None, reason="Requires `google-cloud-bigquery-storage`" ) @@ -623,7 +661,9 @@ def warning_match(warning): assert client_info.user_agent == "ipython-" + IPython.__version__ query_job_mock.to_dataframe.assert_called_once_with( - bqstorage_client=bqstorage_instance_mock, progress_bar_type="tqdm" + bqstorage_client=bqstorage_instance_mock, + create_bqstorage_client=mock.ANY, + progress_bar_type="tqdm", ) assert isinstance(return_value, pandas.DataFrame) @@ -666,7 +706,9 @@ def test_bigquery_magic_with_rest_client_requested(monkeypatch): bqstorage_mock.assert_not_called() query_job_mock.to_dataframe.assert_called_once_with( - bqstorage_client=None, progress_bar_type="tqdm" + bqstorage_client=None, + create_bqstorage_client=False, + progress_bar_type="tqdm", ) assert isinstance(return_value, pandas.DataFrame) @@ -720,7 +762,12 @@ def test_bigquery_magic_w_max_results_valid_calls_queryjob_result(): client_query_mock.return_value = query_job_mock ip.run_cell_magic("bigquery", "--max_results=5", sql) - query_job_mock.result.assert_called_with(max_results=5) + query_job_mock.result.assert_called_with(max_results=5) + query_job_mock.result.return_value.to_dataframe.assert_called_once_with( + bqstorage_client=None, + create_bqstorage_client=False, + progress_bar_type=mock.ANY, + ) @pytest.mark.usefixtures("ipython_interactive") @@ -887,11 +934,12 @@ def test_bigquery_magic_w_table_id_and_bqstorage_client(): table_id = "bigquery-public-data.samples.shakespeare" with default_patch, client_patch as client_mock, bqstorage_client_patch: + client_mock()._ensure_bqstorage_client.return_value = bqstorage_instance_mock client_mock().list_rows.return_value = row_iterator_mock ip.run_cell_magic("bigquery", "--max_results=5", table_id) row_iterator_mock.to_dataframe.assert_called_once_with( - bqstorage_client=bqstorage_instance_mock + bqstorage_client=bqstorage_instance_mock, create_bqstorage_client=mock.ANY, ) @@ -1208,7 +1256,9 @@ def test_bigquery_magic_w_progress_bar_type_w_context_setter(monkeypatch): bqstorage_mock.assert_not_called() query_job_mock.to_dataframe.assert_called_once_with( - bqstorage_client=None, progress_bar_type=magics.context.progress_bar_type + bqstorage_client=None, + create_bqstorage_client=False, + progress_bar_type=magics.context.progress_bar_type, ) assert isinstance(return_value, pandas.DataFrame) diff --git a/tests/unit/test_query.py b/tests/unit/test_query.py index 90fc30b20..69a6772e5 100644 --- a/tests/unit/test_query.py +++ b/tests/unit/test_query.py @@ -13,6 +13,7 @@ # limitations under the License. import datetime +import decimal import unittest import mock @@ -430,6 +431,18 @@ def test_positional(self): self.assertEqual(param.type_, "INT64") self.assertEqual(param.value, 123) + def test_ctor_w_scalar_query_parameter_type(self): + from google.cloud.bigquery import enums + + param = self._make_one( + name="foo", + type_=enums.SqlParameterScalarTypes.BIGNUMERIC, + value=decimal.Decimal("123.456"), + ) + self.assertEqual(param.name, "foo") + self.assertEqual(param.type_, "BIGNUMERIC") + self.assertEqual(param.value, decimal.Decimal("123.456")) + def test_from_api_repr_w_name(self): RESOURCE = { "name": "foo", @@ -1302,7 +1315,7 @@ def _verifySchema(self, query, resource): self.assertEqual(found.description, expected.get("description")) self.assertEqual(found.fields, expected.get("fields", ())) else: - self.assertEqual(query.schema, ()) + self.assertEqual(query.schema, []) def test_ctor_defaults(self): query = self._make_one(self._make_resource()) @@ -1312,7 +1325,7 @@ def test_ctor_defaults(self): self.assertIsNone(query.page_token) self.assertEqual(query.project, self.PROJECT) self.assertEqual(query.rows, []) - self.assertEqual(query.schema, ()) + self.assertEqual(query.schema, []) self.assertIsNone(query.total_rows) self.assertIsNone(query.total_bytes_processed) diff --git a/tests/unit/test_retry.py b/tests/unit/test_retry.py index 0bef1e5e1..e0a992f78 100644 --- a/tests/unit/test_retry.py +++ b/tests/unit/test_retry.py @@ -51,6 +51,22 @@ def test_w_unstructured_requests_connectionerror(self): exc = requests.exceptions.ConnectionError() self.assertTrue(self._call_fut(exc)) + def test_w_unstructured_requests_chunked_encoding_error(self): + exc = requests.exceptions.ChunkedEncodingError() + self.assertTrue(self._call_fut(exc)) + + def test_w_unstructured_requests_connecttimeout(self): + exc = requests.exceptions.ConnectTimeout() + self.assertTrue(self._call_fut(exc)) + + def test_w_unstructured_requests_readtimeout(self): + exc = requests.exceptions.ReadTimeout() + self.assertTrue(self._call_fut(exc)) + + def test_w_unstructured_requests_timeout(self): + exc = requests.exceptions.Timeout() + self.assertTrue(self._call_fut(exc)) + def test_w_auth_transporterror(self): from google.auth.exceptions import TransportError @@ -82,3 +98,27 @@ def test_w_unstructured_bad_gateway(self): exc = BadGateway("testing") self.assertTrue(self._call_fut(exc)) + + +def test_DEFAULT_JOB_RETRY_predicate(): + from google.cloud.bigquery.retry import DEFAULT_JOB_RETRY + from google.api_core.exceptions import ClientError + + assert not DEFAULT_JOB_RETRY._predicate(TypeError()) + assert not DEFAULT_JOB_RETRY._predicate(ClientError("fail")) + assert not DEFAULT_JOB_RETRY._predicate( + ClientError("fail", errors=[dict(reason="idk")]) + ) + + assert DEFAULT_JOB_RETRY._predicate( + ClientError("fail", errors=[dict(reason="rateLimitExceeded")]) + ) + assert DEFAULT_JOB_RETRY._predicate( + ClientError("fail", errors=[dict(reason="backendError")]) + ) + + +def test_DEFAULT_JOB_RETRY_deadline(): + from google.cloud.bigquery.retry import DEFAULT_JOB_RETRY + + assert DEFAULT_JOB_RETRY._deadline == 600 diff --git a/tests/unit/test_schema.py b/tests/unit/test_schema.py index 87baaf379..d0b5ca54c 100644 --- a/tests/unit/test_schema.py +++ b/tests/unit/test_schema.py @@ -12,9 +12,11 @@ # See the License for the specific language governing permissions and # limitations under the License. +from google.cloud.bigquery.schema import PolicyTagList import unittest import mock +import pytest class TestSchemaField(unittest.TestCase): @@ -40,6 +42,7 @@ def test_constructor_defaults(self): self.assertEqual(field.mode, "NULLABLE") self.assertIsNone(field.description) self.assertEqual(field.fields, ()) + self.assertEqual(field.policy_tags, PolicyTagList()) def