Merge remote-tracking branch 'upstream/main' into pre-commit-ci-update-config

Author: mroeschke

.github/workflows/unit-tests.yml

@@ -107,7 +107,7 @@ jobs:
 
     services:
       mysql:
-        image: mysql:8
+        image: mysql:9
         env:
           MYSQL_ALLOW_EMPTY_PASSWORD: yes
           MYSQL_DATABASE: pandas
@@ -120,7 +120,7 @@ jobs:
           - 3306:3306
 
       postgres:
-        image: postgres:16
+        image: postgres:17
         env:
           PGUSER: postgres
           POSTGRES_USER: postgres
@@ -135,7 +135,7 @@ jobs:
           - 5432:5432
 
       moto:
-        image: motoserver/moto:5.0.0
+        image: motoserver/moto:5.0.27
         env:
           AWS_ACCESS_KEY_ID: foobar_key
           AWS_SECRET_ACCESS_KEY: foobar_secret
@@ -242,15 +242,14 @@ jobs:
       - name: Build environment and Run Tests
         # https://github.com/numpy/numpy/issues/24703#issuecomment-1722379388
         run: |
-          /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
+          /opt/python/cp313-cp313/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install numpy -Csetup-args="-Dallow-noblas=true"
           python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
           python -m pip install --no-cache-dir --no-build-isolation -e . -Csetup-args="--werror"
           python -m pip list --no-cache-dir
-          export PANDAS_CI=1
-          python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
+          PANDAS_CI=1 python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-32bit
@@ -259,7 +258,7 @@ jobs:
   Linux-Musl:
     runs-on: ubuntu-22.04
     container:
-      image: quay.io/pypa/musllinux_1_1_x86_64
+      image: quay.io/pypa/musllinux_1_2_x86_64
     steps:
       - name: Checkout pandas Repo
         # actions/checkout does not work since it requires node
@@ -281,7 +280,7 @@ jobs:
           apk add musl-locales
       - name: Build environment
         run: |
-          /opt/python/cp311-cp311/bin/python -m venv ~/virtualenvs/pandas-dev
+          /opt/python/cp313-cp313/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
           python -m pip install --no-cache-dir -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.2.1
           python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytest>=7.3.2 pytest-xdist>=3.4.0 hypothesis>=6.84.0
@@ -291,8 +290,7 @@ jobs:
       - name: Run Tests
         run: |
           . ~/virtualenvs/pandas-dev/bin/activate
-          export PANDAS_CI=1
-          python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
+          PANDAS_CI=1 python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
       group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-musl
@@ -357,8 +355,7 @@ jobs:
           python --version
           python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
           python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy
-          python -m pip install versioneer[toml]
-          python -m pip install python-dateutil tzdata cython hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
+          python -m pip install versioneer[toml] python-dateutil tzdata cython hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps -Csetup-args="--werror"
           python -m pip list
 
@@ -375,7 +372,7 @@ jobs:
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.os }}-python-freethreading-dev
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-python-freethreading-dev
       cancel-in-progress: true
 
     env:
@@ -396,14 +393,11 @@ jobs:
           nogil: true
 
       - name: Build Environment
-        # TODO: Once numpy 2.2.1 is out, don't install nightly version
-        # Tests segfault with numpy 2.2.0: https://github.com/numpy/numpy/pull/27955
         run: |
           python --version
-          python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
-          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple cython numpy
-          python -m pip install versioneer[toml]
-          python -m pip install python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
+          python -m pip install --upgrade pip setuptools wheel numpy meson[ninja]==1.2.1 meson-python==0.13.1
+          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple cython
+          python -m pip install versioneer[toml] python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps -Csetup-args="--werror"
           python -m pip list
 

pandas/_config/config.py

@@ -321,6 +321,11 @@ def reset_option(pat: str) -> None:
     """
     Reset one or more options to their default value.
 
+    This method resets the specified pandas option(s) back to their default
+    values. It allows partial string matching for convenience, but users should
+    exercise caution to avoid unintended resets due to changes in option names
+    in future versions.
+
     Parameters
     ----------
     pat : str/regex

pandas/core/base.py

@@ -506,6 +506,11 @@ def array(self) -> ExtensionArray:
         """
         The ExtensionArray of the data backing this Series or Index.
 
+        This property provides direct access to the underlying array data of a
+        Series or Index without requiring conversion to a NumPy array. It
+        returns an ExtensionArray, which is the native storage format for
+        pandas extension dtypes.
+
         Returns
         -------
         ExtensionArray

pandas/core/frame.py

@@ -13673,6 +13673,10 @@ def isin_(x):
         doc="""
         The column labels of the DataFrame.
 
+        This property holds the column names as a pandas ``Index`` object.
+        It provides an immutable sequence of column labels that can be
+        used for data selection, renaming, and alignment in DataFrame operations.
+
         Returns
         -------
         pandas.Index

pandas/core/groupby/groupby.py

@@ -570,6 +570,13 @@ def indices(self) -> dict[Hashable, npt.NDArray[np.intp]]:
         """
         Dict {group name -> group indices}.
 
+        The dictionary keys represent the group labels (e.g., timestamps for a
+        time-based resampling operation), and the values are arrays of integer
+        positions indicating where the elements of each group are located in the
+        original data. This property is particularly useful when working with
+        resampled data, as it provides insight into how the original time-series data
+        has been grouped.
+
         See Also
         --------
         core.groupby.DataFrameGroupBy.indices : Provides a mapping of group rows to
@@ -3709,14 +3716,21 @@ def rolling(
             an integer index is not used to calculate the rolling window.
 
         closed : str, default None
-            If ``'right'``, the first point in the window is excluded from calculations.
+            Determines the inclusivity of points in the window
+            If ``'right'``, (First, Last] the last point in the window
+            is included in the calculations.
+
+            If ``'left'``, [First, Last) the first point in the window
+            is included in the calculations.
 
-            If ``'left'``, the last point in the window is excluded from calculations.
+            If ``'both'``, [First, Last] all points in the window
+            are included in the calculations.
 
-            If ``'both'``, no points in the window are excluded from calculations.
+            If ``'neither'``, (First, Last) the first and last points
+            in the window are excludedfrom calculations.
 
-            If ``'neither'``, the first and last points in the window are excluded
-            from calculations.
+            () and [] are referencing open and closed set
+            notation respetively.
 
             Default ``None`` (``'right'``).
 

pandas/core/reshape/tile.py

@@ -73,7 +73,7 @@ def cut(
 
     Parameters
     ----------
-    x : array-like
+    x : 1d ndarray or Series
         The input array to be binned. Must be 1-dimensional.
     bins : int, sequence of scalars, or IntervalIndex
         The criteria to bin by.
@@ -126,7 +126,7 @@ def cut(
           Categorical for all other inputs. The values stored within
           are whatever the type in the sequence is.
 
-        * False : returns an ndarray of integers.
+        * False : returns a 1d ndarray or Series of integers.
 
     bins : numpy.ndarray or IntervalIndex.
         The computed or specified bins. Only returned when `retbins=True`.

pandas/core/window/rolling.py

@@ -929,14 +929,21 @@ class Window(BaseWindow):
         an integer index is not used to calculate the rolling window.
 
     closed : str, default None
-        If ``'right'``, the first point in the window is excluded from calculations.
+        Determines the inclusivity of points in the window
+        If ``'right'``, (First, Last] the last point in the window
+        is included in the calculations.
 
-        If ``'left'``, the last point in the window is excluded from calculations.
+        If ``'left'``, [First, Last) the first point in the window
+        is included in the calculations.
 
-        If ``'both'``, no point in the window is excluded from calculations.
+        If ``'both'``, [First, Last] all points in the window
+        are included in the calculations.
 
-        If ``'neither'``, the first and last points in the window are excluded
-        from calculations.
+        If ``'neither'``, (First, Last) the first and last points
+        in the window are excludedfrom calculations.
+
+        () and [] are referencing open and closed set
+        notation respetively.
 
         Default ``None`` (``'right'``).