Merge remote-tracking branch 'upstream/main' into add-pandas-merge-how-param-validation

Author: KevsterAmp

doc/source/development/contributing.rst

@@ -74,7 +74,6 @@ If you are new to Git, you can reference some of these resources for learning Gi
 to the :ref:`contributor community <community>` for help if needed:
 
 * `Git documentation <https://git-scm.com/doc>`_.
-* `Numpy's Git resources <https://numpy.org/doc/stable/dev/gitwash/git_resources.html>`_ tutorial.
 
 Also, the project follows a forking workflow further described on this page whereby
 contributors fork the repository, make changes and then create a pull request.

pandas/_libs/lib.pyx

@@ -2702,7 +2702,7 @@ def maybe_convert_objects(ndarray[object] objects,
         if using_string_dtype() and is_string_array(objects, skipna=True):
             from pandas.core.arrays.string_ import StringDtype
 
-            dtype = StringDtype(storage="pyarrow", na_value=np.nan)
+            dtype = StringDtype(na_value=np.nan)
             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

@@ -796,6 +796,24 @@ 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"
+        and left.dtype.na_value is np.nan
+    ):
+        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"
+        and right.dtype.na_value is np.nan
+    ):
+        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:
@@ -1158,7 +1176,10 @@ def assert_frame_equal(
         Specify how to compare internal data. If False, compare by columns.
         If True, compare by blocks.
     check_exact : bool, default False
-        Whether to compare number exactly.
+        Whether to compare number exactly. If False, the comparison uses the
+        relative tolerance (``rtol``) and absolute tolerance (``atol``)
+        parameters to determine if two values are considered close,
+        according to the formula: ``|a - b| <= (atol + rtol * |b|)``.
 
         .. versionchanged:: 2.2.0
 

pandas/compat/__init__.py

@@ -25,6 +25,7 @@
 )
 from pandas.compat.numpy import is_numpy_dev
 from pandas.compat.pyarrow import (
+    HAS_PYARROW,
     pa_version_under10p1,
     pa_version_under11p0,
     pa_version_under13p0,
@@ -156,6 +157,7 @@ def is_ci_environment() -> bool:
     "pa_version_under14p1",
     "pa_version_under16p0",
     "pa_version_under17p0",
+    "HAS_PYARROW",
     "IS64",
     "ISMUSL",
     "PY311",

pandas/compat/pyarrow.py

@@ -17,6 +17,7 @@
     pa_version_under15p0 = _palv < Version("15.0.0")
     pa_version_under16p0 = _palv < Version("16.0.0")
     pa_version_under17p0 = _palv < Version("17.0.0")
+    HAS_PYARROW = True
 except ImportError:
     pa_version_under10p1 = True
     pa_version_under11p0 = True
@@ -27,3 +28,4 @@
     pa_version_under15p0 = True
     pa_version_under16p0 = True
     pa_version_under17p0 = True
+    HAS_PYARROW = False

pandas/conftest.py

@@ -1313,6 +1313,7 @@ def string_storage(request):
         ("python", pd.NA),
         pytest.param(("pyarrow", pd.NA), marks=td.skip_if_no("pyarrow")),
         pytest.param(("pyarrow", np.nan), marks=td.skip_if_no("pyarrow")),
+        ("python", np.nan),
     ]
 )
 def string_dtype_arguments(request):
@@ -1374,12 +1375,14 @@ def object_dtype(request):
         ("python", pd.NA),
         pytest.param(("pyarrow", pd.NA), marks=td.skip_if_no("pyarrow")),
         pytest.param(("pyarrow", np.nan), marks=td.skip_if_no("pyarrow")),
+        ("python", np.nan),
     ],
     ids=[
         "string=object",
         "string=string[python]",
         "string=string[pyarrow]",
         "string=str[pyarrow]",
+        "string=str[python]",
     ],
 )
 def any_string_dtype(request):
@@ -1389,6 +1392,7 @@ def any_string_dtype(request):
     * 'string[python]' (NA variant)
     * 'string[pyarrow]' (NA variant)
     * 'str' (NaN variant, with pyarrow)
+    * 'str' (NaN variant, without pyarrow)
     """
     if isinstance(request.param, np.dtype):
         return request.param