iter

Author: glemaitre

imblearn/over_sampling/_random_over_sampler.py

@@ -157,7 +157,7 @@ def __init__(
 
     def _check_X_y(self, X, y):
         y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
-        X = _check_X(X)
+        X = _check_X(self, X)
         _check_n_features(self, X, reset=True)
         _check_feature_names(self, X, reset=True)
         return X, y, binarize_y

imblearn/over_sampling/_smote/base.py

@@ -608,7 +608,7 @@ def _check_X_y(self, X, y):
         features.
         """
         y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
-        X = _check_X(X)
+        X = _check_X(self, X)
         _check_n_features(self, X, reset=True)
         _check_feature_names(self, X, reset=True)
         return X, y, binarize_y

imblearn/under_sampling/_prototype_selection/_random_under_sampler.py

@@ -104,7 +104,7 @@ def __init__(
 
     def _check_X_y(self, X, y):
         y, binarize_y = check_target_type(y, indicate_one_vs_all=True)
-        X = _check_X(X)
+        X = _check_X(self, X)
         _check_n_features(self, X, reset=True)
         _check_feature_names(self, X, reset=True)
         return X, y, binarize_y

imblearn/utils/_validation.py

@@ -14,12 +14,12 @@
 import sklearn
 from sklearn.base import clone
 from sklearn.neighbors import NearestNeighbors
-from sklearn.utils import check_array, column_or_1d
+from sklearn.utils import column_or_1d
 from sklearn.utils.fixes import parse_version
 from sklearn.utils.multiclass import type_of_target
 from sklearn.utils.validation import _num_samples
 
-from .fixes import _is_pandas_df
+from .fixes import _is_pandas_df, validate_data
 
 SAMPLING_KIND = (
     "over-sampling",
@@ -638,7 +638,7 @@ def inner_f(*args, **kwargs):
     return inner_f
 
 
-def _check_X(X):
+def _check_X(estimator, X):
     """Check X and do not check it if a dataframe."""
     n_samples = _num_samples(X)
     if n_samples < 1:
@@ -648,6 +648,6 @@ def _check_X(X):
     if _is_pandas_df(X):
         return X
 
-    return check_array(
-        X, dtype=None, accept_sparse=["csr", "csc"], ensure_all_finite=False
+    return validate_data(
+        estimator, X, dtype=None, accept_sparse=["csr", "csc"], ensure_all_finite=False
     )