test_constructor_explicit(self): field = self._make_one("test", "STRING", mode="REQUIRED", description="Testing") @@ -103,7 +106,14 @@ def test_to_api_repr_with_subfield(self): self.assertEqual( field.to_api_repr(), { - "fields": [{"mode": "NULLABLE", "name": "bar", "type": "INTEGER"}], + "fields": [ + { + "mode": "NULLABLE", + "name": "bar", + "type": "INTEGER", + "policyTags": {"names": []}, + } + ], "mode": "REQUIRED", "name": "foo", "type": record_type, @@ -403,6 +413,23 @@ def test___eq___hit_w_fields(self): other = self._make_one("test", "RECORD", fields=[sub1, sub2]) self.assertEqual(field, other) + def test___eq___hit_w_policy_tags(self): + field = self._make_one( + "test", + "STRING", + mode="REQUIRED", + description="Testing", + policy_tags=PolicyTagList(names=["foo", "bar"]), + ) + other = self._make_one( + "test", + "STRING", + mode="REQUIRED", + description="Testing", + policy_tags=PolicyTagList(names=["bar", "foo"]), + ) + self.assertEqual(field, other) # Policy tags order does not matter. + def test___ne___wrong_type(self): field = self._make_one("toast", "INTEGER") other = object() @@ -425,6 +452,23 @@ def test___ne___different_values(self): ) self.assertNotEqual(field1, field2) + def test___ne___different_policy_tags(self): + field = self._make_one( + "test", + "STRING", + mode="REQUIRED", + description="Testing", + policy_tags=PolicyTagList(names=["foo", "bar"]), + ) + other = self._make_one( + "test", + "STRING", + mode="REQUIRED", + description="Testing", + policy_tags=PolicyTagList(names=["foo", "baz"]), + ) + self.assertNotEqual(field, other) + def test___hash__set_equality(self): sub1 = self._make_one("sub1", "STRING") sub2 = self._make_one("sub2", "STRING") @@ -445,7 +489,7 @@ def test___hash__not_equals(self): def test___repr__(self): field1 = self._make_one("field1", "STRING") - expected = "SchemaField('field1', 'STRING', 'NULLABLE', None, (), None)" + expected = "SchemaField('field1', 'STRING', 'NULLABLE', None, (), ())" self.assertEqual(repr(field1), expected) @@ -523,10 +567,22 @@ def test_defaults(self): resource = self._call_fut([full_name, age]) self.assertEqual(len(resource), 2) self.assertEqual( - resource[0], {"name": "full_name", "type": "STRING", "mode": "REQUIRED"}, + resource[0], + { + "name": "full_name", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, ) self.assertEqual( - resource[1], {"name": "age", "type": "INTEGER", "mode": "REQUIRED"} + resource[1], + { + "name": "age", + "type": "INTEGER", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, ) def test_w_description(self): @@ -552,11 +608,18 @@ def test_w_description(self): "type": "STRING", "mode": "REQUIRED", "description": DESCRIPTION, + "policyTags": {"names": []}, }, ) self.assertEqual( resource[1], - {"name": "age", "type": "INTEGER", "mode": "REQUIRED", "description": None}, + { + "name": "age", + "type": "INTEGER", + "mode": "REQUIRED", + "description": None, + "policyTags": {"names": []}, + }, ) def test_w_subfields(self): @@ -571,7 +634,13 @@ def test_w_subfields(self): resource = self._call_fut([full_name, phone]) self.assertEqual(len(resource), 2) self.assertEqual( - resource[0], {"name": "full_name", "type": "STRING", "mode": "REQUIRED"}, + resource[0], + { + "name": "full_name", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, ) self.assertEqual( resource[1], @@ -580,8 +649,18 @@ def test_w_subfields(self): "type": "RECORD", "mode": "REPEATED", "fields": [ - {"name": "type", "type": "STRING", "mode": "REQUIRED"}, - {"name": "number", "type": "STRING", "mode": "REQUIRED"}, + { + "name": "type", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, + { + "name": "number", + "type": "STRING", + "mode": "REQUIRED", + "policyTags": {"names": []}, + }, ], }, ) @@ -715,3 +794,165 @@ def test___hash__not_equals(self): set_one = {policy1} set_two = {policy2} self.assertNotEqual(set_one, set_two) + + +@pytest.mark.parametrize( + "api,expect,key2", + [ + ( + dict(name="n", type="NUMERIC"), + ("n", "NUMERIC", None, None, None), + ("n", "NUMERIC"), + ), + ( + dict(name="n", type="NUMERIC", precision=9), + ("n", "NUMERIC", 9, None, None), + ("n", "NUMERIC(9)"), + ), + ( + dict(name="n", type="NUMERIC", precision=9, scale=2), + ("n", "NUMERIC", 9, 2, None), + ("n", "NUMERIC(9, 2)"), + ), + ( + dict(name="n", type="BIGNUMERIC"), + ("n", "BIGNUMERIC", None, None, None), + ("n", "BIGNUMERIC"), + ), + ( + dict(name="n", type="BIGNUMERIC", precision=40), + ("n", "BIGNUMERIC", 40, None, None), + ("n", "BIGNUMERIC(40)"), + ), + ( + dict(name="n", type="BIGNUMERIC", precision=40, scale=2), + ("n", "BIGNUMERIC", 40, 2, None), + ("n", "BIGNUMERIC(40, 2)"), + ), + ( + dict(name="n", type="STRING"), + ("n", "STRING", None, None, None), + ("n", "STRING"), + ), + ( + dict(name="n", type="STRING", maxLength=9), + ("n", "STRING", None, None, 9), + ("n", "STRING(9)"), + ), + ( + dict(name="n", type="BYTES"), + ("n", "BYTES", None, None, None), + ("n", "BYTES"), + ), + ( + dict(name="n", type="BYTES", maxLength=9), + ("n", "BYTES", None, None, 9), + ("n", "BYTES(9)"), + ), + ], +) +def test_from_api_repr_parameterized(api, expect, key2): + from google.cloud.bigquery.schema import SchemaField + + field = SchemaField.from_api_repr(api) + + assert ( + field.name, + field.field_type, + field.precision, + field.scale, + field.max_length, + ) == expect + + assert field._key()[:2] == key2 + + +@pytest.mark.parametrize( + "field,api", + [ + ( + dict(name="n", field_type="NUMERIC"), + dict(name="n", type="NUMERIC", mode="NULLABLE", policyTags={"names": []}), + ), + ( + dict(name="n", field_type="NUMERIC", precision=9), + dict( + name="n", + type="NUMERIC", + mode="NULLABLE", + precision=9, + policyTags={"names": []}, + ), + ), + ( + dict(name="n", field_type="NUMERIC", precision=9, scale=2), + dict( + name="n", + type="NUMERIC", + mode="NULLABLE", + precision=9, + scale=2, + policyTags={"names": []}, + ), + ), + ( + dict(name="n", field_type="BIGNUMERIC"), + dict( + name="n", type="BIGNUMERIC", mode="NULLABLE", policyTags={"names": []} + ), + ), + ( + dict(name="n", field_type="BIGNUMERIC", precision=40), + dict( + name="n", + type="BIGNUMERIC", + mode="NULLABLE", + precision=40, + policyTags={"names": []}, + ), + ), + ( + dict(name="n", field_type="BIGNUMERIC", precision=40, scale=2), + dict( + name="n", + type="BIGNUMERIC", + mode="NULLABLE", + precision=40, + scale=2, + policyTags={"names": []}, + ), + ), + ( + dict(name="n", field_type="STRING"), + dict(name="n", type="STRING", mode="NULLABLE", policyTags={"names": []}), + ), + ( + dict(name="n", field_type="STRING", max_length=9), + dict( + name="n", + type="STRING", + mode="NULLABLE", + maxLength=9, + policyTags={"names": []}, + ), + ), + ( + dict(name="n", field_type="BYTES"), + dict(name="n", type="BYTES", mode="NULLABLE", policyTags={"names": []}), + ), + ( + dict(name="n", field_type="BYTES", max_length=9), + dict( + name="n", + type="BYTES", + mode="NULLABLE", + maxLength=9, + policyTags={"names": []}, + ), + ), + ], +) +def