Merge pull request #19 from emergentmethods/fix/outlier-checkl

fix: ensure outlier check isnt trying to convert the return array to df

datasieve/pipeline.py

@@ -105,7 +105,7 @@ def transform(self, X, y=None, sample_weight=None, outlier_check=False) -> Tuple
                 **self.fitparams[name]
             )
 
-        X, y, sample_weight = self._convert_back_to_df(X, y, sample_weight, feature_list)
+        X, y, sample_weight = self._convert_back_to_df(X, y, sample_weight, feature_list, outlier_check)
 
         return X, y, sample_weight
 
@@ -195,15 +195,15 @@ def _validate_arguments(self, X, y, sample_weight, fit=False, outlier_check=Fals
 
         return X, y, sample_weight
 
-    def _convert_back_to_df(self, X, y, sample_weight, feature_list):
+    def _convert_back_to_df(self, X, y, sample_weight, feature_list, outlier_check=False):
         if not self.pandas_types:
             return X, y, sample_weight
 
         assert X.shape[1] == len(feature_list)
 
         X = pd.DataFrame(X, columns=feature_list)
 
-        if y is not None:
+        if y is not None and not outlier_check:
             y = pd.DataFrame(y, columns=self.label_list)
 
         return X, y, sample_weight

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "datasieve"
-version = "0.1.5"
+version = "0.1.6"
 description = "This package implements a flexible data pipeline to help organize row removal (e.g. outlier removal) and feature modification (e.g. PCA)"
 authors = ['Robert Caulk']
 readme = "README.md"