Fix TypeError when merging categorical dates

pandas/core/reshape/merge.py

@@ -877,7 +877,7 @@ def _get_merge_keys(self):
         return left_keys, right_keys, join_names
 
     def _maybe_coerce_merge_keys(self):
-        # we have valid mergee's but we may have to further
+        # we have valid mergees but we may have to further
         # coerce these if they are originally incompatible types
         #
         # for example if these are categorical, but are not dtype_equal
@@ -894,6 +894,7 @@ def _maybe_coerce_merge_keys(self):
             if is_categorical_dtype(lk) and is_categorical_dtype(rk):
                 if lk.is_dtype_equal(rk):
                     continue
+
             elif is_categorical_dtype(lk) or is_categorical_dtype(rk):
                 pass
 
@@ -904,7 +905,7 @@ def _maybe_coerce_merge_keys(self):
             # kinds to proceed, eg. int64 and int8
             # further if we are object, but we infer to
             # the same, then proceed
-            if (is_numeric_dtype(lk) and is_numeric_dtype(rk)):
+            if is_numeric_dtype(lk) and is_numeric_dtype(rk):
                 if lk.dtype.kind == rk.dtype.kind:
                     continue
 
@@ -915,11 +916,15 @@ def _maybe_coerce_merge_keys(self):
             # Houston, we have a problem!
             # let's coerce to object
             if name in self.left.columns:
+                cat = is_categorical_dtype(lk)
+                typ = lk.categories.dtype if cat else object
                 self.left = self.left.assign(
-                    **{name: self.left[name].astype(object)})
+                    **{name: self.left[name].astype(typ)})
             if name in self.right.columns:
+                cat = is_categorical_dtype(rk)
+                typ = rk.categories.dtype if cat else object
                 self.right = self.right.assign(
-                    **{name: self.right[name].astype(object)})
+                    **{name: self.right[name].astype(typ)})
 
     def _validate_specification(self):
         # Hm, any way to make this logic less complicated??

pandas/tests/reshape/test_merge.py

@@ -1,7 +1,7 @@
 # pylint: disable=E1103
 
 import pytest
-from datetime import datetime
+from datetime import datetime, date
 from numpy.random import randn
 from numpy import nan
 import numpy as np
@@ -1515,6 +1515,33 @@ def test_self_join_multiple_categories(self):
 
         assert_frame_equal(result, df)
 
+    def test_categorical_dates(self):
+        # GH 16900
+        # dates should not be coerced to ints
+
+        df = pd.DataFrame(
+            [[date(2001, 1, 1), 1.1],
+             [date(2001, 1, 2), 1.3]],
+            columns=['date', 'num2']
+        )
+        df['date'] = df['date'].astype('category')
+
+        df2 = pd.DataFrame(
+            [[date(2001, 1, 1), 1.3],
+             [date(2001, 1, 3), 1.4]],
+            columns=['date', 'num4']
+        )
+        df2['date'] = df2['date'].astype('category')
+
+        result = pd.merge(df, df2, how='outer', on=['date'])
+        assert result.shape == (3, 3)
+        assert result['date'].iloc[0] == pd.Timestamp('2001-01-01')
+        assert result['date'].iloc[-1] == pd.Timestamp('2001-01-03')
+
+        result_inner = pd.merge(df, df2, how='inner', on=['date'])
+        assert result_inner.shape == (1, 3)
+        assert result_inner['date'].iloc[-1] == pd.Timestamp('2001-01-01')
+
 
 @pytest.fixture
 def left_df():