BUG: Fix all-NaT when ArrowEA.astype to categorical

doc/source/whatsnew/v3.0.0.rst

@@ -693,7 +693,7 @@ Categorical
 - Bug in :meth:`Categorical.astype` where ``copy=False`` would still trigger a copy of the codes (:issue:`62000`)
 - Bug in :meth:`DataFrame.pivot` and :meth:`DataFrame.set_index` raising an ``ArrowNotImplementedError`` for columns with pyarrow dictionary dtype (:issue:`53051`)
 - Bug in :meth:`Series.convert_dtypes` with ``dtype_backend="pyarrow"`` where empty :class:`CategoricalDtype` :class:`Series` raised an error or got converted to ``null[pyarrow]`` (:issue:`59934`)
--
+- Bug in :meth:`array.astype` where casting a pyarrow-backed array to a temporal :class:`CategoricalDtype` (e.g. with datetime or timedelta categories) raised or incorrectly converted values to all ``NaT`` (:issue:`62051`)
 
 Datetimelike
 ^^^^^^^^^^^^

pandas/core/indexes/base.py

@@ -3673,6 +3673,7 @@ def get_indexer(
         method = clean_reindex_fill_method(method)
         orig_target = target
         target = self._maybe_cast_listlike_indexer(target)
+        target, self = target._maybe_downcast_for_indexing(self)
 
         self._check_indexing_method(method, limit, tolerance)
 

pandas/core/indexes/datetimelike.py

@@ -43,6 +43,7 @@
 from pandas.core.dtypes.common import (
     is_integer,
     is_list_like,
+    is_timedelta64_dtype,
 )
 from pandas.core.dtypes.concat import concat_compat
 from pandas.core.dtypes.dtypes import (
@@ -57,6 +58,7 @@
     TimedeltaArray,
 )
 from pandas.core.arrays.datetimelike import DatetimeLikeArrayMixin
+from pandas.core.arrays.timedeltas import sequence_to_td64ns
 import pandas.core.common as com
 import pandas.core.indexes.base as ibase
 from pandas.core.indexes.base import (
@@ -415,7 +417,16 @@ def _maybe_cast_listlike_indexer(self, keyarr):
                 # TODO: com.asarray_tuplesafe shouldn't cast e.g. DatetimeArray
             else:
                 res = keyarr
-        return Index(res, dtype=res.dtype)
+
+        res_index = Index(res, dtype=res.dtype)
+
+        if isinstance(res, ExtensionArray):
+            if res_index.dtype == "string[pyarrow]" and is_timedelta64_dtype(
+                self.dtype
+            ):
+                data, freq = sequence_to_td64ns(res_index, copy=False, unit=None)
+                res_index = type(res_index)(data)
+        return res_index
 
 
 class DatetimeTimedeltaMixin(DatetimeIndexOpsMixin, ABC):

pandas/tests/arrays/categorical/test_astype.py

@@ -7,14 +7,17 @@
     CategoricalDtype,
     CategoricalIndex,
     DatetimeIndex,
+    Index,
     Interval,
     NaT,
     Period,
     Timestamp,
     array,
+    isna,
     to_datetime,
 )
 import pandas._testing as tm
+from pandas.core.arrays.arrow.array import ArrowExtensionArray
 
 
 class TestAstype:
@@ -160,3 +163,27 @@ def test_astype_category_readonly_mask_values(self):
         result = arr.astype("category")
         expected = array([0, 1, 2], dtype="Int64").astype("category")
         tm.assert_extension_array_equal(result, expected)
+
+    def test_arrow_array_astype_to_categorical_dtype_date(self):
+        # GH#62051
+        pytest.importorskip("pyarrow")
+        arr = array(
+            ["2017-01-01", "2018-01-01", "2019-01-01"], dtype="date32[day][pyarrow]"
+        )
+        cats = Index(["2017-01-01", "2018-01-01", "2019-01-01"], dtype="M8[s]")
+        dtype = CategoricalDtype(categories=cats, ordered=False)
+        assert not all(isna(arr.astype(dtype)))
+
+        arr_index, cats = Index(arr)._maybe_downcast_for_indexing(cats)
+        assert cats._should_compare(arr_index)
+
+    def test_arrow_array_astype_to_categorical_dtype_timedelta(self):
+        # GH#62051
+        pytest.importorskip("pyarrow")
+        arr = ArrowExtensionArray._from_sequence(["1h", "2h", "3h"])
+        cats = Index(["1h", "2h", "3h"], dtype="m8[ns]")
+        dtype = CategoricalDtype(cats, ordered=False)
+        assert not all(isna(arr.astype(dtype)))
+
+        arr_index = cats._maybe_cast_listlike_indexer(Index(arr))
+        tm.assert_index_equal(arr_index, cats)