Merge branch 'main' into depr-unit

Author: jbrockmendel

.github/workflows/wheels.yml

@@ -162,7 +162,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v3.1.4
+        uses: pypa/cibuildwheel@v3.2.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:

asv_bench/benchmarks/algorithms.py

@@ -199,8 +199,8 @@ class SortIntegerArray:
     params = [10**3, 10**5]
 
     def setup(self, N):
-        data = np.arange(N, dtype=float)
-        data[40] = np.nan
+        data = np.arange(N, dtype=float).astype(object)
+        data[40] = pd.NA
         self.array = pd.array(data, dtype="Int64")
 
     def time_argsort(self, N):

asv_bench/benchmarks/frame_methods.py

@@ -4,6 +4,7 @@
 import numpy as np
 
 from pandas import (
+    NA,
     DataFrame,
     Index,
     MultiIndex,
@@ -445,6 +446,8 @@ def setup(self, inplace, dtype):
             values[::2] = np.nan
             if dtype == "Int64":
                 values = values.round()
+                values = values.astype(object)
+                values[::2] = NA
             self.df = DataFrame(values, dtype=dtype)
         self.fill_values = self.df.iloc[self.df.first_valid_index()].to_dict()
 

asv_bench/benchmarks/groupby.py

@@ -689,6 +689,10 @@ def setup(self, dtype, method, with_nans):
             null_vals = vals.astype(float, copy=True)
             null_vals[::2, :] = np.nan
             null_vals[::3, :] = np.nan
+            if dtype in ["Int64", "Float64"]:
+                null_vals = null_vals.astype(object)
+                null_vals[::2, :] = NA
+                null_vals[::3, :] = NA
             df = DataFrame(null_vals, columns=list("abcde"), dtype=dtype)
             df["key"] = keys
             self.df = df

doc/source/user_guide/text.rst

@@ -75,7 +75,7 @@ or convert from existing pandas data:
 
 .. ipython:: python
 
-   s1 = pd.Series([1, 2, np.nan], dtype="Int64")
+   s1 = pd.Series([1, 2, pd.NA], dtype="Int64")
    s1
    s2 = s1.astype("string")
    s2

doc/source/whatsnew/v0.21.0.rst

@@ -635,22 +635,17 @@ Previous behavior:
 
 New behavior:
 
-.. code-block:: ipython
+.. ipython:: python
 
-   In [1]: pi = pd.period_range('2017-01', periods=12, freq='M')
+   pi = pd.period_range('2017-01', periods=12, freq='M')
 
-   In [2]: s = pd.Series(np.arange(12), index=pi)
+   s = pd.Series(np.arange(12), index=pi)
 
-   In [3]: resampled = s.resample('2Q').mean()
+   resampled = s.resample('2Q').mean()
 
-   In [4]: resampled
-   Out[4]:
-   2017Q1    2.5
-   2017Q3    8.5
-   Freq: 2Q-DEC, dtype: float64
+   resampled
 
-   In [5]: resampled.index
-   Out[5]: PeriodIndex(['2017Q1', '2017Q3'], dtype='period[2Q-DEC]')
+   resampled.index
 
 Upsampling and calling ``.ohlc()`` previously returned a ``Series``, basically identical to calling ``.asfreq()``. OHLC upsampling now returns a DataFrame with columns ``open``, ``high``, ``low`` and ``close`` (:issue:`13083`). This is consistent with downsampling and ``DatetimeIndex`` behavior.
 

doc/source/whatsnew/v0.24.0.rst

@@ -50,7 +50,7 @@ marker of ``np.nan`` will infer to integer dtype. The display of the ``Series``
 
 .. ipython:: python
 
-   s = pd.Series([1, 2, np.nan], dtype='Int64')
+   s = pd.Series([1, 2, pd.NA], dtype='Int64')
    s
 
 
@@ -166,7 +166,7 @@ See the :ref:`dtypes docs <basics.dtypes>` for more on extension arrays.
 
 .. ipython:: python
 
-   pd.array([1, 2, np.nan], dtype='Int64')
+   pd.array([1, 2, pd.NA], dtype='Int64')
    pd.array(['a', 'b', 'c'], dtype='category')
 
 Passing data for which there isn't dedicated extension type (e.g. float, integer, etc.)

doc/source/whatsnew/v2.2.0.rst

@@ -664,7 +664,7 @@ Other Deprecations
 - Deprecated :meth:`DatetimeArray.__init__` and :meth:`TimedeltaArray.__init__`, use :func:`array` instead (:issue:`55623`)
 - Deprecated :meth:`Index.format`, use ``index.astype(str)`` or ``index.map(formatter)`` instead (:issue:`55413`)
 - Deprecated :meth:`Series.ravel`, the underlying array is already 1D, so ravel is not necessary (:issue:`52511`)
-- Deprecated :meth:`Series.resample` and :meth:`DataFrame.resample` with a :class:`PeriodIndex` (and the 'convention' keyword), convert to :class:`DatetimeIndex` (with ``.to_timestamp()``) before resampling instead (:issue:`53481`)
+- Deprecated :meth:`Series.resample` and :meth:`DataFrame.resample` with a :class:`PeriodIndex` (and the 'convention' keyword), convert to :class:`DatetimeIndex` (with ``.to_timestamp()``) before resampling instead (:issue:`53481`). Note: this deprecation was later undone in pandas 2.3.3 (:issue:`57033`)
 - Deprecated :meth:`Series.view`, use :meth:`Series.astype` instead to change the dtype (:issue:`20251`)
 - Deprecated :meth:`offsets.Tick.is_anchored`, use ``False`` instead (:issue:`55388`)
 - Deprecated ``core.internals`` members ``Block``, ``ExtensionBlock``, and ``DatetimeTZBlock``, use public APIs instead (:issue:`55139`)

