Merge branch 'target_encoding_heirarchical_columnwise' of https://github.com/nercisla/category_encoders into target_encoding_heirarchical_columnwise

Author: nercisla

category_encoders/leave_one_out.py

@@ -128,7 +128,7 @@ def fit_column_map(self, series, y):
         codes[codes == -1] = len(categories)
         categories = np.append(categories, np.nan)
 
-        return_map = pd.Series(dict([(code, category) for code, category in enumerate(categories)]))
+        return_map = pd.Series({code: category for code, category in enumerate(categories)})
 
         result = y.groupby(codes).agg(['sum', 'count'])
         return result.rename(return_map)

category_encoders/target_encoder.py

@@ -152,10 +152,7 @@ def __init__(self, verbose=0, cols=None, drop_invariant=False, return_df=True, h
     def _check_dict_key_tuples(self, d):
         min_tuple_size = min(len(v) for v in d.values())
         max_tuple_size = max(len(v) for v in d.values())
-        if min_tuple_size == max_tuple_size:
-            return True, min_tuple_size
-        else:
-            return False, min_tuple_size
+        return min_tuple_size == max_tuple_size, min_tuple_size
 
     def _fit(self, X, y, **kwargs):
         if isinstance(self.hierarchy, dict):

tests/test_target_encoder.py

@@ -258,6 +258,20 @@ def test_hierarchy_error(self):
             encoders.TargetEncoder(verbose=1, smoothing=2, min_samples_leaf=2, hierarchy=hierarchical_map,
                                      cols=['Plant'])
 
+    def test_trivial_hierarchy(self):
+        trivial_hierarchical_map = {
+            'Plant': {
+                'Plant': ('Rose', 'Daisy', 'Daffodil', 'Bluebell')
+            }
+        }
+
+        enc_hier = encoders.TargetEncoder(verbose=1, smoothing=2, min_samples_leaf=2, hierarchy=trivial_hierarchical_map,
+                                     cols=['Plant'])
+        result_hier = enc_hier.fit_transform(self.hierarchical_cat_example, self.hierarchical_cat_example['target'])
+        enc_no_hier = encoders.TargetEncoder(verbose=1, smoothing=2, min_samples_leaf=2, cols=['Plant'])
+        result_no_hier = enc_no_hier.fit_transform(self.hierarchical_cat_example, self.hierarchical_cat_example['target'])
+        pd.testing.assert_series_equal(result_hier["Plant"], result_no_hier["Plant"])
+
     def test_hierarchy_multi_level(self):
         hierarchy_multi_level_df = pd.DataFrame(
             {
@@ -291,7 +305,6 @@ def test_hierarchy_multi_level(self):
         self.assertAlmostEqual(0.2466, values[13], delta=1e-4)
         self.assertAlmostEqual(0.4741, values[14], delta=1e-4)
 
-
     def test_hierarchy_columnwise_compass(self):
         X, y = load_compass()
         cols = X.columns[~X.columns.str.startswith('HIER')]
@@ -341,4 +354,4 @@ def test_hierarchy_mapping_cols_missing(self):
         enc = encoders.TargetEncoder(verbose=1, smoothing=2, min_samples_leaf=2, hierarchy=hierarchical_map,
                                                         cols=['Compass'])
         with self.assertRaises(ValueError):
-            enc.fit_transform(X, y)
+            enc.fit_transform(X, y)