pep8 fixes

code/optional-py-scripts/ch03.py

@@ -20,9 +20,10 @@
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.neighbors import KNeighborsClassifier
-from sklearn.tree import export_graphviz
+# from sklearn.tree import export_graphviz
 from matplotlib.colors import ListedColormap
 import matplotlib.pyplot as plt
+import warnings
 
 # for sklearn 0.18's alternative syntax
 from distutils.version import LooseVersion as Version
@@ -108,6 +109,7 @@ def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
                     marker='o',
                     s=55, label='test set')
 
+
 X_combined_std = np.vstack((X_train_std, X_test_std))
 y_combined = np.hstack((y_train, y_test))
 
@@ -130,6 +132,7 @@ def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
 def sigmoid(z):
     return 1.0 / (1.0 + np.exp(-z))
 
+
 z = np.arange(-7, 7, 0.1)
 phi_z = sigmoid(z)
 
@@ -161,6 +164,7 @@ def cost_1(z):
 def cost_0(z):
     return - np.log(1 - sigmoid(z))
 
+
 z = np.arange(-10, 10, 0.1)
 phi_z = sigmoid(z)
 
@@ -331,6 +335,7 @@ def entropy(p):
 def error(p):
     return 1 - np.max([p, 1 - p])
 
+
 x = np.arange(0.0, 1.0, 0.01)
 
 ent = [entropy(p) if p != 0 else None for p in x]

code/optional-py-scripts/ch05.py

@@ -175,6 +175,7 @@ def plot_decision_regions(X, y, classifier, resolution=0.02):
                     alpha=0.8, c=cmap(idx),
                     marker=markers[idx], label=cl)
 
+
 lr = LogisticRegression()
 lr = lr.fit(X_train_pca, y_train)
 
@@ -596,6 +597,7 @@ def project_x(x_new, X, gamma, alphas, lambdas):
     k = np.exp(-gamma * pair_dist)
     return k.dot(alphas / lambdas)
 
+
 # projection of the "new" datapoint
 x_reproj = project_x(x_new, X, gamma=15, alphas=alphas, lambdas=lambdas)
 print('Reprojection x_reproj:', x_reproj)

code/optional-py-scripts/ch08.py

@@ -127,6 +127,7 @@ def preprocessor(text):
         ' '.join(emoticons).replace('-', '')
     return text
 
+
 print('Preprocessor on Excerpt:\n\n', preprocessor(df.loc[0, 'review'][-50:]))
 
 res = preprocessor("</a>This :) is :( a test :-)!")
@@ -246,6 +247,7 @@ def stream_docs(path):
             text, label = line[:-3], int(line[-2])
             yield text, label
 
+
 next(stream_docs(path='./movie_data.csv'))
 
 

code/optional-py-scripts/ch10.py

@@ -139,6 +139,7 @@ def lin_regplot(X, y, model):
     plt.plot(X, model.predict(X), color='red', linewidth=2)
     return
 
+
 lin_regplot(X_std, y_std, lr)
 plt.xlabel('Average number of rooms [RM] (standardized)')
 plt.ylabel('Price in $1000\'s [MEDV] (standardized)')
@@ -196,7 +197,8 @@ def lin_regplot(X, y, model):
     ransac = RANSACRegressor(LinearRegression(),
                              max_trials=100,
                              min_samples=50,
-                             residual_metric=lambda x: np.sum(np.abs(x), axis=1),
+                             residual_metric=lambda x: np.sum(
+                                np.abs(x), axis=1),
                              residual_threshold=5.0,
                              random_state=0)
 else:

code/optional-py-scripts/ch13.py

@@ -188,6 +188,7 @@ def predict_linreg(X, w):
     predict = theano.function(inputs=[Xt], givens={w: w}, outputs=net_input)
     return predict(X)
 
+
 plt.scatter(X_train, y_train, marker='s', s=50)
 plt.plot(range(X_train.shape[0]),
          predict_linreg(X_train, w),
@@ -229,6 +230,7 @@ def logistic_activation(X, w):
     z = net_input(X, w)
     return logistic(z)
 
+
 print('P(y=1|x) = %.3f' % logistic_activation(X, w)[0])
 
 
@@ -274,6 +276,7 @@ def softmax_activation(X, w):
     z = net_input(X, w)
     return softmax(z)
 
+
 y_probas = softmax(Z)
 print('Probabilities:\n', y_probas)
 
@@ -294,6 +297,7 @@ def tanh(z):
     e_m = np.exp(-z)
     return (e_p - e_m) / (e_p + e_m)
 
+
 z = np.arange(-5, 5, 0.005)
 log_act = logistic(z)
 tanh_act = tanh(z)
@@ -359,6 +363,7 @@ def load_mnist(path, kind='train'):
 
     return images, labels
 
+
 X_train, y_train = load_mnist('mnist', kind='train')
 print('Training rows: %d, columns: %d' % (X_train.shape[0], X_train.shape[1]))