MAINT fix FutureWarning raised by scikit-learn in examples (scikit-learn#27442)

Author: glemaitre

doc/conf.py

@@ -701,7 +701,6 @@ def setup(app):
     ),
 )
 
-
 # maps functions with a class name that is indistinguishable when case is
 # ignore to another filename
 autosummary_filename_map = {

examples/cluster/plot_face_compress.py

@@ -77,7 +77,11 @@
 
 n_bins = 8
 encoder = KBinsDiscretizer(
-    n_bins=n_bins, encode="ordinal", strategy="uniform", random_state=0
+    n_bins=n_bins,
+    encode="ordinal",
+    strategy="uniform",
+    random_state=0,
+    subsample=200_000,
 )
 compressed_raccoon_uniform = encoder.fit_transform(raccoon_face.reshape(-1, 1)).reshape(
     raccoon_face.shape
@@ -122,7 +126,11 @@
 # find a more optimal mapping.
 
 encoder = KBinsDiscretizer(
-    n_bins=n_bins, encode="ordinal", strategy="kmeans", random_state=0
+    n_bins=n_bins,
+    encode="ordinal",
+    strategy="kmeans",
+    random_state=0,
+    subsample=200_000,
 )
 compressed_raccoon_kmeans = encoder.fit_transform(raccoon_face.reshape(-1, 1)).reshape(
     raccoon_face.shape

examples/linear_model/plot_ard.py

@@ -58,8 +58,8 @@
 from sklearn.linear_model import ARDRegression, BayesianRidge, LinearRegression
 
 olr = LinearRegression().fit(X, y)
-brr = BayesianRidge(compute_score=True, n_iter=30).fit(X, y)
-ard = ARDRegression(compute_score=True, n_iter=30).fit(X, y)
+brr = BayesianRidge(compute_score=True, max_iter=30).fit(X, y)
+ard = ARDRegression(compute_score=True, max_iter=30).fit(X, y)
 df = pd.DataFrame(
     {
         "Weights of true generative process": true_weights,
@@ -117,7 +117,7 @@
 
 # %%
 # Indeed, both models minimize the log-likelihood up to an arbitrary cutoff
-# defined by the `n_iter` parameter.
+# defined by the `max_iter` parameter.
 #
 # Bayesian regressions with polynomial feature expansion
 # ======================================================

examples/preprocessing/plot_discretization_strategies.py

@@ -76,7 +76,9 @@
     i += 1
     # transform the dataset with KBinsDiscretizer
     for strategy in strategies:
-        enc = KBinsDiscretizer(n_bins=4, encode="ordinal", strategy=strategy)
+        enc = KBinsDiscretizer(
+            n_bins=4, encode="ordinal", strategy=strategy, subsample=200_000
+        )
         enc.fit(X)
         grid_encoded = enc.transform(grid)
 

examples/release_highlights/plot_release_highlights_0_22_0.py

@@ -89,7 +89,7 @@
 X, y = load_iris(return_X_y=True)
 estimators = [
     ("rf", RandomForestClassifier(n_estimators=10, random_state=42)),
-    ("svr", make_pipeline(StandardScaler(), LinearSVC(random_state=42))),
+    ("svr", make_pipeline(StandardScaler(), LinearSVC(dual="auto", random_state=42))),
 ]
 clf = StackingClassifier(estimators=estimators, final_estimator=LogisticRegression())
 X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=42)