[MRG + 1] 18 more examples with matplotlib 2.0 updates (scikit-learn#…

…8983)

* updated plot_label_propagation_versus_svm_iris.py plot

* updated svm/plot_weighted_samples.py plot

* made semi_supervised/plot_label_propagation_versus_svm_iris.py pep8 compliant

* modified tree/plot_tree_regression.py [size and edgecolor]

* updated tree/plot_tree_regression_multioutput.py [size+color]

* fixed examples/semi_supervised/plot_label_propagation_versus_svm_iris.py for backward compatibility

* neural_networks/plot_mlp_alpha.py - matplotlib2 update

* examples/neural_networks/plot_mlp_alpha.py - pep8 fix

* examples/neighbors/plot_nearest_centroid.py - matplotlib2.0 + pep8 fix

* neighbors/plot_classification.py - matplotlib2.0 + pep8 fix

* examples/neighbors/plot_lof.py - matplotlib2.0 update

* examples/model_selection/plot_underfitting_overfitting.py - matplotlib2.0 + pep8

* examples/mixture/plot_concentration_prior.py - matplotlib2.0 + pep8

* examples/linear_model/plot_logistic_multinomial.py - matplotlib2.0 update

* linear_model/plot_sgd_iris.py - matplotlib2.0 + pep8 fix

* examples/linear_model/plot_sgd_weighted_samples.py - matplotlib2.0 + pep8

* examples/linear_model/plot_sgd_separating_hyperplane.py - matplotlib2.0 update

* examples/feature_selection/plot_permutation_test_for_classification.py - matplotlib + pe8

* examples/linear_model/plot_bayesian_ridge.py - matplotlib2.0 update

* examples/feature_selection/plot_feature_selection.py - matplotlib2.0 update

* examples/feature_selection/plot_f_test_vs_mi.py - matplotlib2.0 + pep8

* examples/feature_selection/plot_f_test_vs_mi.py - matplotlib2.0+ pep8 fix

* examples/model_selection/plot_underfitting_overfitting.py - error fixed

* blue -> black edgecolor fix for 2 examples

examples/feature_selection/plot_f_test_vs_mi.py

@@ -9,7 +9,8 @@
 We consider 3 features x_1, x_2, x_3 distributed uniformly over [0, 1], the
 target depends on them as follows:
 
-y = x_1 + sin(6 * pi * x_2) + 0.1 * N(0, 1), that is the third features is completely irrelevant.
+y = x_1 + sin(6 * pi * x_2) + 0.1 * N(0, 1), that is the third features is
+completely irrelevant.
 
 The code below plots the dependency of y against individual x_i and normalized
 values of univariate F-tests statistics and mutual information.
@@ -39,11 +40,10 @@
 plt.figure(figsize=(15, 5))
 for i in range(3):
     plt.subplot(1, 3, i + 1)
-    plt.scatter(X[:, i], y)
+    plt.scatter(X[:, i], y, edgecolor='black', s=20)
     plt.xlabel("$x_{}$".format(i + 1), fontsize=14)
     if i == 0:
         plt.ylabel("$y$", fontsize=14)
     plt.title("F-test={:.2f}, MI={:.2f}".format(f_test[i], mi[i]),
               fontsize=16)
 plt.show()
-

examples/feature_selection/plot_feature_selection.py

@@ -54,7 +54,8 @@
 scores = -np.log10(selector.pvalues_)
 scores /= scores.max()
 plt.bar(X_indices - .45, scores, width=.2,
-        label=r'Univariate score ($-Log(p_{value})$)', color='darkorange')
+        label=r'Univariate score ($-Log(p_{value})$)', color='darkorange',
+        edgecolor='black')
 
 ###############################################################################
 # Compare to the weights of an SVM
@@ -65,7 +66,7 @@
 svm_weights /= svm_weights.max()
 
 plt.bar(X_indices - .25, svm_weights, width=.2, label='SVM weight',
-        color='navy')
+        color='navy', edgecolor='black')
 
 clf_selected = svm.SVC(kernel='linear')
 clf_selected.fit(selector.transform(X), y)
@@ -74,7 +75,8 @@
 svm_weights_selected /= svm_weights_selected.max()
 
 plt.bar(X_indices[selector.get_support()] - .05, svm_weights_selected,
-        width=.2, label='SVM weights after selection', color='c')
+        width=.2, label='SVM weights after selection', color='c',
+        edgecolor='black')
 
 
 plt.title("Comparing feature selection")

examples/feature_selection/plot_permutation_test_for_classification.py

@@ -49,13 +49,14 @@
 
 ###############################################################################
 # View histogram of permutation scores
-plt.hist(permutation_scores, 20, label='Permutation scores')
+plt.hist(permutation_scores, 20, label='Permutation scores',
+         edgecolor='black')
 ylim = plt.ylim()
 # BUG: vlines(..., linestyle='--') fails on older versions of matplotlib
-#plt.vlines(score, ylim[0], ylim[1], linestyle='--',
+# plt.vlines(score, ylim[0], ylim[1], linestyle='--',
 #          color='g', linewidth=3, label='Classification Score'
 #          ' (pvalue %s)' % pvalue)
-#plt.vlines(1.0 / n_classes, ylim[0], ylim[1], linestyle='--',
+# plt.vlines(1.0 / n_classes, ylim[0], ylim[1], linestyle='--',
 #          color='k', linewidth=3, label='Luck')
 plt.plot(2 * [score], ylim, '--g', linewidth=3,
          label='Classification Score'

examples/linear_model/plot_bayesian_ridge.py

@@ -72,7 +72,8 @@
 
 plt.figure(figsize=(6, 5))
 plt.title("Histogram of the weights")
-plt.hist(clf.coef_, bins=n_features, color='gold', log=True)
+plt.hist(clf.coef_, bins=n_features, color='gold', log=True,
+         edgecolor='black')
 plt.scatter(clf.coef_[relevant_features], 5 * np.ones(len(relevant_features)),
             color='navy', label="Relevant features")
 plt.ylabel("Features")

examples/linear_model/plot_logistic_multinomial.py

@@ -50,7 +50,8 @@
     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)
+        plt.scatter(X[idx, 0], X[idx, 1], c=color, cmap=plt.cm.Paired,
+                    edgecolor='black', s=20)
 
     # Plot the three one-against-all classifiers
     xmin, xmax = plt.xlim()

examples/linear_model/plot_sgd_iris.py

@@ -17,8 +17,10 @@
 
 # import some data to play with
 iris = datasets.load_iris()
-X = iris.data[:, :2]  # we only take the first two features. We could
-                      # avoid this ugly slicing by using a two-dim dataset
+
+# we only take the first two features. We could
+# avoid this ugly slicing by using a two-dim dataset
+X = iris.data[:, :2]
 y = iris.target
 colors = "bry"
 
@@ -56,7 +58,7 @@
 for i, color in zip(clf.classes_, colors):
     idx = np.where(y == i)
     plt.scatter(X[idx, 0], X[idx, 1], c=color, label=iris.target_names[i],
-                cmap=plt.cm.Paired)
+                cmap=plt.cm.Paired, edgecolor='black', s=20)
 plt.title("Decision surface of multi-class SGD")
 plt.axis('tight')
 

examples/linear_model/plot_sgd_separating_hyperplane.py

@@ -36,7 +36,8 @@
 linestyles = ['dashed', 'solid', 'dashed']
 colors = 'k'
 plt.contour(X1, X2, Z, levels, colors=colors, linestyles=linestyles)
-plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)
+plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired,
+            edgecolor='black', s=20)
 
 plt.axis('tight')
 plt.show()

examples/linear_model/plot_sgd_weighted_samples.py

@@ -24,16 +24,16 @@
 xx, yy = np.meshgrid(np.linspace(-4, 5, 500), np.linspace(-4, 5, 500))
 plt.figure()
 plt.scatter(X[:, 0], X[:, 1], c=y, s=sample_weight, alpha=0.9,
-            cmap=plt.cm.bone)
+            cmap=plt.cm.bone, edgecolor='black')
 
-## fit the unweighted model
+# fit the unweighted model
 clf = linear_model.SGDClassifier(alpha=0.01, n_iter=100)
 clf.fit(X, y)
 Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
 Z = Z.reshape(xx.shape)
 no_weights = plt.contour(xx, yy, Z, levels=[0], linestyles=['solid'])
 
