MAINT Standardize sample weights validation in KernelDensity (scikit-learn#15519)

Co-authored-by: Sallie Walecka <[email protected]>

Author: 2 people

sklearn/neighbors/_kde.py

@@ -7,7 +7,8 @@
 import numpy as np
 from scipy.special import gammainc
 from ..base import BaseEstimator
-from ..utils import check_array, check_random_state, check_consistent_length
+from ..utils import check_array, check_random_state
+from ..utils.validation import _check_sample_weight
 
 from ..utils.extmath import row_norms
 from ._ball_tree import BallTree, DTYPE
@@ -154,13 +155,7 @@ def fit(self, X, y=None, sample_weight=None):
         X = check_array(X, order='C', dtype=DTYPE)
 
         if sample_weight is not None:
-            sample_weight = check_array(sample_weight, order='C', dtype=DTYPE,
-                                        ensure_2d=False)
-            if sample_weight.ndim != 1:
-                raise ValueError("the shape of sample_weight must be ({0},),"
-                                 " but was {1}".format(X.shape[0],
-                                                       sample_weight.shape))
-            check_consistent_length(X, sample_weight)
+            sample_weight = _check_sample_weight(sample_weight, X, DTYPE)
             if sample_weight.min() <= 0:
                 raise ValueError("sample_weight must have positive values")
 

sklearn/neighbors/tests/test_kde.py

@@ -204,6 +204,21 @@ def test_kde_sample_weights():
                     assert_allclose(scores_scaled_weight, scores_weight)
 
 
+def test_sample_weight_invalid():
+    # Check sample weighting raises errors.
+    kde = KernelDensity()
+    data = np.reshape([1., 2., 3.], (-1, 1))
+
+    sample_weight = [0.1, 0.2]
+    with pytest.raises(ValueError):
+        kde.fit(data, sample_weight=sample_weight)
+
+    sample_weight = [0.1, -0.2, 0.3]
+    expected_err = "sample_weight must have positive values"
+    with pytest.raises(ValueError, match=expected_err):
+        kde.fit(data, sample_weight=sample_weight)
+
+
 @pytest.mark.parametrize('sample_weight', [None, [0.1, 0.2, 0.3]])
 def test_pickling(tmpdir, sample_weight):
     # Make sure that predictions are the same before and after pickling. Used