Merge remote-tracking branch 'upstream/main' into cln/isin/datelike

doc/source/whatsnew/v3.0.0.rst

@@ -221,6 +221,7 @@ Removal of prior version deprecations/changes
 - :func:`read_excel`, :func:`read_json`, :func:`read_html`, and :func:`read_xml` no longer accept raw string or byte representation of the data. That type of data must be wrapped in a :py:class:`StringIO` or :py:class:`BytesIO` (:issue:`53767`)
 - :func:`to_datetime` with a ``unit`` specified no longer parses strings into floats, instead parses them the same way as without ``unit`` (:issue:`50735`)
 - :meth:`DataFrame.groupby` with ``as_index=False`` and aggregation methods will no longer exclude from the result the groupings that do not arise from the input (:issue:`49519`)
+- :meth:`ExtensionArray._reduce` now requires a ``keepdims: bool = False`` parameter in the signature (:issue:`52788`)
 - :meth:`Series.dt.to_pydatetime` now returns a :class:`Series` of :py:class:`datetime.datetime` objects (:issue:`52459`)
 - :meth:`SeriesGroupBy.agg` no longer pins the name of the group to the input passed to the provided ``func`` (:issue:`51703`)
 - All arguments except ``name`` in :meth:`Index.rename` are now keyword only (:issue:`56493`)
@@ -462,6 +463,7 @@ Plotting
 
 Groupby/resample/rolling
 ^^^^^^^^^^^^^^^^^^^^^^^^
+- Bug in :meth:`.DataFrameGroupBy.__len__` and :meth:`.SeriesGroupBy.__len__` would raise when the grouping contained NA values and ``dropna=False`` (:issue:`58644`)
 - Bug in :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupby.groups` that would not respect groupby argument ``dropna`` (:issue:`55919`)
 - Bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
@@ -470,7 +472,6 @@ Groupby/resample/rolling
 - 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.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:`.DataFrameGroupBy.__len__` and :meth:`.SeriesGroupBy.__len__` would raise when the grouping contained NA values and ``dropna=False`` (:issue:`58644`)
 
 
 Reshaping

pandas/core/arrays/base.py

@@ -1933,12 +1933,6 @@ def _reduce(
         keepdims : bool, default False
             If False, a scalar is returned.
             If True, the result has dimension with size one along the reduced axis.
-
-            .. versionadded:: 2.1
-
-               This parameter is not required in the _reduce signature to keep backward
-               compatibility, but will become required in the future. If the parameter
-               is not found in the method signature, a FutureWarning will be emitted.
         **kwargs
             Additional keyword arguments passed to the reduction function.
             Currently, `ddof` is the only supported kwarg.

pandas/core/frame.py

@@ -21,7 +21,6 @@
     Sequence,
 )
 import functools
-from inspect import signature
 from io import StringIO
 import itertools
 import operator
@@ -11408,28 +11407,11 @@ def func(values: np.ndarray):
             # We only use this in the case that operates on self.values
             return op(values, axis=axis, skipna=skipna, **kwds)
 
-        dtype_has_keepdims: dict[ExtensionDtype, bool] = {}
-
         def blk_func(values, axis: Axis = 1):
             if isinstance(values, ExtensionArray):
                 if not is_1d_only_ea_dtype(values.dtype):
                     return values._reduce(name, axis=1, skipna=skipna, **kwds)
-                has_keepdims = dtype_has_keepdims.get(values.dtype)
-                if has_keepdims is None:
-                    sign = signature(values._reduce)
-                    has_keepdims = "keepdims" in sign.parameters
-                    dtype_has_keepdims[values.dtype] = has_keepdims
-                if has_keepdims:
-                    return values._reduce(name, skipna=skipna, keepdims=True, **kwds)
-                else:
-                    warnings.warn(
-                        f"{type(values)}._reduce will require a `keepdims` parameter "
-                        "in the future",
-                        FutureWarning,
-                        stacklevel=find_stack_level(),
-                    )
-                    result = values._reduce(name, skipna=skipna, **kwds)
-                    return np.array([result])
+                return values._reduce(name, skipna=skipna, keepdims=True, **kwds)
             else:
                 return op(values, axis=axis, skipna=skipna, **kwds)
 

pandas/io/orc.py

@@ -73,7 +73,7 @@ def read_orc(
         .. versionadded:: 2.0
 
     filesystem : fsspec or pyarrow filesystem, default None
-        Filesystem object to use when reading the parquet file.
+        Filesystem object to use when reading the orc file.
 
         .. versionadded:: 2.1.0
 
@@ -99,7 +99,7 @@ def read_orc(
     --------
     >>> result = pd.read_orc("example_pa.orc")  # doctest: +SKIP
     """
-    # we require a newer version of pyarrow than we support for parquet
+    # we require a newer version of pyarrow than we support for orc
 
     orc = import_optional_dependency("pyarrow.orc")