ENH: Add private RNG normalizer (#14199)

Author: bruAristimunha

doc/changes/dev/14199.apichange.rst

@@ -0,0 +1 @@
+Add ``rng`` parameters to APIs that use randomness, while retaining keyword-only ``seed`` and ``random_state`` for compatibility (:gh:`9233` by `Bruno Aristimunha`_).

examples/datasets/spm_faces_dataset.py

@@ -36,7 +36,7 @@
 raw.resample(100)
 raw.filter(1.0, None)  # high-pass
 reject = dict(mag=5e-12)
-ica = ICA(n_components=0.95, max_iter="auto", random_state=0)
+ica = ICA(n_components=0.95, max_iter="auto", rng=97)
 ica.fit(raw, reject=reject)
 # compute correlation scores, get bad indices sorted by score
 eog_epochs = create_eog_epochs(raw, ch_name="MRT31-2908", reject=reject)

examples/decoding/decoding_csp_eeg.py

@@ -80,7 +80,7 @@
 scores = []
 epochs_data = epochs.get_data(copy=False)
 epochs_data_train = epochs_train.get_data(copy=False)
-cv = ShuffleSplit(10, test_size=0.2, random_state=42)
+cv = ShuffleSplit(10, test_size=0.2, random_state=103)
 cv_split = cv.split(epochs_data_train)
 
 # Assemble a classifier

examples/decoding/decoding_csp_timefreq.py

@@ -53,7 +53,7 @@
     LinearDiscriminantAnalysis(),
 )
 n_splits = 3  # for cross-validation, 5 is better, here we use 3 for speed
-cv = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)
+cv = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=191)
 
 # Classification & time-frequency parameters
 tmin, tmax = -0.200, 2.000

examples/decoding/decoding_rsa.py

@@ -125,13 +125,13 @@
 # to focus the classifier on the time interval with best SNR.
 clf = make_pipeline(
     StandardScaler(),
-    OneVsRestClassifier(LogisticRegression(C=1)),
+    OneVsRestClassifier(LogisticRegression(C=1, random_state=79)),
 )
 X = epochs.get_data(tmin=0.05, tmax=0.3).mean(axis=2)
 y = epochs.events[:, 2]
 
 classes = set(y)
-cv = StratifiedKFold(n_splits=5, random_state=0, shuffle=True)
+cv = StratifiedKFold(n_splits=5, random_state=83, shuffle=True)
 
 # Compute confusion matrix for each cross-validation fold
 y_pred = np.zeros((len(y), len(classes)))
@@ -173,7 +173,7 @@
 chance = 0.5
 # TODO VERSION: this is MDS(2, n_init=4, init='random', metric='precomputed'),
 # but that spelling requires scikit-learn >= 1.8
-summary, _ = smacof(chance - confusion, n_components=2, n_init=4, random_state=0)
+summary, _ = smacof(chance - confusion, n_components=2, n_init=4, random_state=89)
 cmap = plt.colormaps["rainbow"]
 colors = ["r", "b"]
 names = list(conds["condition"].values)

examples/decoding/decoding_spatio_temporal_source.py

@@ -103,7 +103,7 @@
 clf = make_pipeline(
     StandardScaler(),  # z-score normalization
     SelectKBest(f_classif, k=500),  # select features for speed
-    LinearModel(LogisticRegression(C=1, solver="liblinear")),
+    LinearModel(LogisticRegression(C=1, solver="liblinear", random_state=107)),
 )
 time_decod = SlidingEstimator(clf, scoring="roc_auc")
 

examples/decoding/decoding_spoc_CMC.py

@@ -60,7 +60,7 @@
 
 # Classification pipeline with SPoC spatial filtering and Ridge Regression
 spoc = SPoC(n_components=2, log=True, reg="oas", rank="full")
-clf = make_pipeline(spoc, Ridge())
+clf = make_pipeline(spoc, Ridge(random_state=127))
 # Define a two fold cross-validation
 cv = KFold(n_splits=2, shuffle=False)
 

examples/decoding/decoding_time_generalization_conditions.py

@@ -69,7 +69,8 @@
 # and test on all right visual vs auditory trials.
 clf = make_pipeline(
     StandardScaler(),
-    LogisticRegression(solver="liblinear"),  # liblinear is faster than lbfgs
+    # liblinear is faster than lbfgs
+    LogisticRegression(solver="liblinear", random_state=131),
 )
 time_gen = GeneralizingEstimator(clf, scoring="roc_auc", n_jobs=None, verbose=True)
 

examples/decoding/decoding_unsupervised_spatial_filter.py

@@ -63,7 +63,7 @@
 
 ##############################################################################
 # Transform data with PCA computed on the average ie evoked response
-pca = UnsupervisedSpatialFilter(PCA(30), average=False)
+pca = UnsupervisedSpatialFilter(PCA(30, random_state=193), average=False)
 pca_data = pca.fit_transform(X)
 ev = mne.EvokedArray(
     np.mean(pca_data, axis=0),
@@ -74,7 +74,9 @@
 
 ##############################################################################
 # Transform data with ICA computed on the raw epochs (no averaging)
-ica = UnsupervisedSpatialFilter(FastICA(30, whiten="unit-variance"), average=False)
+ica = UnsupervisedSpatialFilter(
+    FastICA(30, whiten="unit-variance", random_state=197), average=False
+)
 ica_data = ica.fit_transform(X)
 ev1 = mne.EvokedArray(
     np.mean(ica_data, axis=0),

examples/decoding/decoding_xdawn_eeg.py

@@ -80,7 +80,9 @@
     XdawnTransformer(n_components=n_filter),
     Vectorizer(),
     MinMaxScaler(),
-    OneVsRestClassifier(LogisticRegression(solver="liblinear", **kwargs)),
+    OneVsRestClassifier(
+        LogisticRegression(solver="liblinear", random_state=157, **kwargs)
+    ),
 )
 
 # Get the data and labels
@@ -89,7 +91,7 @@
 y = epochs.events[:, -1]
 
 # Cross validator
-cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=42)
+cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=163)
 
 # Do cross-validation
 preds = np.empty(len(y))