[MRG] Pass sample_weight when predicting on stacked folds

doc/whats_new/v0.23.rst

@@ -182,6 +182,13 @@ Changelog
   used during `fit`.
   :pr:`16437` by :user:`Jin-Hwan CHO <chofchof>`.
 
+- |Fix| Fixed a bug in :class:`ensemble.StackingClassifier` and
+  :class:`ensemble.StackingRegressor` where the `sample_weight`
+  argument was not being passed to `cross_val_predict` when
+  evaluating the base estimators on cross-validation folds
+  to obtain the input to the meta estimator.
+  :pr:`16539` by :user:`Bill DeRose <wderose>`.
+
 :mod:`sklearn.feature_extraction`
 .................................
 

sklearn/ensemble/_stacking.py

@@ -122,6 +122,10 @@ def fit(self, X, y, sample_weight=None):
             Note that this is supported only if all underlying estimators
             support sample weights.
 
+            .. versionchanged:: 0.23
+               when not None, `sample_weight` is passed to all underlying
+               estimators
+
         Returns
         -------
         self : object
@@ -166,10 +170,13 @@ def fit(self, X, y, sample_weight=None):
             self._method_name(name, est, meth)
             for name, est, meth in zip(names, all_estimators, stack_method)
         ]
-
+        fit_params = ({"sample_weight": sample_weight}
+                      if sample_weight is not None
+                      else None)
         predictions = Parallel(n_jobs=self.n_jobs)(
             delayed(cross_val_predict)(clone(est), X, y, cv=deepcopy(cv),
                                        method=meth, n_jobs=self.n_jobs,
+                                       fit_params=fit_params,
                                        verbose=self.verbose)
             for est, meth in zip(all_estimators, self.stack_method_)
             if est != 'drop'
@@ -183,21 +190,8 @@ def fit(self, X, y, sample_weight=None):
         ]
 
         X_meta = self._concatenate_predictions(X, predictions)
-        if sample_weight is not None:
-            try:
-                self.final_estimator_.fit(
-                    X_meta, y, sample_weight=sample_weight
-                )
-            except TypeError as exc:
-                if "unexpected keyword argument 'sample_weight'" in str(exc):
-                    raise TypeError(
-                        "Underlying estimator {} does not support sample "
-                        "weights."
-                        .format(self.final_estimator_.__class__.__name__)
-                    ) from exc
-                raise
-        else:
-            self.final_estimator_.fit(X_meta, y)
+        _fit_single_estimator(self.final_estimator_, X_meta, y,
+                              sample_weight=sample_weight)
 
         return self
 

sklearn/ensemble/tests/test_stacking.py

@@ -38,6 +38,7 @@
 from sklearn.model_selection import StratifiedKFold
 from sklearn.model_selection import KFold
 
+from sklearn.utils._mocking import CheckingClassifier
 from sklearn.utils._testing import assert_allclose
 from sklearn.utils._testing import assert_allclose_dense_sparse
 from sklearn.utils._testing import ignore_warnings
@@ -439,6 +440,19 @@ def test_stacking_with_sample_weight(stacker, X, y):
     assert np.abs(y_pred_no_weight - y_pred_biased).sum() > 0
 
 
+def test_stacking_classifier_sample_weight_fit_param():
+    # check sample_weight is passed to all invocations of fit
+    stacker = StackingClassifier(
+        estimators=[
+            ('lr', CheckingClassifier(expected_fit_params=['sample_weight']))
+        ],
+        final_estimator=CheckingClassifier(
+            expected_fit_params=['sample_weight']
+        )
+    )
+    stacker.fit(X_iris, y_iris, sample_weight=np.ones(X_iris.shape[0]))
+
+
 @pytest.mark.filterwarnings("ignore::sklearn.exceptions.ConvergenceWarning")
 @pytest.mark.parametrize(
     "stacker, X, y",

sklearn/utils/_mocking.py

@@ -95,6 +95,7 @@ def fit(self, X, y, **fit_params):
             assert self.check_X(X)
         if self.check_y is not None:
             assert self.check_y(y)
+        self.n_features_in_ = len(X)
         self.classes_ = np.unique(check_array(y, ensure_2d=False,
                                               allow_nd=True))
         if self.expected_fit_params: