Inconsistent behaviour when calling apply() on a categorical column with missing data pandas-dev#20714 SOLVED

Author: manuhortet

pandas/core/arrays/categorical.py

@@ -1198,7 +1198,7 @@ def map(self, mapper):
                                    categories=new_categories,
                                    ordered=self.ordered)
         except ValueError:
-            return np.take(new_categories, self._codes)
+            return take_1d(new_categories, self._codes)
 
     __eq__ = _cat_compare_op('__eq__')
     __ne__ = _cat_compare_op('__ne__')

pandas/tests/series/test_apply.py

@@ -164,6 +164,15 @@ def test_apply_dict_depr(self):
         with tm.assert_produces_warning(FutureWarning):
             tsdf.A.agg({'foo': ['sum', 'mean']})
 
+    def test_apply_categorical_with_nan_values(self):
+        # GH 20714
+        s1 = pd.Series(['1-1', '1-1', np.NaN], dtype='category')
+        s1 = s1.apply(lambda x: x.split('-')[0])
+
+        s2 = pd.Series(['1', '1', np.NaN], dtype='category')
+
+        tm.assert_series_equal(s1, s2, check_dtype=False)
+
 
 class TestSeriesAggregate(TestData):