fixed tests

Author: PaulWestenthanner

category_encoders/gray.py

@@ -96,8 +96,9 @@ def _fit(self, X, y=None, **kwargs):
             col = col_to_encode["col"]
             bin_mapping = col_to_encode["mapping"]
             n_cols_out = bin_mapping.shape[1]
-            map_null = bin_mapping[bin_mapping.index < 0]
-            map_non_null = bin_mapping[bin_mapping.index >= 0].copy()
+            null_cond = (bin_mapping.index < 0) | (bin_mapping.isnull().all(1))
+            map_null = bin_mapping[null_cond]
+            map_non_null = bin_mapping[~null_cond].copy()
             ordinal_mapping = [m for m in self.ordinal_encoder.mapping if m.get("col") == col]
             if len(ordinal_mapping) != 1:
                 raise ValueError("Cannot find ordinal encoder mapping of Gray encoder")

tests/test_encoders.py

@@ -624,13 +624,17 @@ def test_metamorphic(self):
                 result5 = enc5.fit_transform(x5, y)
                 self.assertTrue((result1.values == result5.values).all())
 
-                enc6 = getattr(encoders, encoder_name)()
-                result6 = enc6.fit_transform(x6, y)
-                self.assertTrue((result1.values == result6.values).all())
-
-                enc7 = getattr(encoders, encoder_name)()
-                result7 = enc7.fit_transform(x7, y)
-                self.assertTrue((result1.values == result7.values).all())
+                # gray encoder re-orders inputs so that nan is last, hence the output is changed
+                if encoder_name != "GrayEncoder":
+                    enc6 = getattr(encoders, encoder_name)()
+                    result6 = enc6.fit_transform(x6, y)
+                    self.assertTrue((result1.values == result6.values).all())
+
+                # gray encoder actually does re-order inputs
+                if encoder_name != "GrayEncoder":
+                    enc7 = getattr(encoders, encoder_name)()
+                    result7 = enc7.fit_transform(x7, y)
+                    self.assertTrue((result1.values == result7.values).all())
 
                 # Arguments
                 enc9 = getattr(encoders, encoder_name)(return_df=False)