Merge branch 'main' into concat_str

.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
 

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+    rev: v0.9.4
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -41,7 +41,7 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
@@ -70,7 +70,7 @@ repos:
     -   id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.13.2
+    rev: 6.0.0
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
@@ -95,17 +95,22 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.6
+    rev: v19.1.7
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.6.1
+    rev: v1.7.0
     hooks:
     - id: meson-fmt
       args: ['--inplace']
+-   repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: v0.10.0.1
+    hooks:
+    -   id: shellcheck
+        args: ["--severity=warning"]
 -   repo: local
     hooks:
     -   id: pyright

asv_bench/benchmarks/io/style.py

@@ -13,8 +13,8 @@ class Render:
     def setup(self, cols, rows):
         self.df = DataFrame(
             np.random.randn(rows, cols),
-            columns=[f"float_{i+1}" for i in range(cols)],
-            index=[f"row_{i+1}" for i in range(rows)],
+            columns=[f"float_{i + 1}" for i in range(cols)],
+            index=[f"row_{i + 1}" for i in range(rows)],
         )
 
     def time_apply_render(self, cols, rows):

ci/code_checks.sh

@@ -24,15 +24,15 @@ else
 fi
 
 [[ -z "$CHECK" || "$CHECK" == "code" || "$CHECK" == "doctests" || "$CHECK" == "docstrings" || "$CHECK" == "single-docs" || "$CHECK" == "notebooks" ]] || \
-    { echo "Unknown command $1. Usage: $0 [code|doctests|docstrings|single-docs|notebooks]"; exit 9999; }
+    { echo "Unknown command $1. Usage: $0 [code|doctests|docstrings|single-docs|notebooks]"; exit 1; }
 
-BASE_DIR="$(dirname $0)/.."
+BASE_DIR="$(dirname "$0")/.."
 RET=0
 
 ### CODE ###
 if [[ -z "$CHECK" || "$CHECK" == "code" ]]; then
 
-    MSG='Check import. No warnings, and blocklist some optional dependencies' ; echo $MSG
+    MSG='Check import. No warnings, and blocklist some optional dependencies' ; echo "$MSG"
     python -W error -c "
 import sys
 import pandas
@@ -49,24 +49,24 @@ if mods:
     sys.stderr.write('err: pandas should not import: {}\n'.format(', '.join(mods)))
     sys.exit(len(mods))
     "
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
+    RET=$(($RET + $?)) ; echo "$MSG" "DONE"
 
 fi
 
 ### DOCTESTS ###
 if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
-    MSG='Python and Cython Doctests' ; echo $MSG
+    MSG='Python and Cython Doctests' ; echo "$MSG"
     python -c 'import pandas as pd; pd.test(run_doctests=True)'
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
+    RET=$(($RET + $?)) ; echo "$MSG" "DONE"
 
 fi
 
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate Docstrings' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py \
+    MSG='Validate Docstrings' ; echo "$MSG"
+    "$BASE_DIR"/scripts/validate_docstrings.py \
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
@@ -265,7 +265,7 @@ fi
 if [[ -z "$CHECK" || "$CHECK" == "notebooks" ]]; then
 
     MSG='Notebooks' ; echo $MSG
-    jupyter nbconvert --execute $(find doc/source -name '*.ipynb') --to notebook
+    jupyter nbconvert --execute "$(find doc/source -name '*.ipynb')" --to notebook
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/run_tests.sh

@@ -3,10 +3,8 @@
 # Workaround for pytest-xdist (it collects different tests in the workers if PYTHONHASHSEED is not set)
 # https://github.com/pytest-dev/pytest/issues/920
 # https://github.com/pytest-dev/pytest/issues/1075
-export PYTHONHASHSEED=$(python -c 'import random; print(random.randint(1, 4294967295))')
-
-# May help reproduce flaky CI builds if set in subsequent runs
-echo PYTHONHASHSEED=$PYTHONHASHSEED
+PYTHONHASHSEED=$(python -c 'import random; print(random.randint(1, 4294967295))')
+export PYTHONHASHSEED
 
 COVERAGE="-s --cov=pandas --cov-report=xml --cov-append --cov-config=pyproject.toml"
 
@@ -16,5 +14,5 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
-echo $PYTEST_CMD
+echo "$PYTEST_CMD"
 sh -c "$PYTEST_CMD"

ci/upload_wheels.sh

@@ -1,3 +1,4 @@
+#!/bin/bash
 # Modified from numpy's https://github.com/numpy/numpy/blob/main/tools/wheels/upload_wheels.sh
 
 set_upload_vars() {
@@ -19,20 +20,20 @@ set_upload_vars() {
     fi
 }
 upload_wheels() {
-    echo ${PWD}
+    echo "${PWD}"
     if [[ ${ANACONDA_UPLOAD} == true ]]; then
-        if [ -z ${TOKEN} ]; then
+        if [ -z "${TOKEN}" ]; then
             echo no token set, not uploading
         else
             # sdists are located under dist folder when built through setup.py
             if compgen -G "./dist/*.gz"; then
                 echo "Found sdist"
-                anaconda -q -t ${TOKEN} upload --skip -u ${ANACONDA_ORG} ./dist/*.gz
+                anaconda -q -t "${TOKEN}" upload --skip -u "${ANACONDA_ORG}" ./dist/*.gz
                 echo "Uploaded sdist"
             fi
             if compgen -G "./wheelhouse/*.whl"; then
                 echo "Found wheel"
-                anaconda -q -t ${TOKEN} upload --skip -u ${ANACONDA_ORG} ./wheelhouse/*.whl
+                anaconda -q -t "${TOKEN}" upload --skip -u "${ANACONDA_ORG}" ./wheelhouse/*.whl
                 echo "Uploaded wheel"
             fi
             echo "PyPI-style index: https://pypi.anaconda.org/$ANACONDA_ORG/simple"

