TST: added test that sample_weight can be a list (scikit-learn#8261)

Author: dalmia

sklearn/calibration.py

@@ -19,7 +19,7 @@
 from .base import BaseEstimator, ClassifierMixin, RegressorMixin, clone
 from .preprocessing import label_binarize, LabelBinarizer
 from .utils import check_X_y, check_array, indexable, column_or_1d
-from .utils.validation import check_is_fitted
+from .utils.validation import check_is_fitted, check_consistent_length
 from .utils.fixes import signature
 from .isotonic import IsotonicRegression
 from .svm import LinearSVC
@@ -167,6 +167,9 @@ def fit(self, X, y, sample_weight=None):
                               " itself." % estimator_name)
                 base_estimator_sample_weight = None
             else:
+                if sample_weight is not None:
+                    sample_weight = check_array(sample_weight, ensure_2d=False)
+                    check_consistent_length(y, sample_weight)
                 base_estimator_sample_weight = sample_weight
             for train, test in cv.split(X, y):
                 this_estimator = clone(base_estimator)

sklearn/ensemble/bagging.py

@@ -20,7 +20,7 @@
 from ..utils import check_random_state, check_X_y, check_array, column_or_1d
 from ..utils.random import sample_without_replacement
 from ..utils.validation import has_fit_parameter, check_is_fitted
-from ..utils import indices_to_mask
+from ..utils import indices_to_mask, check_consistent_length
 from ..utils.fixes import bincount
 from ..utils.metaestimators import if_delegate_has_method
 from ..utils.multiclass import check_classification_targets
@@ -82,8 +82,8 @@ def _parallel_build_estimators(n_estimators, ensemble, X, y, sample_weight,
 
     for i in range(n_estimators):
         if verbose > 1:
-            print("Building estimator %d of %d for this parallel run (total %d)..." %
-                  (i + 1, n_estimators, total_n_estimators))
+            print("Building estimator %d of %d for this parallel run "
+                  "(total %d)..." % (i + 1, n_estimators, total_n_estimators))
 
         random_state = np.random.RandomState(seeds[i])
         estimator = ensemble._make_estimator(append=False,
@@ -282,6 +282,9 @@ def _fit(self, X, y, max_samples=None, max_depth=None, sample_weight=None):
 
         # Convert data
         X, y = check_X_y(X, y, ['csr', 'csc'])
+        if sample_weight is not None:
+            sample_weight = check_array(sample_weight, ensure_2d=False)
+            check_consistent_length(y, sample_weight)
 
         # Remap output
         n_samples, self.n_features_ = X.shape

sklearn/linear_model/logistic.py

@@ -888,6 +888,9 @@ def _log_reg_scoring_path(X, y, train, test, pos_class=None, Cs=10,
     y_test = y[test]
 
     if sample_weight is not None:
+        sample_weight = check_array(sample_weight, ensure_2d=False)
+        check_consistent_length(y, sample_weight)
+
         sample_weight = sample_weight[train]
 
     coefs, Cs, n_iter = logistic_regression_path(

sklearn/naive_bayes.py

@@ -25,7 +25,7 @@
 from .preprocessing import binarize
 from .preprocessing import LabelBinarizer
 from .preprocessing import label_binarize
-from .utils import check_X_y, check_array
+from .utils import check_X_y, check_array, check_consistent_length
 from .utils.extmath import safe_sparse_dot, logsumexp
 from .utils.multiclass import _check_partial_fit_first_call
 from .utils.fixes import in1d
@@ -333,6 +333,9 @@ def _partial_fit(self, X, y, classes=None, _refit=False,
             Returns self.
         """
         X, y = check_X_y(X, y)
+        if sample_weight is not None:
+            sample_weight = check_array(sample_weight, ensure_2d=False)
+            check_consistent_length(y, sample_weight)
 
         # If the ratio of data variance between dimensions is too small, it
         # will cause numerical errors. To address this, we artificially

sklearn/utils/estimator_checks.py

@@ -72,6 +72,7 @@ def _yield_non_meta_checks(name, Estimator):
     yield check_fit_score_takes_y
     yield check_dtype_object
     yield check_sample_weights_pandas_series
+    yield check_sample_weights_list
     yield check_estimators_fit_returns_self
 
     # Check that all estimator yield informative messages when
@@ -396,6 +397,21 @@ def check_sample_weights_pandas_series(name, Estimator):
                            "input of type pandas.Series to class weight.")
 
 
+@ignore_warnings(category=DeprecationWarning)
+def check_sample_weights_list(name, Estimator):
+    # check that estimators will accept a 'sample_weight' parameter of
+    # type list in the 'fit' function.
+    estimator = Estimator()
+    if has_fit_parameter(estimator, "sample_weight"):
+        rnd = np.random.RandomState(0)
+        X = rnd.uniform(size=(10, 3))
+        y = np.arange(10) % 3
+        y = multioutput_estimator_convert_y_2d(name, y)
+        sample_weight = [3] * 10
+        # Test that estimators don't raise any exception
+        estimator.fit(X, y, sample_weight=sample_weight)
+
+
 @ignore_warnings(category=(DeprecationWarning, UserWarning))
 def check_dtype_object(name, Estimator):
     # check that estimators treat dtype object as numeric if possible