Operate on categories

Author: MarcoGorelli

pandas/core/indexes/accessors.py

@@ -16,7 +16,6 @@
 from pandas.core.dtypes.generic import ABCSeries
 
 from pandas.core.accessor import PandasDelegate, delegate_names
-from pandas.core.algorithms import take_1d
 from pandas.core.arrays import DatetimeArray, PeriodArray, TimedeltaArray
 from pandas.core.base import NoNewAttributesMixin, PandasObject
 from pandas.core.indexes.datetimes import DatetimeIndex
@@ -75,9 +74,7 @@ def _delegate_property_get(self, name):
 
         result = np.asarray(result)
 
-        # blow up if we operate on categories
         if self.orig is not None:
-            result = take_1d(result, self.orig.cat.codes)
             index = self.orig.index
         else:
             index = self._parent.index
@@ -324,7 +321,11 @@ def __new__(cls, data):
 
         orig = data if is_categorical_dtype(data) else None
         if orig is not None:
-            data = Series(orig.values.categories, name=orig.name, copy=False)
+            data = Series(
+                orig.values.astype(orig.values.categories.dtype),
+                name=orig.name,
+                copy=False,
+            )
 
         if is_datetime64_dtype(data.dtype):
             return DatetimeProperties(data, orig)

pandas/tests/indexes/test_category.py

@@ -1125,3 +1125,26 @@ def test_engine_type(self, dtype, engine_type):
             ci.values._codes = ci.values._codes.astype("int64")
         assert np.issubdtype(ci.codes.dtype, dtype)
         assert isinstance(ci._engine, engine_type)
+
+    def test_dt_tz_localize(self, tz_aware_fixture):
+        # GH 27952
+        tz = tz_aware_fixture
+        datetimes = pd.Series(
+            ["2019-01-01", "2019-01-01", "2019-01-02"], dtype="datetime64[ns]"
+        )
+        categorical = datetimes.astype("category")
+        result = categorical.dt.tz_localize(tz)
+        expected = datetimes.dt.tz_localize(tz)
+        tm.assert_series_equal(result, expected)
+
+    @pytest.mark.parametrize("accessor", [("year"), ("month"), ("day")])
+    def test_dt_other_accessors(self, accessor):
+        # GH 27952
+        tz = None
+        datetimes = pd.Series(
+            ["2018-01-01", "2018-01-01", "2019-01-02"], dtype="datetime64[ns]"
+        )
+        categorical = datetimes.astype("category")
+        result = getattr(categorical.dt, accessor)
+        expected = getattr(datetimes.dt, accessor)
+        tm.assert_series_equal(result, expected)