doc/make.py

@@ -260,8 +260,7 @@ def latex(self, force=False):
                 for i in range(3):
                     self._run_os("pdflatex", "-interaction=nonstopmode", "pandas.tex")
                 raise SystemExit(
-                    "You should check the file "
-                    '"build/latex/pandas.pdf" for problems.'
+                    'You should check the file "build/latex/pandas.pdf" for problems.'
                 )
             self._run_os("make")
             return ret_code
@@ -343,8 +342,7 @@ def main():
         dest="verbosity",
         default=0,
         help=(
-            "increase verbosity (can be repeated), "
-            "passed to the sphinx build command"
+            "increase verbosity (can be repeated), passed to the sphinx build command"
         ),
     )
     argparser.add_argument(

doc/source/development/contributing_codebase.rst

@@ -344,7 +344,7 @@ be located.
    - tests.scalar
    - tests.tseries.offsets
 
-2. Does your test depend only on code in pd._libs?
+2. Does your test depend only on code in ``pd._libs``?
    This test likely belongs in one of:
 
    - tests.libs

doc/source/development/developer.rst

@@ -99,7 +99,7 @@ Column metadata
 * Boolean: ``'bool'``
 * Integers: ``'int8', 'int16', 'int32', 'int64', 'uint8', 'uint16', 'uint32', 'uint64'``
 * Floats: ``'float16', 'float32', 'float64'``
-* Date and Time Types: ``'datetime', 'datetimetz'``, ``'timedelta'``
+* Date and Time Types: ``'datetime', 'datetimetz', 'timedelta'``
 * String: ``'unicode', 'bytes'``
 * Categorical: ``'categorical'``
 * Other Python objects: ``'object'``

doc/source/reference/series.rst

@@ -25,6 +25,7 @@ Attributes
    Series.array
    Series.values
    Series.dtype
+   Series.info
    Series.shape
    Series.nbytes
    Series.ndim

doc/source/reference/style.rst

@@ -27,6 +27,7 @@ Styler properties
    Styler.template_html_style
    Styler.template_html_table
    Styler.template_latex
+   Styler.template_typst
    Styler.template_string
    Styler.loader
 
@@ -77,6 +78,7 @@ Style export and import
 
    Styler.to_html
    Styler.to_latex
+   Styler.to_typst
    Styler.to_excel
    Styler.to_string
    Styler.export

doc/source/user_guide/cookbook.rst

@@ -874,7 +874,7 @@ Timeseries
 <https://stackoverflow.com/questions/13893227/vectorized-look-up-of-values-in-pandas-dataframe>`__
 
 `Aggregation and plotting time series
-<https://nipunbatra.github.io/blog/visualisation/2013/05/01/aggregation-timeseries.html>`__
+<https://nipunbatra.github.io/blog/posts/2013-05-01-aggregation-timeseries.html>`__
 
 Turn a matrix with hours in columns and days in rows into a continuous row sequence in the form of a time series.
 `How to rearrange a Python pandas DataFrame?
@@ -1043,7 +1043,7 @@ CSV
 
 The :ref:`CSV <io.read_csv_table>` docs
 
-`read_csv in action <https://wesmckinney.com/blog/update-on-upcoming-pandas-v0-10-new-file-parser-other-performance-wins/>`__
+`read_csv in action <https://www.datacamp.com/tutorial/pandas-read-csv>`__
 
 `appending to a csv
 <https://stackoverflow.com/questions/17134942/pandas-dataframe-output-end-of-csv>`__

doc/source/user_guide/enhancingperf.rst

@@ -427,7 +427,7 @@ prefer that Numba throw an error if it cannot compile a function in a way that
 speeds up your code, pass Numba the argument
 ``nopython=True`` (e.g.  ``@jit(nopython=True)``). For more on
 troubleshooting Numba modes, see the `Numba troubleshooting page
-<https://numba.pydata.org/numba-doc/latest/user/troubleshoot.html#the-compiled-code-is-too-slow>`__.
+<https://numba.readthedocs.io/en/stable/user/troubleshoot.html>`__.
 
 Using ``parallel=True`` (e.g. ``@jit(parallel=True)``) may result in a ``SIGABRT`` if the threading layer leads to unsafe
 behavior. You can first `specify a safe threading layer <https://numba.readthedocs.io/en/stable/user/threading-layer.html#selecting-a-threading-layer-for-safe-parallel-execution>`__

doc/source/user_guide/gotchas.rst

@@ -372,5 +372,5 @@ constructors using something similar to the following:
    s = pd.Series(newx)
 
 See `the NumPy documentation on byte order
-<https://numpy.org/doc/stable/user/basics.byteswapping.html>`__ for more
+<https://numpy.org/doc/stable/user/byteswapping.html>`__ for more
 details.

doc/source/user_guide/groupby.rst

@@ -418,7 +418,7 @@ You can also include the grouping columns if you want to operate on them.
 
 .. note::
 
-   The ``groupby`` operation in Pandas drops the ``name`` field of the columns Index object
+   The ``groupby`` operation in pandas drops the ``name`` field of the columns Index object
    after the operation. This change ensures consistency in syntax between different
    column selection methods within groupby operations.
 

doc/source/user_guide/io.rst

@@ -990,7 +990,7 @@ Thousand separators
 
 For large numbers that have been written with a thousands separator, you can
 set the ``thousands`` keyword to a string of length 1 so that integers will be parsed
-correctly:
+correctly.
 
 By default, numbers with a thousands separator will be parsed as strings: