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

@@ -3674,6 +3674,14 @@ def get_indexer(
  orig_target = target
  target = self._maybe_cast_listlike_indexer(target)
 
+ from pandas.api.types import is_timedelta64_dtype
+
+ if target.dtype == "string[pyarrow]" and is_timedelta64_dtype(self.dtype):
+ from pandas.core.arrays.timedeltas import sequence_to_td64ns
+
+ data, freq = sequence_to_td64ns(target, copy=False, unit=None)
+ target = type(target)(data)
+
  self._check_indexing_method(method, limit, tolerance)
 
  if not self._index_as_unique:

pandas/core/indexes/datetimes.py

@@ -384,6 +384,18 @@ def _is_comparable_dtype(self, dtype: DtypeObj) -> bool:
  if self.tz is not None:
  # If we have tz, we can compare to tzaware
  return isinstance(dtype, DatetimeTZDtype)
+
+ from pandas import ArrowDtype
+
+ if isinstance(dtype, ArrowDtype):
+ import pyarrow as pa
+
+ return (
+ pa.types.is_date32(dtype.pyarrow_dtype)
+ or pa.types.is_date64(dtype.pyarrow_dtype)
+ or pa.types.is_timestamp(dtype.pyarrow_dtype)
+ )
+
  # if we dont have tz, we can only compare to tznaive
  return lib.is_np_dtype(dtype, "M")
 

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 +163,20 @@ 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_temporal(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 = 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)))