test_to_api_repr_parameterized(field, api): + from google.cloud.bigquery.schema import SchemaField + + assert SchemaField(**field).to_api_repr() == api diff --git a/tests/unit/test_signature_compatibility.py b/tests/unit/test_signature_compatibility.py index e5016b0e5..07b823e2c 100644 --- a/tests/unit/test_signature_compatibility.py +++ b/tests/unit/test_signature_compatibility.py @@ -12,6 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. +from collections import OrderedDict import inspect import pytest @@ -32,12 +33,30 @@ def row_iterator_class(): def test_to_arrow_method_signatures_match(query_job_class, row_iterator_class): - sig = inspect.signature(query_job_class.to_arrow) - sig2 = inspect.signature(row_iterator_class.to_arrow) - assert sig == sig2 + query_job_sig = inspect.signature(query_job_class.to_arrow) + iterator_sig = inspect.signature(row_iterator_class.to_arrow) + + assert "max_results" in query_job_sig.parameters + + # Compare the signatures while ignoring the max_results parameter, which is + # specific to the method on QueryJob. + params = OrderedDict(query_job_sig.parameters) + del params["max_results"] + query_job_sig = query_job_sig.replace(parameters=params.values()) + + assert query_job_sig == iterator_sig def test_to_dataframe_method_signatures_match(query_job_class, row_iterator_class): - sig = inspect.signature(query_job_class.to_dataframe) - sig2 = inspect.signature(row_iterator_class.to_dataframe) - assert sig == sig2 + query_job_sig = inspect.signature(query_job_class.to_dataframe) + iterator_sig = inspect.signature(row_iterator_class.to_dataframe) + + assert "max_results" in query_job_sig.parameters + + # Compare the signatures while ignoring the max_results parameter, which is + # specific to the method on QueryJob. + params = OrderedDict(query_job_sig.parameters) + del params["max_results"] + query_job_sig = query_job_sig.replace(parameters=params.values()) + + assert query_job_sig == iterator_sig diff --git a/tests/unit/test_table.py b/tests/unit/test_table.py index ce4a15761..1ce930ee4 100644 --- a/tests/unit/test_table.py +++ b/tests/unit/test_table.py @@ -14,16 +14,17 @@ import datetime import logging +import re import time +import types import unittest import warnings import mock -import pkg_resources import pytest -import pytz import google.api_core.exceptions +from test_utils.imports import maybe_fail_import try: from google.cloud import bigquery_storage @@ -39,14 +40,16 @@ except (ImportError, AttributeError): # pragma: NO COVER pandas = None +try: + import geopandas +except (ImportError, AttributeError): # pragma: NO COVER + geopandas = None + try: import pyarrow import pyarrow.types - - PYARROW_VERSION = pkg_resources.parse_version(pyarrow.__version__) except ImportError: # pragma: NO COVER pyarrow = None - PYARROW_VERSION = pkg_resources.parse_version("0.0.1") try: from tqdm import tqdm @@ -56,9 +59,6 @@ from google.cloud.bigquery.dataset import DatasetReference -PYARROW_TIMESTAMP_VERSION = pkg_resources.parse_version("2.0.0") - - def _mock_client(): from google.cloud.bigquery import client @@ -113,8 +113,6 @@ def _make_one(self, *args, **kw): return self._get_target_class()(*args, **kw) def test_ctor_defaults(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset_ref = DatasetReference("project_1", "dataset_1") table_ref = self._make_one(dataset_ref, "table_1") @@ -122,8 +120,6 @@ def test_ctor_defaults(self): self.assertEqual(table_ref.table_id, "table_1") def test_to_api_repr(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset_ref = DatasetReference("project_1", "dataset_1") table_ref = self._make_one(dataset_ref, "table_1") @@ -135,7 +131,6 @@ def test_to_api_repr(self): ) def test_from_api_repr(self): - from google.cloud.bigquery.dataset import DatasetReference from google.cloud.bigquery.table import TableReference dataset_ref = DatasetReference("project_1", "dataset_1") @@ -202,8 +197,6 @@ def test_from_string_ignores_default_project(self): self.assertEqual(got.table_id, "string_table") def test___eq___wrong_type(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset_ref = DatasetReference("project_1", "dataset_1") table = self._make_one(dataset_ref, "table_1") other = object() @@ -211,8 +204,6 @@ def test___eq___wrong_type(self): self.assertEqual(table, mock.ANY) def test___eq___project_mismatch(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset = DatasetReference("project_1", "dataset_1") other_dataset = DatasetReference("project_2", "dataset_1") table = self._make_one(dataset, "table_1") @@ -220,8 +211,6 @@ def test___eq___project_mismatch(self): self.assertNotEqual(table, other) def test___eq___dataset_mismatch(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset = DatasetReference("project_1", "dataset_1") other_dataset = DatasetReference("project_1", "dataset_2") table = self._make_one(dataset, "table_1") @@ -229,24 +218,18 @@ def test___eq___dataset_mismatch(self): self.assertNotEqual(table, other) def test___eq___table_mismatch(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset = DatasetReference("project_1", "dataset_1") table = self._make_one(dataset, "table_1") other = self._make_one(dataset, "table_2") self.assertNotEqual(table, other) def test___eq___equality(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset = DatasetReference("project_1", "dataset_1") table = self._make_one(dataset, "table_1") other = self._make_one(dataset, "table_1") self.assertEqual(table, other) def test___hash__set_equality(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset = DatasetReference("project_1", "dataset_1") table1 = self._make_one(dataset, "table1") table2 = self._make_one(dataset, "table2") @@ -255,8 +238,6 @@ def test___hash__set_equality(self): self.assertEqual(set_one, set_two) def test___hash__not_equals(self): - from google.cloud.bigquery.dataset import DatasetReference - dataset = DatasetReference("project_1", "dataset_1") table1 = self._make_one(dataset, "table1") table2 = self._make_one(dataset, "table2") @@ -292,8 +273,6 @@ def _get_target_class(): return Table def _make_one(self, *args, **kw): - from google.cloud.bigquery.dataset import DatasetReference - if len(args) == 0: dataset = DatasetReference(self.PROJECT, self.DS_ID) table_ref = dataset.table(self.TABLE_NAME) @@ -579,6 +558,68 @@ def test_num_rows_getter(self): with self.assertRaises(ValueError): getattr(table, "num_rows") + def test__eq__wrong_type(self): + table = self._make_one("project_foo.dataset_bar.table_baz") + + class TableWannabe: + pass + + not_a_table = TableWannabe() + not_a_table._properties = table._properties + + assert table != not_a_table # Can't fake it. + + def test__eq__same_table_basic(self): + table_1 = self._make_one("project_foo.dataset_bar.table_baz") + table_2 = self._make_one("project_foo.dataset_bar.table_baz") + assert table_1 == table_2 + + def test__eq__same_table_multiple_properties(self): + from google.cloud.bigquery import SchemaField + + table_1 = self._make_one("project_foo.dataset_bar.table_baz") + table_1.require_partition_filter = True + table_1.labels = {"first": "one", "second": "two"} + + table_1.schema = [ + SchemaField("name", "STRING", "REQUIRED"), + SchemaField("age", "INTEGER", "NULLABLE"), + ] + + table_2 = self._make_one("project_foo.dataset_bar.table_baz") + table_2.require_partition_filter = True + table_2.labels = {"first": "one", "second": "two"} + table_2.schema = [ + SchemaField("name", "STRING", "REQUIRED"), + SchemaField("age", "INTEGER", "NULLABLE"), + ] + + assert table_1 == table_2 + + def test__eq__same_table_property_different(self): + table_1 = self._make_one("project_foo.dataset_bar.table_baz") + table_1.description = "This is table baz" + + table_2 = self._make_one("project_foo.dataset_bar.table_baz") + table_2.description = "This is also table baz" + + assert table_1 == table_2 # Still equal, only table reference is important. + + def test__eq__different_table(self): + table_1 = self._make_one("project_foo.dataset_bar.table_baz") + table_2 = self._make_one("project_foo.dataset_bar.table_baz_2") + + assert table_1 != table_2 + + def test_hashable(self): + table_1 = self._make_one("project_foo.dataset_bar.table_baz") + table_1.description = "This is a table" + + table_1b = self._make_one("project_foo.dataset_bar.table_baz") + table_1b.description = "Metadata is irrelevant for hashes" + + assert hash(table_1) == hash(table_1b) + def test_schema_setter_non_sequence(self): dataset = DatasetReference(self.PROJECT, self.DS_ID) table_ref = dataset.table(self.TABLE_NAME) @@ -683,6 +724,40 @@ def test_props_set_by_server(self): self.assertEqual(table.full_table_id, TABLE_FULL_ID) self.assertEqual(table.table_type, "TABLE") + def test_snapshot_definition_not_set(self): + dataset = DatasetReference(self.PROJECT, self.DS_ID) + table_ref = dataset.table(self.TABLE_NAME) + table = self._make_one(table_ref) + + assert table.snapshot_definition is None + + def test_snapshot_definition_set(self): + from google.cloud._helpers import UTC + from google.cloud.bigquery.table import SnapshotDefinition + + dataset = DatasetReference(self.PROJECT, self.DS_ID) + table_ref = dataset.table(self.TABLE_NAME) + table = self._make_one(table_ref) + + table._properties["snapshotDefinition"] = { + "baseTableReference": { + "projectId": "project_x", + "datasetId": "dataset_y", + "tableId": "table_z", + }, + "snapshotTime": "2010-09-28T10:20:30.123Z", + } + + snapshot = table.snapshot_definition + + assert isinstance(snapshot, SnapshotDefinition) + assert snapshot.base_table_reference.path == ( + "/projects/project_x/datasets/dataset_y/tables/table_z" + ) + assert snapshot.snapshot_time == datetime.datetime( + 2010, 9, 28, 10, 20, 30, 123000, tzinfo=UTC + ) + def test_description_setter_bad_value(self): dataset = DatasetReference(self.PROJECT, self.DS_ID) table_ref = dataset.table(self.TABLE_NAME) @@ -837,7 +912,9 @@ def test_mview_last_refresh_time(self): } self.assertEqual( table.mview_last_refresh_time, - datetime.datetime(2020, 11, 30, 15, 57, 22, 496000, tzinfo=pytz.utc), + datetime.datetime( + 2020, 11, 30, 15, 57, 22, 496000, tzinfo=datetime.timezone.utc + ), ) def test_mview_enable_refresh(self): @@ -1507,6 +1584,188 @@ def test_to_api_repr(self): table = self._make_one(resource) self.assertEqual(table.to_api_repr(), resource) + def test__eq__wrong_type(self): + resource = { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + } + table = self._make_one(resource) + + class FakeTableListItem: + project = "project_foo" + dataset_id = "dataset_bar" + table_id = "table_baz" + + not_a_table = FakeTableListItem() + + assert table != not_a_table # Can't fake it. + + def test__eq__same_table(self): + resource = { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + } + table_1 = self._make_one(resource) + table_2 = self._make_one(resource) + + assert table_1 == table_2 + + def test__eq__same_table_property_different(self): + table_ref_resource = { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + + resource_1 = {"tableReference": table_ref_resource, "friendlyName": "Table One"} + table_1 = self._make_one(resource_1) + + resource_2 = {"tableReference": table_ref_resource, "friendlyName": "Table Two"} + table_2 = self._make_one(resource_2) + + assert table_1 == table_2 # Still equal, only table reference is important. + + def test__eq__different_table(self): + resource_1 = { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + } + table_1 = self._make_one(resource_1) + + resource_2 = { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_quux", + } + } + table_2 = self._make_one(resource_2) + + assert table_1 != table_2 + + def test_hashable(self): + resource = { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + } + table_item = self._make_one(resource) + table_item_2 = self._make_one(resource) + + assert hash(table_item) == hash(table_item_2) + + +class TestTableClassesInterchangeability: + @staticmethod + def _make_table(*args, **kwargs): + from