Merge branch 'main' into bug_final_branch

Author: afonso-antunes

Diff for: .github/CODEOWNERS

@@ -10,10 +10,8 @@ doc/source/development            @noatamir
 
 # pandas
 pandas/_libs/                     @WillAyd
-pandas/_libs/tslibs/*             @MarcoGorelli
 pandas/_typing.py                 @Dr-Irv
 pandas/core/groupby/*             @rhshadrach
-pandas/core/tools/datetimes.py    @MarcoGorelli
 pandas/io/excel/*                 @rhshadrach
 pandas/io/formats/style.py        @attack68
 pandas/io/formats/style_render.py @attack68

Diff for: .github/workflows/wheels.yml

@@ -153,7 +153,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/[email protected].0
+        uses: pypa/[email protected].2
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

Diff for: Dockerfile

@@ -13,5 +13,5 @@ COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
 RUN git config --global --add safe.directory /home/pandas
 
-ENV SHELL "/bin/bash"
+ENV SHELL="/bin/bash"
 CMD ["/bin/bash"]

Diff for: asv_bench/benchmarks/rolling.py

@@ -10,7 +10,19 @@ class Methods:
         ["DataFrame", "Series"],
         [("rolling", {"window": 10}), ("rolling", {"window": 1000}), ("expanding", {})],
         ["int", "float"],
-        ["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum", "sem"],
+        [
+            "median",
+            "mean",
+            "max",
+            "min",
+            "std",
+            "count",
+            "skew",
+            "kurt",
+            "sum",
+            "sem",
+            "nunique",
+        ],
     )
     param_names = ["constructor", "window_kwargs", "dtype", "method"]
 

Diff for: ci/code_checks.sh

@@ -72,17 +72,23 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Timedelta.max PR02" \
-        -i "pandas.Timedelta.min PR02" \
-        -i "pandas.Timedelta.resolution PR02" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.resolution PR02" \
-        -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.n GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.normalize GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.rule_code GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.startingMonth GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.n GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.normalize GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.rule_code GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.normalize GL08" \
@@ -185,6 +191,16 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.FY5253Quarter.variation GL08" \
         -i "pandas.tseries.offsets.FY5253Quarter.weekday GL08" \
         -i "pandas.tseries.offsets.FY5253Quarter.year_has_extra_week GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.n GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.normalize GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.rule_code GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.startingMonth GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.n GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.normalize GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.rule_code GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.Hour.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Hour.n GL08" \
         -i "pandas.tseries.offsets.Hour.normalize GL08" \

Diff for: ci/meta.yaml

@@ -89,4 +89,3 @@ extra:
     - datapythonista
     - phofl
     - lithomas1
-    - marcogorelli

Diff for: doc/source/development/contributing_codebase.rst

@@ -537,7 +537,7 @@ Preferred ``pytest`` idioms
     test and does not check if the test will fail. If this is the behavior you desire, use ``pytest.skip`` instead.
 
 If a test is known to fail but the manner in which it fails
-is not meant to be captured, use ``pytest.mark.xfail`` It is common to use this method for a test that
+is not meant to be captured, use ``pytest.mark.xfail``. It is common to use this method for a test that
 exhibits buggy behavior or a non-implemented feature. If
 the failing test has flaky behavior, use the argument ``strict=False``. This
 will make it so pytest does not fail if the test happens to pass. Using ``strict=False`` is highly undesirable, please use it only as a last resort.

Diff for: doc/source/development/debugging_extensions.rst

@@ -23,7 +23,7 @@ By default building pandas from source will generate a release build. To generat
 
 .. note::
 
-   conda environments update CFLAGS/CPPFLAGS with flags that are geared towards generating releases. If using conda, you may need to set ``CFLAGS="$CFLAGS -O0"`` and ``CPPFLAGS="$CPPFLAGS -O0"`` to ensure optimizations are turned off for debugging
+   conda environments update CFLAGS/CPPFLAGS with flags that are geared towards generating releases, and may work counter towards usage in a development environment. If using conda, you should unset these environment variables via ``export CFLAGS=`` and ``export CPPFLAGS=``
 
 By specifying ``builddir="debug"`` all of the targets will be built and placed in the debug directory relative to the project root. This helps to keep your debug and release artifacts separate; you are of course able to choose a different directory name or omit altogether if you do not care to separate build types.
 

