Pushing the docs for revision for branch: master, commit 37c8d0297be0f63cf5ceea55259eed3629023885

Author: sklearn-ci

dev/_downloads/face_recognition.py

@@ -10,7 +10,7 @@
 
 .. _LFW: http://vis-www.cs.umass.edu/lfw/
 
-Expected results for the top 5 most represented people in the dataset::
+Expected results for the top 5 most represented people in the dataset:
 
 ================== ============ ======= ========== =======
                    precision    recall  f1-score   support

dev/_downloads/plot_approximate_nearest_neighbors_scalability.py

@@ -89,7 +89,7 @@
 
     for i in range(n_iter):
         # pick one query at random to study query time variability in LSHForest
-        query = queries[rng.randint(0, n_queries)]
+        query = queries[[rng.randint(0, n_queries)]]
 
         t0 = time.time()
         exact_neighbors = nbrs.kneighbors(query, return_distance=False)

dev/_downloads/plot_compare_methods.py

@@ -113,7 +113,7 @@
 Y = tsne.fit_transform(X)
 t1 = time()
 print("t-SNE: %.2g sec" % (t1 - t0))
-ax = fig.add_subplot(250)
+ax = fig.add_subplot(2, 5, 10)
 plt.scatter(Y[:, 0], Y[:, 1], c=color, cmap=plt.cm.Spectral)
 plt.title("t-SNE (%.2g sec)" % (t1 - t0))
 ax.xaxis.set_major_formatter(NullFormatter())

dev/_downloads/plot_feature_agglomeration_vs_univariate_selection.py

@@ -85,7 +85,7 @@
 clf = GridSearchCV(clf, {'anova__percentile': [5, 10, 20]}, cv=cv)
 clf.fit(X, y)  # set the best parameters
 coef_ = clf.best_estimator_.steps[-1][1].coef_
-coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_)
+coef_ = clf.best_estimator_.steps[0][1].inverse_transform(coef_.reshape(1, -1))
 coef_selection_ = coef_.reshape(size, size)
 
 ###############################################################################

dev/_downloads/plot_gradient_boosting_regression.py

@@ -47,7 +47,7 @@
 # compute test set deviance
 test_score = np.zeros((params['n_estimators'],), dtype=np.float64)
 
-for i, y_pred in enumerate(clf.staged_decision_function(X_test)):
+for i, y_pred in enumerate(clf.staged_predict(X_test)):
     test_score[i] = clf.loss_(y_test, y_pred)
 
 plt.figure(figsize=(12, 6))

dev/_downloads/plot_lasso_coordinate_descent_path.py

@@ -13,6 +13,7 @@
 # Author: Alexandre Gramfort <[email protected]>
 # License: BSD 3 clause
 
+from itertools import cycle
 import numpy as np
 import matplotlib.pyplot as plt
 
@@ -47,9 +48,13 @@
 
 plt.figure(1)
 ax = plt.gca()
-ax.set_color_cycle(2 * ['b', 'r', 'g', 'c', 'k'])
-l1 = plt.plot(-np.log10(alphas_lasso), coefs_lasso.T)
-l2 = plt.plot(-np.log10(alphas_enet), coefs_enet.T, linestyle='--')
+
+colors = cycle(['b', 'r', 'g', 'c', 'k'])
+neg_log_alphas_lasso = -np.log10(alphas_lasso)
+neg_log_alphas_enet = -np.log10(alphas_enet)
+for coef_l, coef_e, c in zip(coefs_lasso, coefs_enet, colors):
+    l1 = plt.plot(neg_log_alphas_lasso, coef_l, c=c)
+    l2 = plt.plot(neg_log_alphas_enet, coef_e, linestyle='--', c=c)
 
 plt.xlabel('-Log(alpha)')
 plt.ylabel('coefficients')
@@ -60,10 +65,10 @@
 
 plt.figure(2)
 ax = plt.gca()
-ax.set_color_cycle(2 * ['b', 'r', 'g', 'c', 'k'])
-l1 = plt.plot(-np.log10(alphas_lasso), coefs_lasso.T)
-l2 = plt.plot(-np.log10(alphas_positive_lasso), coefs_positive_lasso.T,
-              linestyle='--')
+neg_log_alphas_positive_lasso = -np.log10(alphas_positive_lasso)
+for coef_l, coef_pl, c in zip(coefs_lasso, coefs_positive_lasso, colors):
+    l1 = plt.plot(neg_log_alphas_lasso, coef_l, c=c)
+    l2 = plt.plot(neg_log_alphas_positive_lasso, coef_pl, linestyle='--', c=c)
 
 plt.xlabel('-Log(alpha)')
 plt.ylabel('coefficients')
@@ -74,10 +79,10 @@
 
 plt.figure(3)
 ax = plt.gca()
-ax.set_color_cycle(2 * ['b', 'r', 'g', 'c', 'k'])
-l1 = plt.plot(-np.log10(alphas_enet), coefs_enet.T)
-l2 = plt.plot(-np.log10(alphas_positive_enet), coefs_positive_enet.T,
-              linestyle='--')
+neg_log_alphas_positive_enet = -np.log10(alphas_positive_enet)
+for (coef_e, coef_pe, c) in zip(coefs_enet, coefs_positive_enet, colors):
+    l1 = plt.plot(neg_log_alphas_enet, coef_e, c=c)
+    l2 = plt.plot(neg_log_alphas_positive_enet, coef_pe, linestyle='--', c=c)
 
 plt.xlabel('-Log(alpha)')
 plt.ylabel('coefficients')

dev/_downloads/plot_lda_qda.py

@@ -67,8 +67,6 @@ def plot_data(lda, X, y, y_pred, fig_index):
     X0, X1 = X[y == 0], X[y == 1]
     X0_tp, X0_fp = X0[tp0], X0[~tp0]
     X1_tp, X1_fp = X1[tp1], X1[~tp1]
-    xmin, xmax = X[:, 0].min(), X[:, 0].max()
-    ymin, ymax = X[:, 1].min(), X[:, 1].max()
 
     # class 0: dots
     plt.plot(X0_tp[:, 0], X0_tp[:, 1], 'o', color='red')
@@ -133,8 +131,8 @@ def plot_qda_cov(qda, splot):
     plt.axis('tight')
 
     # Quadratic Discriminant Analysis
-    qda = QuadraticDiscriminantAnalysis()
-    y_pred = qda.fit(X, y, store_covariances=True).predict(X)
+    qda = QuadraticDiscriminantAnalysis(store_covariances=True)
+    y_pred = qda.fit(X, y).predict(X)
     splot = plot_data(qda, X, y, y_pred, fig_index=2 * i + 2)
     plot_qda_cov(qda, splot)
     plt.axis('tight')

dev/_downloads/plot_logistic_multinomial.py

@@ -0,0 +1,70 @@
+"""
+====================================================
+Plot multinomial and One-vs-Rest Logistic Regression
+====================================================
+
+Plot decision surface of multinomial and One-vs-Rest Logistic Regression.
+The hyperplanes corresponding to the three One-vs-Rest (OVR) classifiers
+are represented by the dashed lines.
+"""
+print(__doc__)
+# Authors: Tom Dupre la Tour <[email protected]>
+# Licence: BSD 3 clause
+
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.datasets import make_blobs
+from sklearn.linear_model import LogisticRegression
+
+# make 3-class dataset for classification
+centers = [[-5, 0], [0, 1.5], [5, -1]]
+X, y = make_blobs(n_samples=1000, centers=centers, random_state=40)
+transformation = [[0.4, 0.2], [-0.4, 1.2]]
+X = np.dot(X, transformation)
+
+for multi_class in ('multinomial', 'ovr'):
+    clf = LogisticRegression(solver='sag', max_iter=100, random_state=42,
+                             multi_class=multi_class).fit(X, y)
+
+    # print the training scores
+    print("training score : %.3f (%s)" % (clf.score(X, y), multi_class))
+
+    # create a mesh to plot in
+    h = .02  # step size in the mesh
+    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
+    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
+    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
+                         np.arange(y_min, y_max, h))
+
+    # Plot the decision boundary. For that, we will assign a color to each
+    # point in the mesh [x_min, m_max]x[y_min, y_max].
+    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
+    # Put the result into a color plot
+    Z = Z.reshape(xx.shape)
+    plt.figure()
+    plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
+    plt.title("Decision surface of LogisticRegression (%s)" % multi_class)
+    plt.axis('tight')
+
+    # Plot also the training points
+    colors = "bry"
+    for i, color in zip(clf.classes_, colors):
+        idx = np.where(y == i)
+        plt.scatter(X[idx, 0], X[idx, 1], c=color, cmap=plt.cm.Paired)
+
+    # Plot the three one-against-all classifiers
+    xmin, xmax = plt.xlim()
+    ymin, ymax = plt.ylim()
+    coef = clf.coef_
+    intercept = clf.intercept_
+
+    def plot_hyperplane(c, color):
+        def line(x0):
+            return (-(x0 * coef[c, 0]) - intercept[c]) / coef[c, 1]
+        plt.plot([xmin, xmax], [line(xmin), line(xmax)],
+                 ls="--", color=color)
+
+    for i, color in zip(clf.classes_, colors):
+        plot_hyperplane(i, color)
+
+plt.show()

dev/_downloads/plot_manifold_sphere.py

@@ -103,7 +103,7 @@
 print("%s: %.2g sec" % ('ISO', t1 - t0))
 
 ax = fig.add_subplot(257)
-plt.scatter(trans_data[0], trans_data[1],  c=colors, cmap=plt.cm.rainbow)
+plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
 plt.title("%s (%.2g sec)" % ('Isomap', t1 - t0))
 ax.xaxis.set_major_formatter(NullFormatter())
 ax.yaxis.set_major_formatter(NullFormatter())
@@ -117,7 +117,7 @@
 print("MDS: %.2g sec" % (t1 - t0))
 
 ax = fig.add_subplot(258)
-plt.scatter(trans_data[0], trans_data[1],  c=colors, cmap=plt.cm.rainbow)
+plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
 plt.title("MDS (%.2g sec)" % (t1 - t0))
 ax.xaxis.set_major_formatter(NullFormatter())
 ax.yaxis.set_major_formatter(NullFormatter())
@@ -132,7 +132,7 @@
 print("Spectral Embedding: %.2g sec" % (t1 - t0))
 
 ax = fig.add_subplot(259)
-plt.scatter(trans_data[0], trans_data[1],  c=colors, cmap=plt.cm.rainbow)
+plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
 plt.title("Spectral Embedding (%.2g sec)" % (t1 - t0))
 ax.xaxis.set_major_formatter(NullFormatter())
 ax.yaxis.set_major_formatter(NullFormatter())
@@ -145,8 +145,8 @@
 t1 = time()
 print("t-SNE: %.2g sec" % (t1 - t0))
 
-ax = fig.add_subplot(250)
-plt.scatter(trans_data[0], trans_data[1],  c=colors, cmap=plt.cm.rainbow)
+ax = fig.add_subplot(2, 5, 10)
+plt.scatter(trans_data[0], trans_data[1], c=colors, cmap=plt.cm.rainbow)
 plt.title("t-SNE (%.2g sec)" % (t1 - t0))
 ax.xaxis.set_major_formatter(NullFormatter())
 ax.yaxis.set_major_formatter(NullFormatter())

dev/_downloads/plot_ols.py

@@ -50,8 +50,8 @@
 
 # The coefficients
 print('Coefficients: \n', regr.coef_)
-# The mean square error
-print("Residual sum of squares: %.2f"
+# The mean squared error
+print("Mean squared error: %.2f"
       % np.mean((regr.predict(diabetes_X_test) - diabetes_y_test) ** 2))
 # Explained variance score: 1 is perfect prediction
 print('Variance score: %.2f' % regr.score(diabetes_X_test, diabetes_y_test))