google.cloud.bigquery.table import Table + + return Table(*args, **kwargs) + + @staticmethod + def _make_table_ref(*args, **kwargs): + from google.cloud.bigquery.table import TableReference + + return TableReference(*args, **kwargs) + + @staticmethod + def _make_table_list_item(*args, **kwargs): + from google.cloud.bigquery.table import TableListItem + + return TableListItem(*args, **kwargs) + + def test_table_eq_table_ref(self): + + table = self._make_table("project_foo.dataset_bar.table_baz") + dataset_ref = DatasetReference("project_foo", "dataset_bar") + table_ref = self._make_table_ref(dataset_ref, "table_baz") + + assert table == table_ref + assert table_ref == table + + def test_table_eq_table_list_item(self): + table = self._make_table("project_foo.dataset_bar.table_baz") + table_list_item = self._make_table_list_item( + { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + } + ) + + assert table == table_list_item + assert table_list_item == table + + def test_table_ref_eq_table_list_item(self): + + dataset_ref = DatasetReference("project_foo", "dataset_bar") + table_ref = self._make_table_ref(dataset_ref, "table_baz") + table_list_item = self._make_table_list_item( + { + "tableReference": { + "projectId": "project_foo", + "datasetId": "dataset_bar", + "tableId": "table_baz", + } + } + ) + + assert table_ref == table_list_item + assert table_list_item == table_ref + + +class TestSnapshotDefinition: + @staticmethod + def _get_target_class(): + from google.cloud.bigquery.table import SnapshotDefinition + + return SnapshotDefinition + + @classmethod + def _make_one(cls, *args, **kwargs): + klass = cls._get_target_class() + return klass(*args, **kwargs) + + def test_ctor_empty_resource(self): + instance = self._make_one(resource={}) + assert instance.base_table_reference is None + assert instance.snapshot_time is None + + def test_ctor_full_resource(self): + from google.cloud._helpers import UTC + from google.cloud.bigquery.table import TableReference + + resource = { + "baseTableReference": { + "projectId": "my-project", + "datasetId": "your-dataset", + "tableId": "our-table", + }, + "snapshotTime": "2005-06-07T19:35:02.123Z", + } + instance = self._make_one(resource) + + expected_table_ref = TableReference.from_string( + "my-project.your-dataset.our-table" + ) + assert instance.base_table_reference == expected_table_ref + + expected_time = datetime.datetime(2005, 6, 7, 19, 35, 2, 123000, tzinfo=UTC) + assert instance.snapshot_time == expected_time + class TestRow(unittest.TestCase): def test_row(self): @@ -1570,6 +1829,46 @@ def test_to_dataframe(self): self.assertIsInstance(df, pandas.DataFrame) self.assertEqual(len(df), 0) # verify the number of rows + @mock.patch("google.cloud.bigquery.table.pandas", new=None) + def test_to_dataframe_iterable_error_if_pandas_is_none(self): + row_iterator = self._make_one() + with self.assertRaises(ValueError): + row_iterator.to_dataframe_iterable() + + @unittest.skipIf(pandas is None, "Requires `pandas`") + def test_to_dataframe_iterable(self): + row_iterator = self._make_one() + df_iter = row_iterator.to_dataframe_iterable() + + result = list(df_iter) + + self.assertEqual(len(result), 1) + df = result[0] + self.assertIsInstance(df, pandas.DataFrame) + self.assertEqual(len(df), 0) # Verify the number of rows. + self.assertEqual(len(df.columns), 0) + + @mock.patch("google.cloud.bigquery.table.geopandas", new=None) + def test_to_geodataframe_if_geopandas_is_none(self): + row_iterator = self._make_one() + with self.assertRaisesRegex( + ValueError, + re.escape( + "The geopandas library is not installed, please install " + "geopandas to use the to_geodataframe() function." + ), + ): + row_iterator.to_geodataframe(create_bqstorage_client=False) + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_geodataframe(self): + row_iterator = self._make_one() + df = row_iterator.to_geodataframe(create_bqstorage_client=False) + self.assertIsInstance(df, geopandas.GeoDataFrame) + self.assertEqual(len(df), 0) # verify the number of rows + self.assertEqual(df.crs.srs, "EPSG:4326") + self.assertEqual(df.crs.name, "WGS 84") + class TestRowIterator(unittest.TestCase): def _class_under_test(self): @@ -1607,6 +1906,16 @@ def _make_one( client, api_request, path, schema, table=table, **kwargs ) + def _make_one_from_data(self, schema=(), rows=()): + from google.cloud.bigquery.schema import SchemaField + + schema = [SchemaField(*a) for a in schema] + rows = [{"f": [{"v": v} for v in row]} for row in rows] + + path = "/foo" + api_request = mock.Mock(return_value={"rows": rows}) + return self._make_one(_mock_client(), api_request, path, schema) + def test_constructor(self): from google.cloud.bigquery.table import _item_to_row from google.cloud.bigquery.table import _rows_page_start @@ -1768,6 +2077,57 @@ def test__validate_bqstorage_returns_false_when_completely_cached(self): ) ) + def test__validate_bqstorage_returns_false_if_max_results_set(self): + iterator = self._make_one( + max_results=10, first_page_response=None # not cached + ) + result = iterator._validate_bqstorage( + bqstorage_client=None, create_bqstorage_client=True + ) + self.assertFalse(result) + + def test__validate_bqstorage_returns_false_if_missing_dependency(self): + iterator = self._make_one(first_page_response=None) # not cached + + def fail_bqstorage_import(name, globals, locals, fromlist, level): + # NOTE: *very* simplified, assuming a straightforward absolute import + return "bigquery_storage" in name or ( + fromlist is not None and "bigquery_storage" in fromlist + ) + + no_bqstorage = maybe_fail_import(predicate=fail_bqstorage_import) + + with no_bqstorage: + result = iterator._validate_bqstorage( + bqstorage_client=None, create_bqstorage_client=True + ) + + self.assertFalse(result) + + @unittest.skipIf( + bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" + ) + def test__validate_bqstorage_returns_false_w_warning_if_obsolete_version(self): + from google.cloud.bigquery.exceptions import LegacyBigQueryStorageError + + iterator = self._make_one(first_page_response=None) # not cached + + patcher = mock.patch( + "google.cloud.bigquery.table._helpers.BQ_STORAGE_VERSIONS.verify_version", + side_effect=LegacyBigQueryStorageError("BQ Storage too old"), + ) + with patcher, warnings.catch_warnings(record=True) as