iter

Author: glemaitre

imblearn/base.py

@@ -53,6 +53,7 @@ def fit(self, X, y):
         if (not dask_collection or
                 (dask_collection and self.validate_if_dask_collection)):
             X, y, _ = self._check_X_y(X, y)
+
         self._classes_counts = get_classes_counts(y)
         self.sampling_strategy_ = check_sampling_strategy(
             self.sampling_strategy, self._classes_counts, self._sampling_type

imblearn/datasets/_imbalance.py

@@ -9,7 +9,10 @@
 
 from ..under_sampling import RandomUnderSampler
 from ..utils import check_sampling_strategy
-from ..utils._validation import _deprecate_positional_args
+from ..utils._validation import (
+    _deprecate_positional_args,
+    get_classes_counts,
+)
 
 
 @_deprecate_positional_args
@@ -87,11 +90,11 @@ def make_imbalance(
     >>> print('Distribution after imbalancing: {}'.format(Counter(y_res)))
     Distribution after imbalancing: Counter({2: 30, 1: 20, 0: 10})
     """
-    target_stats = Counter(y)
+    target_stats = get_classes_counts(y)
     # restrict ratio to be a dict or a callable
     if isinstance(sampling_strategy, dict) or callable(sampling_strategy):
         sampling_strategy_ = check_sampling_strategy(
-            sampling_strategy, y, "under-sampling", **kwargs
+            sampling_strategy, target_stats, "under-sampling", **kwargs
         )
     else:
         raise ValueError(

imblearn/ensemble/_bagging.py

@@ -18,7 +18,10 @@
 from ..utils import Substitution, check_target_type, check_sampling_strategy
 from ..utils._docstring import _n_jobs_docstring
 from ..utils._docstring import _random_state_docstring
-from ..utils._validation import _deprecate_positional_args
+from ..utils._validation import (
+    _deprecate_positional_args,
+    get_classes_counts,
+)
 
 
 @Substitution(
@@ -216,11 +219,12 @@ def __init__(
 
     def _validate_y(self, y):
         y_encoded = super()._validate_y(y)
+        classes_counts = get_classes_counts(y)
         if isinstance(self.sampling_strategy, dict):
             self._sampling_strategy = {
                 np.where(self.classes_ == key)[0][0]: value
                 for key, value in check_sampling_strategy(
-                    self.sampling_strategy, y, 'under-sampling',
+                    self.sampling_strategy, classes_counts, 'under-sampling',
                 ).items()
             }
         else:

imblearn/ensemble/_easy_ensemble.py

@@ -17,7 +17,10 @@
 from ..utils import Substitution, check_target_type, check_sampling_strategy
 from ..utils._docstring import _n_jobs_docstring
 from ..utils._docstring import _random_state_docstring
-from ..utils._validation import _deprecate_positional_args
+from ..utils._validation import (
+    _deprecate_positional_args,
+    get_classes_counts,
+)
 from ..pipeline import Pipeline
 
 MAX_INT = np.iinfo(np.int32).max
@@ -156,11 +159,14 @@ def __init__(
 
     def _validate_y(self, y):
         y_encoded = super()._validate_y(y)
+        classes_counts = get_classes_counts(y)
         if isinstance(self.sampling_strategy, dict):
             self._sampling_strategy = {
                 np.where(self.classes_ == key)[0][0]: value
                 for key, value in check_sampling_strategy(
-                    self.sampling_strategy, y, 'under-sampling',
+                    self.sampling_strategy,
+                    classes_counts,
+                    "under-sampling",
                 ).items()
             }
         else:

imblearn/ensemble/_forest.py

@@ -33,8 +33,11 @@
 from ..utils import Substitution
 from ..utils._docstring import _n_jobs_docstring
 from ..utils._docstring import _random_state_docstring
-from ..utils._validation import check_sampling_strategy
-from ..utils._validation import _deprecate_positional_args
+from ..utils._validation import (
+    check_sampling_strategy,
+    _deprecate_positional_args,
+    get_classes_counts,
+)
 
 MAX_INT = np.iinfo(np.int32).max
 
@@ -457,10 +460,11 @@ def fit(self, X, y, sample_weight=None):
             y_encoded = np.ascontiguousarray(y_encoded, dtype=DOUBLE)
 
         if isinstance(self.sampling_strategy, dict):
+            classes_counts = get_classes_counts(y)
             self._sampling_strategy = {
                 np.where(self.classes_[0] == key)[0][0]: value
                 for key, value in check_sampling_strategy(
-                    self.sampling_strategy, y, 'under-sampling',
+                    self.sampling_strategy, classes_counts, 'under-sampling',
                 ).items()
             }
         else: