Fix StringArray.astype for category dtype

pandas/core/arrays/string_.py

@@ -27,6 +27,7 @@
     is_array_like,
     is_bool_dtype,
     is_dtype_equal,
+    is_extension_array_dtype,
     is_integer_dtype,
     is_object_dtype,
     is_string_dtype,
@@ -307,7 +308,6 @@ def __setitem__(self, key, value):
 
     def astype(self, dtype, copy=True):
         dtype = pandas_dtype(dtype)
-
         if is_dtype_equal(dtype, self.dtype):
             if copy:
                 return self.copy()
@@ -327,6 +327,9 @@ def astype(self, dtype, copy=True):
             arr[mask] = "0"
             values = arr.astype(dtype.numpy_dtype)
             return FloatingArray(values, mask, copy=False)
+        elif is_extension_array_dtype(dtype):
+            cls = dtype.construct_array_type()
+            return cls._from_sequence(self, dtype=dtype, copy=copy)
         elif np.issubdtype(dtype, np.floating):
             arr = self._ndarray.copy()
             mask = self.isna()

pandas/tests/series/methods/test_astype.py

@@ -350,6 +350,39 @@ def test_astype_bytes(self):
         assert result.dtypes == np.dtype("S3")
 
 
+class TestAstypeString:
+    @pytest.mark.parametrize(
+        "data, dtype",
+        [
+            (["A", NA], "category"),
+            (["2020-10-10", "2020-10-10"], "datetime64[ns]"),
+            (["2020-10-10", "2020-10-10", NaT], "datetime64[ns]"),
+            (
+                ["2012-01-01 00:00:00-05:00", NaT],
+                "datetime64[ns, US/Eastern]",
+            ),
+            ([1, None], "UInt16"),
+            (["1/1/2021", "2/1/2021"], "period[M]"),
+            (["1/1/2021", "2/1/2021", NaT], "period[M]"),
+            (["1 Day", "59 Days", NaT], "timedelta64[ns]"),
+            # currently no way to parse BooleanArray, IntervalArray from a
+            # list of strings
+        ],
+    )
+    def test_astype_string_to_extension_dtype_roundtrip(self, data, dtype, request):
+        if dtype in ("timedelta64[ns]"):
+            mark = pytest.mark.xfail(reason="TODO fix is_extension_array_dtype GH40478")
+            request.node.add_marker(mark)
+        if NaT in data and dtype in ("period[M]", "datetime64[ns]"):
+            mark = pytest.mark.xfail(
+                reason="TODO StringArray.astype() None to dtype.na_value conversion"
+            )
+            request.node.add_marker(mark)
+        # GH-40351
+        s = Series(data, dtype=dtype)
+        tm.assert_series_equal(s, s.astype("string").astype(dtype))
+
+
 class TestAstypeCategorical:
     def test_astype_categorical_to_other(self):
         cat = Categorical([f"{i} - {i + 499}" for i in range(0, 10000, 500)])
@@ -470,6 +503,18 @@ def test_astype_categories_raises(self):
         with pytest.raises(TypeError, match="got an unexpected"):
             s.astype("category", categories=["a", "b"], ordered=True)
 
+    def test_astype_str_to_extension_dtype(self):
+        # GH-40351
+        s = Series(["A", np.NaN], dtype="string")
+        result = s.astype("category")
+        expected = Series(["A", np.NaN], dtype="category")
+        tm.assert_series_equal(result, expected)
+
+        s = Series(["1/1/2021", "2/1/2021"], dtype="string")
+        result = s.astype("period[M]")
+        expected = Series(["1/1/2021", "2/1/2021"], dtype="period[M]")
+        tm.assert_series_equal(result, expected)
+
     @pytest.mark.parametrize("items", [["a", "b", "c", "a"], [1, 2, 3, 1]])
     def test_astype_from_categorical(self, items):
         ser = Series(items)