[MRG] Examples deprecations (scikit-learn#11561)

amueller · rth · commit 0b8d36254564 · 2018-07-17T00:08:04.000-05:00
diff --git a/examples/applications/plot_prediction_latency.py b/examples/applications/plot_prediction_latency.py
@@ -102,7 +102,7 @@ def generate_dataset(n_train, n_test, n_features, noise=0.1, verbose=False):
 
     random_seed = 13
     X_train, X_test, y_train, y_test = train_test_split(
-        X, y, train_size=n_train, random_state=random_seed)
+        X, y, train_size=n_train, test_size=n_test, random_state=random_seed)
     X_train, y_train = shuffle(X_train, y_train, random_state=random_seed)
 
     X_scaler = StandardScaler()
diff --git a/examples/applications/plot_species_distribution_modeling.py b/examples/applications/plot_species_distribution_modeling.py
@@ -154,7 +154,7 @@ def plot_species_distribution(species=("bradypus_variegatus_0",
         else:
             print(" - plot coastlines from coverage")
             plt.contour(X, Y, land_reference,
-                        levels=[-9999], colors="k",
+                        levels=[-9998], colors="k",
                         linestyles="solid")
             plt.xticks([])
             plt.yticks([])
diff --git a/examples/classification/plot_classification_probability.py b/examples/classification/plot_classification_probability.py
@@ -76,7 +76,7 @@ class dataset, and we classify it with a Support Vector classifier, L1
         plt.yticks(())
         idx = (y_pred == k)
         if idx.any():
-            plt.scatter(X[idx, 0], X[idx, 1], marker='o', c='k')
+            plt.scatter(X[idx, 0], X[idx, 1], marker='o', c='w', edgecolor='k')
 
 ax = plt.axes([0.15, 0.04, 0.7, 0.05])
 plt.title("Probability")
diff --git a/examples/classification/plot_lda_qda.py b/examples/classification/plot_lda_qda.py
@@ -130,8 +130,8 @@ def plot_lda_cov(lda, splot):
 
 
 def plot_qda_cov(qda, splot):
-    plot_ellipse(splot, qda.means_[0], qda.covariances_[0], 'red')
-    plot_ellipse(splot, qda.means_[1], qda.covariances_[1], 'blue')
+    plot_ellipse(splot, qda.means_[0], qda.covariance_[0], 'red')
+    plot_ellipse(splot, qda.means_[1], qda.covariance_[1], 'blue')
 
 for i, (X, y) in enumerate([dataset_fixed_cov(), dataset_cov()]):
     # Linear Discriminant Analysis
diff --git a/examples/cluster/plot_kmeans_silhouette_analysis.py b/examples/cluster/plot_kmeans_silhouette_analysis.py
@@ -139,4 +139,4 @@
                   "with n_clusters = %d" % n_clusters),
                  fontsize=14, fontweight='bold')
 
-    plt.show()
+plt.show()
diff --git a/examples/ensemble/plot_feature_transformation.py b/examples/ensemble/plot_feature_transformation.py
@@ -62,7 +62,7 @@
 
 # Supervised transformation based on random forests
 rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
-rf_enc = OneHotEncoder()
+rf_enc = OneHotEncoder(categories='auto')
 rf_lm = LogisticRegression()
 rf.fit(X_train, y_train)
 rf_enc.fit(rf.apply(X_train))
@@ -72,7 +72,7 @@
 fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
 
 grd = GradientBoostingClassifier(n_estimators=n_estimator)
-grd_enc = OneHotEncoder()
+grd_enc = OneHotEncoder(categories='auto')
 grd_lm = LogisticRegression()
 grd.fit(X_train, y_train)
 grd_enc.fit(grd.apply(X_train)[:, :, 0])
diff --git a/examples/ensemble/plot_isolation_forest.py b/examples/ensemble/plot_isolation_forest.py
@@ -40,7 +40,7 @@
 X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
 
 # fit the model
-clf = IsolationForest(max_samples=100, random_state=rng)
+clf = IsolationForest(max_samples=100, random_state=rng, contamination='auto')
 clf.fit(X_train)
 y_pred_train = clf.predict(X_train)
 y_pred_test = clf.predict(X_test)
diff --git a/examples/ensemble/plot_random_forest_regression_multioutput.py b/examples/ensemble/plot_random_forest_regression_multioutput.py
@@ -39,9 +39,8 @@
 y = np.array([np.pi * np.sin(X).ravel(), np.pi * np.cos(X).ravel()]).T
 y += (0.5 - rng.rand(*y.shape))
 
-X_train, X_test, y_train, y_test = train_test_split(X, y,
-                                                    train_size=400,
-                                                    random_state=4)
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, train_size=400, test_size=200, random_state=4)
 
 max_depth = 30
 regr_multirf = MultiOutputRegressor(RandomForestRegressor(max_depth=max_depth,
diff --git a/examples/ensemble/plot_voting_decision_regions.py b/examples/ensemble/plot_voting_decision_regions.py
@@ -39,7 +39,7 @@
 # Training classifiers
 clf1 = DecisionTreeClassifier(max_depth=4)
 clf2 = KNeighborsClassifier(n_neighbors=7)
-clf3 = SVC(kernel='rbf', probability=True)
+clf3 = SVC(gamma=.1, kernel='rbf', probability=True)
 eclf = VotingClassifier(estimators=[('dt', clf1), ('knn', clf2),
                                     ('svc', clf3)],
                         voting='soft', weights=[2, 1, 2])
diff --git a/examples/model_selection/grid_search_text_feature_extraction.py b/examples/model_selection/grid_search_text_feature_extraction.py
@@ -22,7 +22,7 @@
   pipeline: ['vect', 'tfidf', 'clf']
   parameters:
   {'clf__alpha': (1.0000000000000001e-05, 9.9999999999999995e-07),
-   'clf__n_iter': (10, 50, 80),
+   'clf__max_iter': (10, 50, 80),
    'clf__penalty': ('l2', 'elasticnet'),
    'tfidf__use_idf': (True, False),
    'vect__max_n': (1, 2),
@@ -33,7 +33,7 @@
   Best score: 0.940
   Best parameters set:
       clf__alpha: 9.9999999999999995e-07
-      clf__n_iter: 50
+      clf__max_iter: 50
       clf__penalty: 'elasticnet'
       tfidf__use_idf: True
       vect__max_n: 2
@@ -97,14 +97,14 @@
 # increase processing time in a combinatorial way
 parameters = {
     'vect__max_df': (0.5, 0.75, 1.0),
-    #'vect__max_features': (None, 5000, 10000, 50000),
+    # 'vect__max_features': (None, 5000, 10000, 50000),
     'vect__ngram_range': ((1, 1), (1, 2)),  # unigrams or bigrams
-    #'tfidf__use_idf': (True, False),
-    #'tfidf__norm': ('l1', 'l2'),
+    # 'tfidf__use_idf': (True, False),
+    # 'tfidf__norm': ('l1', 'l2'),
     'clf__max_iter': (5,),
     'clf__alpha': (0.00001, 0.000001),
     'clf__penalty': ('l2', 'elasticnet'),
-    #'clf__n_iter': (10, 50, 80),
+    # 'clf__max_iter': (10, 50, 80),
 }
 
 if __name__ == "__main__":
diff --git a/examples/model_selection/plot_multi_metric_evaluation.py b/examples/model_selection/plot_multi_metric_evaluation.py
@@ -47,7 +47,7 @@
 # ``gs.best_index_``
 gs = GridSearchCV(DecisionTreeClassifier(random_state=42),
                   param_grid={'min_samples_split': range(2, 403, 10)},
-                  scoring=scoring, cv=5, refit='AUC')
+                  scoring=scoring, cv=5, refit='AUC', return_train_score=True)
 gs.fit(X, y)
 results = gs.cv_results_
 
@@ -61,9 +61,8 @@
 
 plt.xlabel("min_samples_split")
 plt.ylabel("Score")
-plt.grid()
 
-ax = plt.axes()
+ax = plt.gca()
 ax.set_xlim(0, 402)
 ax.set_ylim(0.73, 1)
 
diff --git a/examples/neighbors/plot_lof.py b/examples/neighbors/plot_lof.py
@@ -34,7 +34,7 @@
 X = np.r_[X_inliers, X_outliers]
 
 # fit the model
-clf = LocalOutlierFactor(n_neighbors=20)
+clf = LocalOutlierFactor(n_neighbors=20, contamination='auto')
 y_pred = clf.fit_predict(X)
 