warned: + result = iterator._validate_bqstorage( + bqstorage_client=None, create_bqstorage_client=True + ) + + self.assertFalse(result) + + matching_warnings = [ + warning for warning in warned if "BQ Storage too old" in str(warning) + ] + assert matching_warnings, "Obsolete dependency warning not raised." + @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") def test_to_arrow(self): from google.cloud.bigquery.schema import SchemaField @@ -1969,7 +2329,7 @@ def test_to_arrow_w_empty_table(self): @unittest.skipIf( bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" ) - def test_to_arrow_max_results_w_create_bqstorage_warning(self): + def test_to_arrow_max_results_w_explicit_bqstorage_client_warning(self): from google.cloud.bigquery.schema import SchemaField schema = [ @@ -1983,6 +2343,7 @@ def test_to_arrow_max_results_w_create_bqstorage_warning(self): path = "/foo" api_request = mock.Mock(return_value={"rows": rows}) mock_client = _mock_client() + mock_bqstorage_client = mock.sentinel.bq_storage_client row_iterator = self._make_one( client=mock_client, @@ -1993,7 +2354,7 @@ def test_to_arrow_max_results_w_create_bqstorage_warning(self): ) with warnings.catch_warnings(record=True) as warned: - row_iterator.to_arrow(create_bqstorage_client=True) + row_iterator.to_arrow(bqstorage_client=mock_bqstorage_client) matches = [ warning @@ -2003,7 +2364,50 @@ def test_to_arrow_max_results_w_create_bqstorage_warning(self): and "REST" in str(warning) ] self.assertEqual(len(matches), 1, msg="User warning was not emitted.") - mock_client._create_bqstorage_client.assert_not_called() + self.assertIn( + __file__, str(matches[0]), msg="Warning emitted with incorrect stacklevel" + ) + mock_client._ensure_bqstorage_client.assert_not_called() + + @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") + @unittest.skipIf( + bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" + ) + def test_to_arrow_max_results_w_create_bqstorage_client_no_warning(self): + from google.cloud.bigquery.schema import SchemaField + + schema = [ + SchemaField("name", "STRING", mode="REQUIRED"), + SchemaField("age", "INTEGER", mode="REQUIRED"), + ] + rows = [ + {"f": [{"v": "Phred Phlyntstone"}, {"v": "32"}]}, + {"f": [{"v": "Bharney Rhubble"}, {"v": "33"}]}, + ] + path = "/foo" + api_request = mock.Mock(return_value={"rows": rows}) + mock_client = _mock_client() + + row_iterator = self._make_one( + client=mock_client, + api_request=api_request, + path=path, + schema=schema, + max_results=42, + ) + + with warnings.catch_warnings(record=True) as warned: + row_iterator.to_arrow(create_bqstorage_client=True) + + matches = [ + warning + for warning in warned + if warning.category is UserWarning + and "cannot use bqstorage_client" in str(warning).lower() + and "REST" in str(warning) + ] + self.assertFalse(matches) + mock_client._ensure_bqstorage_client.assert_not_called() @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") @unittest.skipIf( @@ -2099,7 +2503,7 @@ def test_to_arrow_w_bqstorage_creates_client(self): bqstorage_client._transport = mock.create_autospec( big_query_read_grpc_transport.BigQueryReadGrpcTransport ) - mock_client._create_bqstorage_client.return_value = bqstorage_client + mock_client._ensure_bqstorage_client.return_value = bqstorage_client session = bigquery_storage.types.ReadSession() bqstorage_client.create_read_session.return_value = session row_iterator = mut.RowIterator( @@ -2114,11 +2518,11 @@ def test_to_arrow_w_bqstorage_creates_client(self): table=mut.TableReference.from_string("proj.dset.tbl"), ) row_iterator.to_arrow(create_bqstorage_client=True) - mock_client._create_bqstorage_client.assert_called_once() + mock_client._ensure_bqstorage_client.assert_called_once() bqstorage_client._transport.grpc_channel.close.assert_called_once() @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") - def test_to_arrow_create_bqstorage_client_wo_bqstorage(self): + def test_to_arrow_ensure_bqstorage_client_wo_bqstorage(self): from google.cloud.bigquery.schema import SchemaField schema = [ @@ -2133,14 +2537,14 @@ def test_to_arrow_create_bqstorage_client_wo_bqstorage(self): api_request = mock.Mock(return_value={"rows": rows}) mock_client = _mock_client() - mock_client._create_bqstorage_client.return_value = None + mock_client._ensure_bqstorage_client.return_value = None row_iterator = self._make_one(mock_client, api_request, path, schema) tbl = row_iterator.to_arrow(create_bqstorage_client=True) # The client attempted to create a BQ Storage client, and even though # that was not possible, results were still returned without errors. - mock_client._create_bqstorage_client.assert_called_once() + mock_client._ensure_bqstorage_client.assert_called_once() self.assertIsInstance(tbl, pyarrow.Table) self.assertEqual(tbl.num_rows, 2) @@ -2236,7 +2640,6 @@ def test_to_arrow_w_pyarrow_none(self): @unittest.skipIf(pandas is None, "Requires `pandas`") def test_to_dataframe_iterable(self): from google.cloud.bigquery.schema import SchemaField - import types schema = [ SchemaField("name", "STRING", mode="REQUIRED"), @@ -2279,7 +2682,6 @@ def test_to_dataframe_iterable(self): @unittest.skipIf(pandas is None, "Requires `pandas`") def test_to_dataframe_iterable_with_dtypes(self): from google.cloud.bigquery.schema import SchemaField - import types schema = [ SchemaField("name", "STRING", mode="REQUIRED"), @@ -2391,6 +2793,61 @@ def test_to_dataframe_iterable_w_bqstorage(self): # Don't close the client if it was passed in. bqstorage_client._transport.grpc_channel.close.assert_not_called() + @unittest.skipIf(pandas is None, "Requires `pandas`") + @unittest.skipIf( + bigquery_storage is None, "Requires `google-cloud-bigquery-storage`" + ) + @unittest.skipIf(pyarrow is None, "Requires `pyarrow`") + def test_to_dataframe_iterable_w_bqstorage_max_results_warning(self): + from google.cloud.bigquery import schema + from google.cloud.bigquery import table as mut + + bqstorage_client = mock.create_autospec(bigquery_storage.BigQueryReadClient) + + iterator_schema = [ + schema.SchemaField("name", "STRING", mode="REQUIRED"), + schema.SchemaField("age", "INTEGER", mode="REQUIRED"), + ] + path = "/foo" + api_request = mock.Mock( + side_effect=[ + { + "rows": [{"f": [{"v": "Bengt"}, {"v": "32"}]}], + "pageToken": "NEXTPAGE", + }, + {"rows": [{"f": [{"v": "Sven"}, {"v": "33"}]}]}, + ] + ) + row_iterator = mut.RowIterator( + _mock_client(), + api_request, + path, + iterator_schema, + table=mut.TableReference.from_string("proj.dset.tbl"), + selected_fields=iterator_schema, + max_results=25, + ) + + with warnings.catch_warnings(record=True) as warned: + dfs = row_iterator.to_dataframe_iterable(bqstorage_client=bqstorage_client) + + # Was a warning emitted? + matches = [ + warning + for warning in warned + if warning.category is UserWarning + and "cannot use bqstorage_client" in str(warning).lower() + and "REST" in str(warning) + ] + assert len(matches) == 1, "User warning was not emitted." + assert __file__ in str(matches[0]), "Warning emitted with incorrect stacklevel" + + # Basic check of what we got as a result. + dataframes = list(dfs) + assert len(dataframes) == 2 + assert isinstance(dataframes[0], pandas.DataFrame) + assert isinstance(dataframes[1], pandas.DataFrame) + @mock.patch("google.cloud.bigquery.table.pandas", new=None) def test_to_dataframe_iterable_error_if_pandas_is_none(self): from google.cloud.bigquery.schema import SchemaField @@ -2452,10 +2909,7 @@ def test_to_dataframe_timestamp_out_of_pyarrow_bounds(self): df = row_iterator.to_dataframe(create_bqstorage_client=False) - tzinfo = None - if PYARROW_VERSION >= PYARROW_TIMESTAMP_VERSION: - tzinfo = datetime.timezone.utc - + tzinfo = datetime.timezone.utc self.assertIsInstance(df, pandas.DataFrame) self.assertEqual(len(df), 2) # verify the number of rows self.assertEqual(list(df.columns), ["some_timestamp"]) @@ -2753,6 +3207,18 @@ def test_to_dataframe_error_if_pandas_is_none(self): with self.assertRaises(ValueError): row_iterator.to_dataframe() + @unittest.skipIf(pandas is None, "Requires `pandas`") + @mock.patch("google.cloud.bigquery.table.shapely", new=None) + def test_to_dataframe_error_if_shapely_is_none(self): + with self.assertRaisesRegex( + ValueError, + re.escape( + "The shapely library is not installed, please install " + "shapely to use the geography_as_object option." + ), + ): + self._make_one_from_data().to_dataframe(geography_as_object=True) + @unittest.skipIf(pandas is None, "Requires `pandas`") def test_to_dataframe_max_results_w_bqstorage_warning(self): from google.cloud.bigquery.schema import SchemaField @@ -2790,7 +3256,7 @@ def test_to_dataframe_max_results_w_bqstorage_warning(self): self.assertEqual(len(matches), 1, msg="User warning was not emitted.") @unittest.skipIf(pandas is None, "Requires `pandas`") - def test_to_dataframe_max_results_w_create_bqstorage_warning(self): + def test_to_dataframe_max_results_w_explicit_bqstorage_client_warning(self): from google.cloud.bigquery.schema import SchemaField schema = [ @@ -2804,6 +3270,7 @@ def test_to_dataframe_max_results_w_create_bqstorage_warning(self): path = "/foo" api_request = mock.Mock(return_value={"rows": rows}) mock_client = _mock_client() + mock_bqstorage_client = mock.sentinel.bq_storage_client row_iterator = self._make_one( client=mock_client, @@ -2814,7 +3281,7 @@ def test_to_dataframe_max_results_w_create_bqstorage_warning(self): ) with warnings.catch_warnings(record=True) as warned: - row_iterator.to_dataframe(create_bqstorage_client=True) + row_iterator.to_dataframe(bqstorage_client=mock_bqstorage_client) matches = [ warning @@ -2824,7 +3291,47 @@ def test_to_dataframe_max_results_w_create_bqstorage_warning(self): and "REST" in str(warning) ] self.assertEqual(len(matches), 1, msg="User warning was not emitted.") - mock_client._create_bqstorage_client.assert_not_called() + self.assertIn( + __file__, str(matches[0]), msg="Warning emitted with incorrect stacklevel" + ) + mock_client._ensure_bqstorage_client.assert_not_called() + + @unittest.skipIf(pandas is None, "Requires `pandas`") + def test_to_dataframe_max_results_w_create_bqstorage_client_no_warning(self): + from google.cloud.bigquery.schema import SchemaField + + schema = [ + SchemaField("name", "STRING", mode="REQUIRED"), + SchemaField("age", "INTEGER", mode="REQUIRED"), + ] + rows = [ + {"f": [{"v": "Phred Phlyntstone"}, {"v": "32"}]}, + {"f": [{"v": "Bharney Rhubble"}, {"v": "33"}]}, + ] + path = "/foo" + api_request = mock.Mock(return_value={"rows": rows}) + mock_client = _mock_client() + + row_iterator = self._make_one( + client=mock_client, + api_request=api_request, + path=path, + schema=schema, + max_results=42, + ) + + with warnings.catch_warnings(record=True) as warned: + row_iterator.to_dataframe(create_bqstorage_client=True) + + matches = [ + warning + for warning in warned + if warning.category is UserWarning + and "cannot use bqstorage_client" in str(warning).lower() + and "REST" in str(warning) + ] + self.assertFalse(matches) + mock_client._ensure_bqstorage_client.assert_not_called() @unittest.skipIf(pandas is None, "Requires `pandas`") @unittest.skipIf( @@ -2839,7 +3346,7 @@ def test_to_dataframe_w_bqstorage_creates_client(self): bqstorage_client._transport = mock.create_autospec( big_query_read_grpc_transport.BigQueryReadGrpcTransport ) - mock_client._create_bqstorage_client.return_value = bqstorage_client + mock_client._ensure_bqstorage_client.return_value = bqstorage_client session = bigquery_storage.types.ReadSession() bqstorage_client.create_read_session.return_value = session row_iterator = mut.RowIterator( @@ -2854,7 +3361,7 @@ def test_to_dataframe_w_bqstorage_creates_client(self): table=mut.TableReference.from_string("proj.dset.tbl"), ) row_iterator.to_dataframe(create_bqstorage_client=True) - mock_client._create_bqstorage_client.assert_called_once() + mock_client._ensure_bqstorage_client.assert_called_once() bqstorage_client._transport.grpc_channel.close.assert_called_once() @unittest.skipIf(pandas is None, "Requires `pandas`") @@ -3469,6 +3976,199 @@ def test_to_dataframe_concat_categorical_dtype_w_pyarrow(self): # Don't close the client if it was passed in. bqstorage_client._transport.grpc_channel.close.assert_not_called() + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_dataframe_geography_as_object(self): + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("geog", "GEOGRAPHY")), + ( + ("foo", "Point(0 0)"), + ("bar", None), + ("baz", "Polygon((0 0, 0 1, 1 0, 0 0))"), + ), + ) + df = row_iterator.to_dataframe( + create_bqstorage_client=False, geography_as_object=True, + ) + self.assertIsInstance(df, pandas.DataFrame) + self.assertEqual(len(df), 3) # verify the number of rows + self.assertEqual(list(df), ["name", "geog"]) # verify the column names + self.assertEqual(df.name.dtype.name, "object") + self.assertEqual(df.geog.dtype.name, "object") + self.assertIsInstance(df.geog, pandas.Series) + self.assertEqual( + [v.__class__.__name__ for v in df.geog], ["Point", "float", "Polygon"] + ) + + @mock.patch("google.cloud.bigquery.table.geopandas", new=None) + def test_to_geodataframe_error_if_geopandas_is_none(self): + with self.assertRaisesRegex( + ValueError, + re.escape( + "The geopandas library is not installed, please install " + "geopandas to use the to_geodataframe() function." + ), + ): + self._make_one_from_data().to_geodataframe() + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_geodataframe(self): + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("geog", "GEOGRAPHY")), + ( + ("foo", "Point(0 0)"), + ("bar", None), + ("baz", "Polygon((0 0, 0 1, 1 0, 0 0))"), + ), + ) + df = row_iterator.to_geodataframe(create_bqstorage_client=False) + self.assertIsInstance(df, geopandas.GeoDataFrame) + self.assertEqual(len(df), 3) # verify the number of rows + self.assertEqual(list(df), ["name", "geog"]) # verify the column names + self.assertEqual(df.name.dtype.name, "object") + self.assertEqual(df.geog.dtype.name, "geometry") + self.assertIsInstance(df.geog, geopandas.GeoSeries) + self.assertEqual(list(map(str, df.area)), ["0.0", "nan", "0.5"]) + self.assertEqual(list(map(str, df.geog.area)), ["0.0", "nan", "0.5"]) + self.assertEqual(df.crs.srs, "EPSG:4326") + self.assertEqual(df.crs.name, "WGS 84") + self.assertEqual(df.geog.crs.srs, "EPSG:4326") + self.assertEqual(df.geog.crs.name, "WGS 84") + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_geodataframe_ambiguous_geog(self): + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("geog", "GEOGRAPHY"), ("geog2", "GEOGRAPHY")), () + ) + with self.assertRaisesRegex( + ValueError, + re.escape( + "There is more than one GEOGRAPHY column in the result. " + "The geography_column argument must be used to specify which " + "one to use to create a GeoDataFrame" + ), + ): + row_iterator.to_geodataframe(create_bqstorage_client=False) + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_geodataframe_bad_geography_column(self): + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("geog", "GEOGRAPHY"), ("geog2", "GEOGRAPHY")), () + ) + with self.assertRaisesRegex( + ValueError, + re.escape( + "The given geography column, xxx, doesn't name" + " a GEOGRAPHY column in the result." + ), + ): + row_iterator.to_geodataframe( + create_bqstorage_client=False, geography_column="xxx" + ) + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_geodataframe_no_geog(self): + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("geog", "STRING")), () + ) + with self.assertRaisesRegex( + TypeError, + re.escape( + "There must be at least one GEOGRAPHY column" + " to create a GeoDataFrame" + ), + ): + row_iterator.to_geodataframe(create_bqstorage_client=False) + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + def test_to_geodataframe_w_geography_column(self): + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("geog", "GEOGRAPHY"), ("geog2", "GEOGRAPHY")), + ( + ("foo", "Point(0 0)", "Point(1 1)"), + ("bar", None, "Point(2 2)"), + ("baz", "Polygon((0 0, 0 1, 1 0, 0 0))", "Point(3 3)"), + ), + ) + df = row_iterator.to_geodataframe( + create_bqstorage_client=False, geography_column="geog" + ) + self.assertIsInstance(df, geopandas.GeoDataFrame) + self.assertEqual(len(df), 3) # verify the number of rows + self.assertEqual(list(df), ["name", "geog", "geog2"]) # verify the column names + self.assertEqual(df.name.dtype.name, "object") + self.assertEqual(df.geog.dtype.name, "geometry") + self.assertEqual(df.geog2.dtype.name, "object") + self.assertIsInstance(df.geog, geopandas.GeoSeries) + self.assertEqual(list(map(str, df.area)), ["0.0", "nan", "0.5"]) + self.assertEqual(list(map(str, df.geog.area)), ["0.0", "nan", "0.5"]) + self.assertEqual( + [v.__class__.__name__ for v in df.geog], ["Point", "NoneType", "Polygon"] + ) + + # Geog2 isn't a GeoSeries, but it contains geomentries: + self.assertIsInstance(df.geog2, pandas.Series) + self.assertEqual( + [v.__class__.__name__ for v in df.geog2], ["Point", "Point", "Point"] + ) + # and can easily be converted to a GeoSeries + self.assertEqual( + list(map(str, geopandas.GeoSeries(df.geog2).area)), ["0.0", "0.0", "0.0"] + ) + + @unittest.skipIf(geopandas is None, "Requires `geopandas`") + @mock.patch("google.cloud.bigquery.table.RowIterator.to_dataframe") + def test_rowiterator_to_geodataframe_delegation(self, to_dataframe): + """ + RowIterator.to_geodataframe just delegates to RowIterator.to_dataframe. + + This test just demonstrates that. We don't need to test all the + variations, which are tested for to_dataframe. + """ + import numpy + from shapely import wkt + + row_iterator = self._make_one_from_data( + (("name", "STRING"), ("g", "GEOGRAPHY")) + ) + bqstorage_client = object() + dtypes = dict(xxx=numpy.dtype("int64")) + progress_bar_type = "normal" + create_bqstorage_client = False + date_as_object = False + geography_column = "g" + + to_dataframe.return_value = pandas.DataFrame( + dict(name=["foo"], g=[wkt.loads("point(0 0)")],) + ) + + df = row_iterator.to_geodataframe( + bqstorage_client=bqstorage_client, + dtypes=dtypes, + progress_bar_type=progress_bar_type, + create_bqstorage_client=create_bqstorage_client, + date_as_object=date_as_object, + geography_column=geography_column, + ) + + to_dataframe.assert_called_once_with( + bqstorage_client, + dtypes, + progress_bar_type, + create_bqstorage_client, + date_as_object, + geography_as_object=True, + ) + + self.assertIsInstance(df, geopandas.GeoDataFrame) + self.assertEqual(len(df), 1) # verify the number of rows + self.assertEqual(list(df), ["name", "g"]) # verify the column names + self.assertEqual(df.name.dtype.name, "object") + self.assertEqual(df.g.dtype.name, "geometry") + self.assertIsInstance(df.g, geopandas.GeoSeries) + self.assertEqual(list(map(str, df.area)), ["0.0"]) + self.assertEqual(list(map(str, df.g.area)), ["0.0"]) + self.assertEqual([v.__class__.__name__ for v in df.g], ["Point"]) + class TestPartitionRange(unittest.TestCase): def _get_target_class(self):