pass sample_weight when predicting on stacked folds

Bill DeRose · Bill DeRose · commit cf8cfd17af74 · 2020-02-24T18:09:42.000-08:00
diff --git a/sklearn/ensemble/_stacking.py b/sklearn/ensemble/_stacking.py
@@ -165,10 +165,12 @@ 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)
         ]
-
         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={
+                                           'sample_weight': sample_weight
+                                        },
                                        verbose=self.verbose)
             for est, meth in zip(all_estimators, self.stack_method_)
             if est != 'drop'
diff --git a/sklearn/ensemble/tests/test_stacking.py b/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_fit_stacking_with_sample_weight_passed():
+    # check sample_weight is passed to all invokations 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",