-## fit the weighted model
+# fit the weighted model
 clf = linear_model.SGDClassifier(alpha=0.01, n_iter=100)
 clf.fit(X, y, sample_weight=sample_weight)
 Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])

examples/mixture/plot_concentration_prior.py

@@ -50,7 +50,7 @@ def plot_ellipses(ax, weights, means, covars):
         # eigenvector normalization
         eig_vals = 2 * np.sqrt(2) * np.sqrt(eig_vals)
         ell = mpl.patches.Ellipse(means[n], eig_vals[0], eig_vals[1],
-                                  180 + angle)
+                                  180 + angle, edgecolor='black')
         ell.set_clip_box(ax.bbox)
         ell.set_alpha(weights[n])
         ell.set_facecolor('#56B4E9')
@@ -71,7 +71,7 @@ def plot_results(ax1, ax2, estimator, X, y, title, plot_title=False):
     ax2.yaxis.grid(True, alpha=0.7)
     for k, w in enumerate(estimator.weights_):
         ax2.bar(k, w, width=0.9, color='#56B4E9', zorder=3,
-                align='center')
+                align='center', edgecolor='black')
         ax2.text(k, w + 0.007, "%.1f%%" % (w * 100.),
                  horizontalalignment='center')
     ax2.set_xlim(-.6, 2 * n_components - .4)

examples/model_selection/plot_underfitting_overfitting.py

@@ -29,12 +29,15 @@
 from sklearn.linear_model import LinearRegression
 from sklearn.model_selection import cross_val_score
 
+
+def true_fun(X):
+    return np.cos(1.5 * np.pi * X)
+
 np.random.seed(0)
 
 n_samples = 30
 degrees = [1, 4, 15]
 
-true_fun = lambda X: np.cos(1.5 * np.pi * X)
 X = np.sort(np.random.rand(n_samples))
 y = true_fun(X) + np.random.randn(n_samples) * 0.1
 
@@ -57,7 +60,7 @@
     X_test = np.linspace(0, 1, 100)
     plt.plot(X_test, pipeline.predict(X_test[:, np.newaxis]), label="Model")
     plt.plot(X_test, true_fun(X_test), label="True function")
-    plt.scatter(X, y, label="Samples")
+    plt.scatter(X, y, edgecolor='b', s=20, label="Samples")
     plt.xlabel("x")
     plt.ylabel("y")
     plt.xlim((0, 1))

examples/neighbors/plot_classification.py

@@ -17,8 +17,10 @@
 
 # import some data to play with
 iris = datasets.load_iris()
-X = iris.data[:, :2]  # we only take the first two features. We could
-                      # avoid this ugly slicing by using a two-dim dataset
+
+# we only take the first two features. We could avoid this ugly
+# slicing by using a two-dim dataset
+X = iris.data[:, :2]
 y = iris.target
 
 h = .02  # step size in the mesh
@@ -46,7 +48,8 @@
     plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
 
     # Plot also the training points
-    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)
+    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold,
+                edgecolor='k', s=20)
     plt.xlim(xx.min(), xx.max())
     plt.ylim(yy.min(), yy.max())
     plt.title("3-Class classification (k = %i, weights = '%s')"

examples/neighbors/plot_lof.py

@@ -17,11 +17,11 @@
 In practice, such informations are generally not available, and taking
 n_neighbors=20 appears to work well in general.
 """
+print(__doc__)
 
 import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.neighbors import LocalOutlierFactor
-print(__doc__)
 
 np.random.seed(42)
 
@@ -44,8 +44,10 @@
 plt.title("Local Outlier Factor (LOF)")
 plt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r)
 
-a = plt.scatter(X[:200, 0], X[:200, 1], c='white')
-b = plt.scatter(X[200:, 0], X[200:, 1], c='red')
+a = plt.scatter(X[:200, 0], X[:200, 1], c='white',
+                edgecolor='k', s=20)
+b = plt.scatter(X[200:, 0], X[200:, 1], c='red',
+                edgecolor='k', s=20)
 plt.axis('tight')
 plt.xlim((-5, 5))
 plt.ylim((-5, 5))

examples/neighbors/plot_nearest_centroid.py

@@ -18,8 +18,9 @@
 
 # import some data to play with
 iris = datasets.load_iris()
-X = iris.data[:, :2]  # we only take the first two features. We could
-                      # avoid this ugly slicing by using a two-dim dataset
+# we only take the first two features. We could avoid this ugly
+# slicing by using a two-dim dataset
+X = iris.data[:, :2]
 y = iris.target
 
 h = .02  # step size in the mesh
@@ -48,7 +49,8 @@
     plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
 
