fix n_outliers property

tvdboom · Aug 28, 2023 · c0ae0d5 · c0ae0d5
1 parent d15e5e6
commit c0ae0d5
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 6 deletions.
diff --git a/atom/atom.py b/atom/atom.py
@@ -274,8 +274,7 @@ def n_outliers(self) -> int | None:
         """Number of samples in the training set containing outliers."""
         if not is_sparse(self.X):
             data = self.train.select_dtypes(include=["number"])
-            z_scores = (np.abs(stats.zscore(data.values.astype(float))) > 3)
-            return (z_scores.abs() > 3).any(axis=1).sum()
+            return (np.abs(stats.zscore(data.values.astype(float))) > 3).any(axis=1).sum()
 
     @property
     def classes(self) -> pd.DataFrame | None:

diff --git a/atom/basetransformer.py b/atom/basetransformer.py
@@ -756,8 +756,6 @@ def _no_data_sets(
             else:
                 test_size = self.test_size
 
-            splitter = self._get_est_class("train_test_split", "model_selection")
-
             try:
                 # Define holdout set size
                 if self.holdout_size:
@@ -773,7 +771,7 @@ def _no_data_sets(
                             f"got {self.holdout_size}."
                         )
 
-                    data, holdout = splitter(
+                    data, holdout = train_test_split(
                         data,
                         test_size=holdout_size,
                         random_state=self.random_state,
@@ -784,7 +782,7 @@ def _no_data_sets(
                 else:
                     holdout = None
 
-                train, test = splitter(
+                train, test = train_test_split(
                     data,
                     test_size=test_size,
                     random_state=self.random_state,