Merge branch 'main' into depr-tuple-arith

Author: jbrockmendel

.github/workflows/unit-tests.yml

@@ -181,8 +181,7 @@ jobs:
     timeout-minutes: 90
     strategy:
       matrix:
-        # Note: Don't use macOS latest since macos 14 appears to be arm64 only
-        os: [macos-13, macos-14, windows-2025]
+        os: [macos-15-intel, macos-15, windows-2025]
         env_file: [actions-311.yaml, actions-312.yaml, actions-313.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
@@ -399,7 +398,7 @@ jobs:
           pyodide build
 
       - name: Set up Node.js
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v6
         with:
           node-version: '20'
 

.github/workflows/wheels.yml

@@ -98,10 +98,9 @@ jobs:
         - [ubuntu-24.04, musllinux_x86_64]
         - [ubuntu-24.04-arm, manylinux_aarch64]
         - [ubuntu-24.04-arm, musllinux_aarch64]
-        - [macos-13, macosx_x86_64]
-        # Note: M1 images on Github Actions start from macOS 14
-        - [macos-14, macosx_arm64]
-        - [windows-2022, win_amd64]
+        - [macos-15-intel, macosx_x86_64]
+        - [macos-15, macosx_arm64]
+        - [windows-2025, win_amd64]
         - [windows-11-arm, win_arm64]
         python: [["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"], ["cp314", "3.14"], ["cp314t", "3.14"]]
         include:

asv_bench/benchmarks/ctors.py

@@ -23,7 +23,7 @@ def gen_of_str(arr):
 
 
 def arr_dict(arr):
-    return dict(zip(range(len(arr)), arr))
+    return dict(zip(range(len(arr)), arr, strict=True))
 
 
 def list_of_tuples(arr):

asv_bench/benchmarks/series_methods.py

@@ -16,7 +16,7 @@ def setup(self):
         self.idx = date_range(
             start=datetime(2015, 10, 26), end=datetime(2016, 1, 1), freq="50s"
         )
-        self.data = dict(zip(self.idx, range(len(self.idx))))
+        self.data = dict(zip(self.idx, range(len(self.idx)), strict=True))
         self.array = np.array([1, 2, 3])
         self.idx2 = Index(["a", "b", "c"])
 
@@ -407,7 +407,9 @@ def setup(self, num_to_replace):
         self.to_replace_list = np.random.choice(self.arr, num_to_replace)
         self.values_list = np.random.choice(self.arr1, num_to_replace)
 
-        self.replace_dict = dict(zip(self.to_replace_list, self.values_list))
+        self.replace_dict = dict(
+            zip(self.to_replace_list, self.values_list, strict=True)
+        )
 
     def time_replace_dict(self, num_to_replace):
         self.ser.replace(self.replace_dict)

ci/code_checks.sh

@@ -73,10 +73,12 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.errors.IncompatibleFrequency SA01,SS06,EX01" \
+        -i "pandas.errors.InvalidVersion GL08" \
         -i "pandas.api.extensions.ExtensionArray.value_counts EX01,RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
-        -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
-        -i "pandas.core.resample.Resampler.quantile PR01,PR07" \
+        -i "pandas.api.typing.DataFrameGroupBy.plot PR02" \
+        -i "pandas.api.typing.SeriesGroupBy.plot PR02" \
+        -i "pandas.api.typing.Resampler.quantile PR01,PR07" \
+        -i "pandas.arrays.NumpyExtensionArray GL08" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BHalfYearBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BHalfYearBegin.n GL08" \

doc/source/reference/groupby.rst

@@ -5,7 +5,7 @@
 =======
 GroupBy
 =======
-.. currentmodule:: pandas.core.groupby
+.. currentmodule:: pandas.api.typing
 
 :class:`pandas.api.typing.DataFrameGroupBy` and :class:`pandas.api.typing.SeriesGroupBy`
 instances are returned by groupby calls :func:`pandas.DataFrame.groupby` and
@@ -40,7 +40,7 @@ Function application helper
 
    NamedAgg
 
-.. currentmodule:: pandas.core.groupby
+.. currentmodule:: pandas.api.typing
 
 Function application
 --------------------

doc/source/reference/resampling.rst

@@ -5,7 +5,7 @@
 ==========
 Resampling
 ==========
-.. currentmodule:: pandas.core.resample
+.. currentmodule:: pandas.api.typing
 
 :class:`pandas.api.typing.Resampler` instances are returned by
 resample calls: :func:`pandas.DataFrame.resample`, :func:`pandas.Series.resample`.

doc/source/reference/window.rst

@@ -17,7 +17,7 @@ calls: :func:`pandas.DataFrame.ewm` and :func:`pandas.Series.ewm`.
 
 Rolling window functions
 ------------------------
-.. currentmodule:: pandas.core.window.rolling
+.. currentmodule:: pandas.api.typing
 
 .. autosummary::
    :toctree: api/
@@ -48,7 +48,8 @@ Rolling window functions
 
 Weighted window functions
 -------------------------
-.. currentmodule:: pandas.core.window.rolling
+.. currentmodule:: pandas.api.typing
+
 
 .. autosummary::
    :toctree: api/
@@ -62,7 +63,8 @@ Weighted window functions
 
 Expanding window functions
 --------------------------
-.. currentmodule:: pandas.core.window.expanding
+.. currentmodule:: pandas.api.typing
+
 
 .. autosummary::
    :toctree: api/
@@ -93,7 +95,8 @@ Expanding window functions
 
 Exponentially-weighted window functions
 ---------------------------------------
-.. currentmodule:: pandas.core.window.ewm
+.. currentmodule:: pandas.api.typing
+
 
 .. autosummary::
    :toctree: api/

doc/source/user_guide/basics.rst

@@ -2372,11 +2372,18 @@ integers:
 
    df.select_dtypes(include=["number", "bool"], exclude=["unsignedinteger"])
 
-To select string columns you must use the ``object`` dtype:
+To select string columns include ``str``:
 
 .. ipython:: python
 
-   df.select_dtypes(include=["object"])
+   df.select_dtypes(include=[str])
+
+.. note::
+
+    This is a change in pandas 3.0. Previously strings were stored in ``object``
+    dtype columns, so would be selected with ``include=[object]``. See
+    :ref:`the migration guide <string_migration.select_dtypes>` for details on
+    how to write code that works with both versions.
 
 To see all the child dtypes of a generic ``dtype`` like ``numpy.number`` you
 can define a function that returns a tree of child dtypes:

doc/source/user_guide/enhancingperf.rst

@@ -455,7 +455,7 @@ by evaluate arithmetic and boolean expression all at once for large :class:`~pan
    :func:`~pandas.eval` is many orders of magnitude slower for
    smaller expressions or objects than plain Python. A good rule of thumb is
    to only use :func:`~pandas.eval` when you have a
-   :class:`~pandas.core.frame.DataFrame` with more than 10,000 rows.
+   :class:`~pandas.DataFrame` with more than 10,000 rows.
 
 Supported syntax
 ~~~~~~~~~~~~~~~~