     # Plot also the training points
-    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)
+    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold,
+                edgecolor='b', s=20)
     plt.title("3-Class classification (shrink_threshold=%r)"
               % shrinkage)
     plt.axis('tight')

examples/neural_networks/plot_mlp_alpha.py

@@ -95,10 +95,11 @@
         ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
 
         # Plot also the training points
-        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
+        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
+                   edgecolors='black', s=25)
         # and testing points
         ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
-                   alpha=0.6)
+                   alpha=0.6, edgecolors='black', s=25)
 
         ax.set_xlim(xx.min(), xx.max())
         ax.set_ylim(yy.min(), yy.max())

examples/semi_supervised/plot_label_propagation_versus_svm_iris.py

@@ -71,9 +71,9 @@
 
     # Plot also the training points
     colors = [color_map[y] for y in y_train]
-    plt.scatter(X[:, 0], X[:, 1], c=colors, cmap=plt.cm.Paired)
+    plt.scatter(X[:, 0], X[:, 1], c=colors, edgecolors='black')
 
     plt.title(titles[i])
 
-plt.text(.90, 0, "Unlabeled points are colored white")
+plt.suptitle("Unlabeled points are colored white", y=0.1)
 plt.show()

examples/svm/plot_weighted_samples.py

@@ -29,7 +29,7 @@ def plot_decision_function(classifier, sample_weight, axis, title):
     # plot the line, the points, and the nearest vectors to the plane
     axis.contourf(xx, yy, Z, alpha=0.75, cmap=plt.cm.bone)
     axis.scatter(X[:, 0], X[:, 1], c=y, s=100 * sample_weight, alpha=0.9,
-                 cmap=plt.cm.bone)
+                 cmap=plt.cm.bone, edgecolors='black')
 
     axis.axis('off')
     axis.set_title(title)

examples/tree/plot_tree_regression.py

@@ -39,8 +39,10 @@
 
 # Plot the results
 plt.figure()
-plt.scatter(X, y, c="darkorange", label="data")
-plt.plot(X_test, y_1, color="cornflowerblue", label="max_depth=2", linewidth=2)
+plt.scatter(X, y, s=20, edgecolor="black",
+            c="darkorange", label="data")
+plt.plot(X_test, y_1, color="cornflowerblue",
+         label="max_depth=2", linewidth=2)
 plt.plot(X_test, y_2, color="yellowgreen", label="max_depth=5", linewidth=2)
 plt.xlabel("data")
 plt.ylabel("target")

examples/tree/plot_tree_regression_multioutput.py

@@ -43,14 +43,19 @@
 # Plot the results
 plt.figure()
 s = 50
-plt.scatter(y[:, 0], y[:, 1], c="navy", s=s, label="data")
-plt.scatter(y_1[:, 0], y_1[:, 1], c="cornflowerblue", s=s, label="max_depth=2")
-plt.scatter(y_2[:, 0], y_2[:, 1], c="c", s=s, label="max_depth=5")
-plt.scatter(y_3[:, 0], y_3[:, 1], c="orange", s=s, label="max_depth=8")
+s = 25
+plt.scatter(y[:, 0], y[:, 1], c="navy", s=s,
+            edgecolor="black", label="data")
+plt.scatter(y_1[:, 0], y_1[:, 1], c="cornflowerblue", s=s,
+            edgecolor="black", label="max_depth=2")
+plt.scatter(y_2[:, 0], y_2[:, 1], c="red", s=s,
+            edgecolor="black", label="max_depth=5")
+plt.scatter(y_3[:, 0], y_3[:, 1], c="orange", s=s,
+            edgecolor="black", label="max_depth=8")
 plt.xlim([-6, 6])
 plt.ylim([-6, 6])
 plt.xlabel("target 1")
 plt.ylabel("target 2")
 plt.title("Multi-output Decision Tree Regression")
-plt.legend()
+plt.legend(loc="best")
 plt.show()