 # plot the level sets of the decision function
diff --git a/examples/neighbors/plot_nearest_centroid.py b/examples/neighbors/plot_nearest_centroid.py
@@ -50,7 +50,7 @@
 
     # Plot also the training points
     plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold,
-                edgecolor='b', s=20)
+                edgecolor='k', s=20)
     plt.title("3-Class classification (shrink_threshold=%r)"
               % shrinkage)
     plt.axis('tight')
diff --git a/examples/neighbors/plot_species_kde.py b/examples/neighbors/plot_species_kde.py
@@ -105,7 +105,7 @@
     else:
         print(" - plot coastlines from coverage")
         plt.contour(X, Y, land_reference,
-                    levels=[-9999], colors="k",
+                    levels=[-9998], colors="k",
                     linestyles="solid")
         plt.xticks([])
         plt.yticks([])
diff --git a/examples/semi_supervised/plot_label_propagation_versus_svm_iris.py b/examples/semi_supervised/plot_label_propagation_versus_svm_iris.py
@@ -42,7 +42,7 @@
 ls50 = (label_propagation.LabelSpreading().fit(X, y_50),
         y_50)
 ls100 = (label_propagation.LabelSpreading().fit(X, y), y)
-rbf_svc = (svm.SVC(kernel='rbf').fit(X, y), y)
+rbf_svc = (svm.SVC(kernel='rbf', gamma=.5).fit(X, y), y)
 
 # create a mesh to plot in
 x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
diff --git a/examples/svm/plot_svm_scale_c.py b/examples/svm/plot_svm_scale_c.py
@@ -129,6 +129,7 @@
         # reduce the variance
         grid = GridSearchCV(clf, refit=False, param_grid=param_grid,
                             cv=ShuffleSplit(train_size=train_size,
+                                            test_size=.3,
                                             n_splits=250, random_state=1))
         grid.fit(X, y)
         scores = grid.cv_results_['mean_test_score']
diff --git a/examples/svm/plot_weighted_samples.py b/examples/svm/plot_weighted_samples.py
@@ -48,10 +48,10 @@ def plot_decision_function(classifier, sample_weight, axis, title):
 # for reference, first fit without class weights
 
 # fit the model
-clf_weights = svm.SVC()
+clf_weights = svm.SVC(gamma=1)
 clf_weights.fit(X, y, sample_weight=sample_weight_last_ten)
 
-clf_no_weights = svm.SVC()
+clf_no_weights = svm.SVC(gamma=1)
 clf_no_weights.fit(X, y)
 
 fig, axes = plt.subplots(1, 2, figsize=(14, 6))
diff --git a/examples/text/plot_document_classification_20newsgroups.py b/examples/text/plot_document_classification_20newsgroups.py
@@ -249,9 +249,9 @@ def benchmark(clf):
 
 results = []
 for clf, name in (
-        (RidgeClassifier(tol=1e-2, solver="lsqr"), "Ridge Classifier"),
-        (Perceptron(n_iter=50, tol=1e-3), "Perceptron"),
-        (PassiveAggressiveClassifier(n_iter=50, tol=1e-3),
+        (RidgeClassifier(tol=1e-2, solver="sag"), "Ridge Classifier"),
+        (Perceptron(max_iter=50, tol=1e-3), "Perceptron"),
+        (PassiveAggressiveClassifier(max_iter=50, tol=1e-3),
          "Passive-Aggressive"),
         (KNeighborsClassifier(n_neighbors=10), "kNN"),
         (RandomForestClassifier(n_estimators=100), "Random forest")):
@@ -267,16 +267,14 @@ def benchmark(clf):
                                        tol=1e-3)))
 
     # Train SGD model
-    results.append(benchmark(SGDClassifier(alpha=.0001, n_iter=50,
-                                           penalty=penalty,
-                                           max_iter=5)))
+    results.append(benchmark(SGDClassifier(alpha=.0001, max_iter=50,
+                                           penalty=penalty)))
 
 # Train SGD with Elastic Net penalty
 print('=' * 80)
 print("Elastic-Net penalty")
-results.append(benchmark(SGDClassifier(alpha=.0001, n_iter=50,
-                                       penalty="elasticnet",
-                                       max_iter=5)))
+results.append(benchmark(SGDClassifier(alpha=.0001, max_iter=50,
+                                       penalty="elasticnet")))
 
 # Train NearestCentroid without threshold
 print('=' * 80)