doc/source/whatsnew/v2.3.2.rst

@@ -22,8 +22,6 @@ become the default string dtype in pandas 3.0. See
 
 Bug fixes
 ^^^^^^^^^
-- Fix :meth:`~Series.str.isdigit` to correctly recognize unicode superscript
-  characters as digits for :class:`StringDtype` backed by PyArrow (:issue:`61466`)
 - Fix :meth:`~DataFrame.to_json` with ``orient="table"`` to correctly use the
   "string" type in the JSON Table Schema for :class:`StringDtype` columns
   (:issue:`61889`)
@@ -39,4 +37,4 @@ Bug fixes
 Contributors
 ~~~~~~~~~~~~
 
-.. contributors:: v2.3.1..v2.3.2|HEAD
+.. contributors:: v2.3.1..v2.3.2

doc/source/whatsnew/v2.3.3.rst

@@ -1,14 +1,14 @@
 .. _whatsnew_233:
 
-What's new in 2.3.3 (September XX, 2025)
+What's new in 2.3.3 (September 29, 2025)
 ----------------------------------------
 
 These are the changes in pandas 2.3.3. See :ref:`release` for a full changelog
 including other versions of pandas.
 
 {{ header }}
 
-.. _whatsnew_220.py14_compat:
+.. _whatsnew_233.py14_compat:
 
 Pandas 2.3.3 is now compatible with Python 3.14
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -37,29 +37,42 @@ Improvements
   specifying ``include=["object"]`` for backwards compatibility. In a future
   release, this will be deprecated and code for pandas 3+ should be updated to
   do ``include=["str"]`` (:issue:`61916`)
-
+- Support the ``/`` operation between a ``pathlib.Path`` object and a :class:`StringDtype`
+  Series, similarly as it works for object-dtype Series (:issue:`61940`)
 
 .. _whatsnew_233.string_fixes.bugs:
 
 Bug fixes
 ^^^^^^^^^
 - Fix bug in :meth:`Series.str.replace` using named capture groups (e.g., ``\g<name>``) with the Arrow-backed dtype would raise an error (:issue:`57636`)
-- Fix regression in ``~Series.str.contains``, ``~Series.str.match`` and ``~Series.str.fullmatch``
+- Fix regression in :meth:`Series.str.contains`, :meth:`~Series.str.match` and :meth:`~Series.str.fullmatch`
   with a compiled regex and custom flags (:issue:`62240`)
-- Fix :meth:`Series.str.match` and :meth:`Series.str.fullmatch` not matching patterns with groups correctly for the Arrow-backed string dtype (:issue:`61072`)
-
-
-Improvements and fixes for Copy-on-Write
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-Bug fixes
-^^^^^^^^^
-
+- Fix :meth:`Series.str.match` and :meth:`~Series.str.fullmatch` not matching patterns with groups correctly for the Arrow-backed string dtype (:issue:`61072`)
+- Fix bug in :meth:`~DataFrame.groupby` with ``sum()`` and unobserved categories resulting in ``0`` instead of the empty string ``""`` (:issue:`61909`)
+- Fix :meth:`Series.str.isdigit` to correctly recognize unicode superscript
+  characters as digits for :class:`StringDtype` backed by PyArrow (:issue:`61466`)
+- Fix comparing a :class:`StringDtype` Series with mixed objects raising an error (:issue:`60228`)
+- Fix error being raised when using a numpy ufunc with a Python-backed string array (:issue:`40800`)
+
+Other changes
+~~~~~~~~~~~~~
+
+- The deprecation of using :meth:`Series.resample` and :meth:`DataFrame.resample`
+  with a :class:`PeriodIndex` (and the 'convention' keyword) has been undone.
+  Resampling with a :class:`PeriodIndex` is supported again, but a subset of
+  methods that return incorrect results will raise an error in pandas 3.0 (:issue:`57033`)
+
+Other bug fixes
+~~~~~~~~~~~~~~~~
+
+- Fix memory leak in :meth:`DataFrame.to_json` with datetime columns (:issue:`62204`)
+- Fixed regression in :meth:`DataFrame.from_records` not initializing subclasses properly (:issue:`57008`)
 - The :meth:`DataFrame.iloc` now works correctly with ``copy_on_write`` option when assigning values after subsetting the columns of a homogeneous DataFrame (:issue:`60309`)
 
-
 .. ---------------------------------------------------------------------------
 .. _whatsnew_233.contributors:
 
 Contributors
 ~~~~~~~~~~~~
+
+.. contributors:: v2.3.2..v2.3.3|HEAD