String dtype: implement object-dtype based StringArray variant with NumPy semantics

pandas/_libs/lib.pyx

@@ -2692,7 +2692,7 @@ def maybe_convert_objects(ndarray[object] objects,
         if using_pyarrow_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(storage="pyarrow_numpy")
+            dtype = StringDtype()
             return dtype.construct_array_type()._from_sequence(objects, dtype=dtype)
 
         elif convert_to_nullable_dtype and is_string_array(objects, skipna=True):

pandas/_testing/asserters.py

@@ -805,6 +805,16 @@ def assert_extension_array_equal(
         left_na, right_na, obj=f"{obj} NA mask", index_values=index_values
     )
 
+    # Specifically for StringArrayNumpySemantics, validate here we have a valid array
+    if isinstance(left.dtype, StringDtype) and left.dtype.storage == "python_numpy":
+        assert np.all(
+            [np.isnan(val) for val in left._ndarray[left_na]]  # type: ignore[attr-defined]
+        ), "wrong missing value sentinels"
+    if isinstance(right.dtype, StringDtype) and right.dtype.storage == "python_numpy":
+        assert np.all(
+            [np.isnan(val) for val in right._ndarray[right_na]]  # type: ignore[attr-defined]
+        ), "wrong missing value sentinels"
+
     left_valid = left[~left_na].to_numpy(dtype=object)
     right_valid = right[~right_na].to_numpy(dtype=object)
     if check_exact:

pandas/compat/__init__.py

@@ -26,6 +26,7 @@
 import pandas.compat.compressors
 from pandas.compat.numpy import is_numpy_dev
 from pandas.compat.pyarrow import (
+    HAS_PYARROW,
     pa_version_under10p1,
     pa_version_under11p0,
     pa_version_under13p0,
@@ -189,6 +190,7 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
     "pa_version_under14p0",
     "pa_version_under14p1",
     "pa_version_under16p0",
+    "HAS_PYARROW",
     "IS64",
     "ISMUSL",
     "PY310",

pandas/compat/pyarrow.py

@@ -16,6 +16,7 @@
     pa_version_under14p1 = _palv < Version("14.0.1")
     pa_version_under15p0 = _palv < Version("15.0.0")
     pa_version_under16p0 = _palv < Version("16.0.0")
+    HAS_PYARROW = True
 except ImportError:
     pa_version_under10p1 = True
     pa_version_under11p0 = True
@@ -25,3 +26,4 @@
     pa_version_under14p1 = True
     pa_version_under15p0 = True
     pa_version_under16p0 = True
+    HAS_PYARROW = False

pandas/conftest.py

@@ -1292,6 +1292,7 @@ def nullable_string_dtype(request):
 @pytest.fixture(
     params=[
         "python",
+        "python_numpy",
         pytest.param("pyarrow", marks=td.skip_if_no("pyarrow")),
         pytest.param("pyarrow_numpy", marks=td.skip_if_no("pyarrow")),
     ]
@@ -1353,6 +1354,7 @@ def object_dtype(request):
     params=[
         "object",
         "string[python]",
+        "string[python_numpy]",
         pytest.param("string[pyarrow]", marks=td.skip_if_no("pyarrow")),
         pytest.param("string[pyarrow_numpy]", marks=td.skip_if_no("pyarrow")),
     ]