Diff for: doc/source/getting_started/overview.rst

@@ -174,3 +174,4 @@ License
 -------
 
 .. literalinclude:: ../../../LICENSE
+   :language: none

Diff for: doc/source/reference/offset_frequency.rst

@@ -776,6 +776,146 @@ Methods
     QuarterBegin.is_year_start
     QuarterBegin.is_year_end
 
+BHalfYearEnd
+------------
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearEnd
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearEnd.freqstr
+    BHalfYearEnd.kwds
+    BHalfYearEnd.name
+    BHalfYearEnd.nanos
+    BHalfYearEnd.normalize
+    BHalfYearEnd.rule_code
+    BHalfYearEnd.n
+    BHalfYearEnd.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearEnd.copy
+    BHalfYearEnd.is_on_offset
+    BHalfYearEnd.is_month_start
+    BHalfYearEnd.is_month_end
+    BHalfYearEnd.is_quarter_start
+    BHalfYearEnd.is_quarter_end
+    BHalfYearEnd.is_year_start
+    BHalfYearEnd.is_year_end
+
+BHalfYearBegin
+--------------
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearBegin
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearBegin.freqstr
+    BHalfYearBegin.kwds
+    BHalfYearBegin.name
+    BHalfYearBegin.nanos
+    BHalfYearBegin.normalize
+    BHalfYearBegin.rule_code
+    BHalfYearBegin.n
+    BHalfYearBegin.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearBegin.copy
+    BHalfYearBegin.is_on_offset
+    BHalfYearBegin.is_month_start
+    BHalfYearBegin.is_month_end
+    BHalfYearBegin.is_quarter_start
+    BHalfYearBegin.is_quarter_end
+    BHalfYearBegin.is_year_start
+    BHalfYearBegin.is_year_end
+
+HalfYearEnd
+-----------
+.. autosummary::
+   :toctree: api/
+
+    HalfYearEnd
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearEnd.freqstr
+    HalfYearEnd.kwds
+    HalfYearEnd.name
+    HalfYearEnd.nanos
+    HalfYearEnd.normalize
+    HalfYearEnd.rule_code
+    HalfYearEnd.n
+    HalfYearEnd.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearEnd.copy
+    HalfYearEnd.is_on_offset
+    HalfYearEnd.is_month_start
+    HalfYearEnd.is_month_end
+    HalfYearEnd.is_quarter_start
+    HalfYearEnd.is_quarter_end
+    HalfYearEnd.is_year_start
+    HalfYearEnd.is_year_end
+
+HalfYearBegin
+-------------
+.. autosummary::
+   :toctree: api/
+
+    HalfYearBegin
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearBegin.freqstr
+    HalfYearBegin.kwds
+    HalfYearBegin.name
+    HalfYearBegin.nanos
+    HalfYearBegin.normalize
+    HalfYearBegin.rule_code
+    HalfYearBegin.n
+    HalfYearBegin.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearBegin.copy
+    HalfYearBegin.is_on_offset
+    HalfYearBegin.is_month_start
+    HalfYearBegin.is_month_end
+    HalfYearBegin.is_quarter_start
+    HalfYearBegin.is_quarter_end
+    HalfYearBegin.is_year_start
+    HalfYearBegin.is_year_end
+
 BYearEnd
 --------
 .. autosummary::

Diff for: doc/source/reference/window.rst

@@ -42,6 +42,7 @@ Rolling window functions
    Rolling.quantile
    Rolling.sem
    Rolling.rank
+   Rolling.nunique
 
 .. _api.functions_window:
 
@@ -86,6 +87,7 @@ Expanding window functions
    Expanding.quantile
    Expanding.sem
    Expanding.rank
+   Expanding.nunique
 
 .. _api.functions_ewm:
 

Diff for: doc/source/user_guide/basics.rst

@@ -36,7 +36,7 @@ of elements to display is five, but you may pass a custom number.
 Attributes and underlying data
 ------------------------------
 
-pandas objects have a number of attributes enabling you to access the metadata
+pandas objects have a number of attributes enabling you to access the metadata.
 
