Merge remote-tracking branch 'upstream/main' into string-dtype-alias

Author: jorisvandenbossche

ci/code_checks.sh

@@ -164,7 +164,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.center RT03,SA01" \
         -i "pandas.Series.str.decode PR07,RT03,SA01" \
         -i "pandas.Series.str.encode PR07,RT03,SA01" \
-        -i "pandas.Series.str.fullmatch RT03" \
         -i "pandas.Series.str.index RT03" \
         -i "pandas.Series.str.ljust RT03,SA01" \
         -i "pandas.Series.str.lower RT03" \

doc/source/whatsnew/v3.0.0.rst

@@ -610,6 +610,7 @@ Groupby/resample/rolling
 - Bug in :meth:`DataFrameGroupBy.agg` that raises ``AttributeError`` when there is dictionary input and duplicated columns, instead of returning a DataFrame with the aggregation of all duplicate columns. (:issue:`55041`)
 - Bug in :meth:`DataFrameGroupBy.apply` that was returning a completely empty DataFrame when all return values of ``func`` were ``None`` instead of returning an empty DataFrame with the original columns and dtypes. (:issue:`57775`)
 - Bug in :meth:`DataFrameGroupBy.apply` with ``as_index=False`` that was returning :class:`MultiIndex` instead of returning :class:`Index`. (:issue:`58291`)
+- Bug in :meth:`DataFrameGroupBy.cumsum` and :meth:`DataFrameGroupBy.cumprod` where ``numeric_only`` parameter was passed indirectly through kwargs instead of passing directly. (:issue:`58811`)
 - Bug in :meth:`DataFrameGroupBy.cumsum` where it did not return the correct dtype when the label contained ``None``. (:issue:`58811`)
 - Bug in :meth:`DataFrameGroupby.transform` and :meth:`SeriesGroupby.transform` with a reducer and ``observed=False`` that coerces dtype to float when there are unobserved categories. (:issue:`55326`)
 - Bug in :meth:`Rolling.apply` where the applied function could be called on fewer than ``min_period`` periods if ``method="table"``. (:issue:`58868`)

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:

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