BUG: DatetimeArray.astype(Sparse) (#50082)

* BUG: DatetimeArray.astype(Sparse)

* GH ref

Author: jbrockmendel

doc/source/whatsnew/v2.0.0.rst

@@ -791,6 +791,7 @@ Reshaping
 Sparse
 ^^^^^^
 - Bug in :meth:`Series.astype` when converting a ``SparseDtype`` with ``datetime64[ns]`` subtype to ``int64`` dtype raising, inconsistent with the non-sparse behavior (:issue:`49631`)
+- Bug in :meth:`Series.astype` when converting a from ``datetime64[ns]`` to ``Sparse[datetime64[ns]]`` incorrectly raising (:issue:`50082`)
 -
 
 ExtensionArray

pandas/core/arrays/datetimes.py

@@ -74,7 +74,10 @@
     is_timedelta64_dtype,
     pandas_dtype,
 )
-from pandas.core.dtypes.dtypes import DatetimeTZDtype
+from pandas.core.dtypes.dtypes import (
+    DatetimeTZDtype,
+    ExtensionDtype,
+)
 from pandas.core.dtypes.missing import isna
 
 from pandas.core.arrays import datetimelike as dtl
@@ -645,6 +648,25 @@ def astype(self, dtype, copy: bool = True):
                 return self.copy()
             return self
 
+        elif isinstance(dtype, ExtensionDtype):
+            if not isinstance(dtype, DatetimeTZDtype):
+                # e.g. Sparse[datetime64[ns]]
+                return super().astype(dtype, copy=copy)
+            elif self.tz is None:
+                # pre-2.0 this did self.tz_localize(dtype.tz), which did not match
+                #  the Series behavior which did
+                #  values.tz_localize("UTC").tz_convert(dtype.tz)
+                raise TypeError(
+                    "Cannot use .astype to convert from timezone-naive dtype to "
+                    "timezone-aware dtype. Use obj.tz_localize instead or "
+                    "series.dt.tz_localize instead"
+                )
+            else:
+                # tzaware unit conversion e.g. datetime64[s, UTC]
+                np_dtype = np.dtype(dtype.str)
+                res_values = astype_overflowsafe(self._ndarray, np_dtype, copy=copy)
+                return type(self)._simple_new(res_values, dtype=dtype, freq=self.freq)
+
         elif (
             self.tz is None
             and is_datetime64_dtype(dtype)
@@ -656,22 +678,6 @@ def astype(self, dtype, copy: bool = True):
             return type(self)._simple_new(res_values, dtype=res_values.dtype)
             # TODO: preserve freq?
 
-        elif self.tz is not None and isinstance(dtype, DatetimeTZDtype):
-            # tzaware unit conversion e.g. datetime64[s, UTC]
-            np_dtype = np.dtype(dtype.str)
-            res_values = astype_overflowsafe(self._ndarray, np_dtype, copy=copy)
-            return type(self)._simple_new(res_values, dtype=dtype, freq=self.freq)
-
-        elif self.tz is None and isinstance(dtype, DatetimeTZDtype):
-            # pre-2.0 this did self.tz_localize(dtype.tz), which did not match
-            #  the Series behavior which did
-            #  values.tz_localize("UTC").tz_convert(dtype.tz)
-            raise TypeError(
-                "Cannot use .astype to convert from timezone-naive dtype to "
-                "timezone-aware dtype. Use obj.tz_localize instead or "
-                "series.dt.tz_localize instead"
-            )
-
         elif self.tz is not None and is_datetime64_dtype(dtype):
             # pre-2.0 behavior for DTA/DTI was
             #  values.tz_convert("UTC").tz_localize(None), which did not match

pandas/tests/arrays/test_datetimes.py

@@ -403,6 +403,15 @@ def test_astype_int(self, dtype):
         assert result.dtype == expected_dtype
         tm.assert_numpy_array_equal(result, expected)
 
+    def test_astype_to_sparse_dt64(self):
+        # GH#50082
+        dti = pd.date_range("2016-01-01", periods=4)
+        dta = dti._data
+        result = dta.astype("Sparse[datetime64[ns]]")
+
+        assert result.dtype == "Sparse[datetime64[ns]]"
+        assert (result == dta).all()
+
     def test_tz_setter_raises(self):
         arr = DatetimeArray._from_sequence(
             ["2000"], dtype=DatetimeTZDtype(tz="US/Central")