Merge branch 'stringdtype2' of github.com:lithomas1/pandas into stringdtype2

Author: lithomas1

pandas/tests/base/test_misc.py

@@ -6,6 +6,7 @@
 from pandas._config import using_pyarrow_string_dtype
 
 from pandas.compat import PYPY
+from pandas.compat.numpy import np_version_gt2
 
 from pandas.core.dtypes.common import (
     is_dtype_equal,
@@ -85,7 +86,7 @@ def test_ndarray_compat_properties(index_or_series_obj):
     PYPY or using_pyarrow_string_dtype(),
     reason="not relevant for PyPy, doesn't work properly for arrow strings",
 )
-def test_memory_usage(index_or_series_memory_obj):
+def test_memory_usage(index_or_series_memory_obj, request):
     obj = index_or_series_memory_obj
     # Clear index caches so that len(obj) == 0 report 0 memory usage
     if isinstance(obj, Series):
@@ -102,6 +103,14 @@ def test_memory_usage(index_or_series_memory_obj):
     is_categorical = isinstance(obj.dtype, pd.CategoricalDtype) or (
         is_ser and isinstance(obj.index.dtype, pd.CategoricalDtype)
     )
+    is_object_string = is_dtype_equal(obj, "string[python]") or (
+        is_ser and is_dtype_equal(obj.index.dtype, "string[python]")
+    )
+    if is_object_string and np_version_gt2:
+        mark = pytest.mark.xfail(
+            True, reason="NumPy does not expose an API to get StringDType memory usage"
+        )
+        request.applymarker(mark)
 
     if len(obj) == 0:
         expected = 0

pandas/tests/frame/test_constructors.py

@@ -3063,12 +3063,12 @@ def test_from_dict_with_columns_na_scalar(self):
             {"a": ["a", "b", "c"], "b": [1.0, 2.0, 3.0], "c": ["d", "e", "f"]},
         ],
     )
-    def test_np_string_array_object_cast(self, data):
+    def test_np_string_array(self, data):
         from numpy.dtypes import StringDType
 
         data["a"] = np.array(data["a"], dtype=StringDType())
         res = DataFrame(data)
-        assert res["a"].dtype == np.object_
+        assert res["a"].dtype == np.dtypes.StringDType()
         assert (res["a"] == data["a"]).all()