 * **shape**: gives the axis dimensions of the object, consistent with ndarray
 * Axis labels
@@ -59,7 +59,7 @@ NumPy's type system to add support for custom arrays
 (see :ref:`basics.dtypes`).
 
 To get the actual data inside a :class:`Index` or :class:`Series`, use
-the ``.array`` property
+the ``.array`` property.
 
 .. ipython:: python
 
@@ -88,18 +88,18 @@ NumPy doesn't have a dtype to represent timezone-aware datetimes, so there
 are two possibly useful representations:
 
 1. An object-dtype :class:`numpy.ndarray` with :class:`Timestamp` objects, each
-   with the correct ``tz``
+   with the correct ``tz``.
 2. A ``datetime64[ns]`` -dtype :class:`numpy.ndarray`, where the values have
-   been converted to UTC and the timezone discarded
+   been converted to UTC and the timezone discarded.
 
-Timezones may be preserved with ``dtype=object``
+Timezones may be preserved with ``dtype=object``:
 
 .. ipython:: python
 
    ser = pd.Series(pd.date_range("2000", periods=2, tz="CET"))
    ser.to_numpy(dtype=object)
 
-Or thrown away with ``dtype='datetime64[ns]'``
+Or thrown away with ``dtype='datetime64[ns]'``:
 
 .. ipython:: python
 

Diff for: doc/source/user_guide/timeseries.rst

@@ -891,6 +891,10 @@ into ``freq`` keyword arguments. The available date offsets and associated frequ
     :class:`~pandas.tseries.offsets.BQuarterEnd`, ``'BQE``, "business quarter end"
     :class:`~pandas.tseries.offsets.BQuarterBegin`, ``'BQS'``, "business quarter begin"
     :class:`~pandas.tseries.offsets.FY5253Quarter`, ``'REQ'``, "retail (aka 52-53 week) quarter"
+    :class:`~pandas.tseries.offsets.HalfYearEnd`, ``'HYE'``, "calendar half year end"
+    :class:`~pandas.tseries.offsets.HalfYearBegin`, ``'HYS'``, "calendar half year begin"
+    :class:`~pandas.tseries.offsets.BHalfYearEnd`, ``'BHYE``, "business half year end"
+    :class:`~pandas.tseries.offsets.BHalfYearBegin`, ``'BHYS'``, "business half year begin"
     :class:`~pandas.tseries.offsets.YearEnd`, ``'YE'``, "calendar year end"
     :class:`~pandas.tseries.offsets.YearBegin`, ``'YS'`` or ``'BYS'``,"calendar year begin"
     :class:`~pandas.tseries.offsets.BYearEnd`, ``'BYE'``, "business year end"

Diff for: doc/source/whatsnew/v2.3.0.rst

@@ -37,6 +37,7 @@ Other enhancements
   updated to work correctly with NumPy >= 2 (:issue:`57739`)
 - :meth:`Series.str.decode` result now has ``StringDtype`` when ``future.infer_string`` is True (:issue:`60709`)
 - :meth:`~Series.to_hdf` and :meth:`~DataFrame.to_hdf` now round-trip with ``StringDtype``  (:issue:`60663`)
+- Improved ``repr`` of :class:`.NumpyExtensionArray` to account for NEP51 (:issue:`61085`)
 - The :meth:`Series.str.decode` has gained the argument ``dtype`` to control the dtype of the result (:issue:`60940`)
 - The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns (:issue:`60633`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)
@@ -118,6 +119,7 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`DataFrame.sum` with ``axis=1``, :meth:`.DataFrameGroupBy.sum` or :meth:`.SeriesGroupBy.sum` with ``skipna=True``, and :meth:`.Resampler.sum` on :class:`StringDtype` with all NA values resulted in ``0`` and is now the empty string ``""`` (:issue:`60229`)
 - Bug in :meth:`Series.__pos__` and :meth:`DataFrame.__pos__` did not raise for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`60710`)
 - Bug in :meth:`Series.rank` for :class:`StringDtype` with ``storage="pyarrow"`` incorrectly returning integer results in case of ``method="average"`` and raising an error if it would truncate results (:issue:`59768`)
 - Bug in :meth:`Series.replace` with :class:`StringDtype` when replacing with a non-string value was not upcasting to ``object`` dtype (:issue:`60282`)