Merge pull request scikit-learn#5721 from amueller/examples_deprecation_fixes

[MRG+1]  Don't use deprecated 1d X (or deprecated matplotlib stuff) in examples

Author: agramfort

examples/applications/plot_prediction_latency.py

@@ -42,7 +42,7 @@ def atomic_benchmark_estimator(estimator, X_test, verbose=False):
     n_instances = X_test.shape[0]
     runtimes = np.zeros(n_instances, dtype=np.float)
     for i in range(n_instances):
-        instance = X_test[i, :]
+        instance = X_test[[i], :]
         start = time.time()
         estimator.predict(instance)
         runtimes[i] = time.time() - start
@@ -241,7 +241,7 @@ def benchmark_throughputs(configuration, duration_secs=0.1):
         start_time = time.time()
         n_predictions = 0
         while (time.time() - start_time) < duration_secs:
-            estimator_config['instance'].predict(X_test[0])
+            estimator_config['instance'].predict(X_test[[0]])
             n_predictions += 1
         throughputs[estimator_config['name']] = n_predictions / duration_secs
     return throughputs

examples/classification/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')

examples/cluster/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)
 
 ###############################################################################

examples/decomposition/plot_sparse_coding.py

@@ -75,7 +75,7 @@ def ricker_matrix(width, resolution, n_components):
     for title, algo, alpha, n_nonzero, color in estimators:
         coder = SparseCoder(dictionary=D, transform_n_nonzero_coefs=n_nonzero,
                             transform_alpha=alpha, transform_algorithm=algo)
-        x = coder.transform(y)
+        x = coder.transform(y.reshape(1, -1))
         density = len(np.flatnonzero(x))
         x = np.ravel(np.dot(x, D))
         squared_error = np.sum((y - x) ** 2)
@@ -86,7 +86,7 @@ def ricker_matrix(width, resolution, n_components):
     # Soft thresholding debiasing
     coder = SparseCoder(dictionary=D, transform_algorithm='threshold',
                         transform_alpha=20)
-    x = coder.transform(y)
+    x = coder.transform(y.reshape(1, -1))
     _, idx = np.where(x != 0)
     x[0, idx], _, _, _ = np.linalg.lstsq(D[idx, :].T, y)
     x = np.ravel(np.dot(x, D))

examples/ensemble/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))

examples/linear_model/plot_sgd_separating_hyperplane.py

@@ -30,7 +30,7 @@
 for (i, j), val in np.ndenumerate(X1):
     x1 = val
     x2 = X2[i, j]
-    p = clf.decision_function([x1, x2])
+    p = clf.decision_function([[x1, x2]])
     Z[i, j] = p[0]
 levels = [-1.0, 0.0, 1.0]
 linestyles = ['dashed', 'solid', 'dashed']

examples/manifold/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())

examples/manifold/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())

examples/neighbors/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)