merge main to make changes and create new PR

Author: crspencer11

.circleci/config.yml

@@ -15,15 +15,16 @@ jobs:
       - checkout
       - run:
           name: Install Environment and Run Tests
-          shell: /bin/bash -exuo pipefail
+          shell: /bin/bash -exo pipefail
+          # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
           command: |
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
-            wget -q $MAMBA_URL -O minimamba.sh
-            chmod +x minimamba.sh
-            MAMBA_DIR="$HOME/miniconda3"
-            rm -rf $MAMBA_DIR
-            ./minimamba.sh -b -p $MAMBA_DIR
-            export PATH=$MAMBA_DIR/bin:$PATH
+            MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MINI_URL -O Miniforge3.sh
+            chmod +x Miniforge3.sh
+            MINI_DIR="$HOME/miniconda3"
+            rm -rf $MINI_DIR
+            ./Miniforge3.sh -b -p $MINI_DIR
+            export PATH=$MINI_DIR/bin:$PATH
             conda info -a
             conda env create -q -n pandas-dev -f $ENV_FILE
             conda list -n pandas-dev
@@ -33,6 +34,7 @@ jobs:
             fi
             python -m pip install --no-build-isolation -ve . --config-settings=setup-args="--werror"
             PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
+            sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
             ci/run_tests.sh
   test-linux-musl:
     docker:
@@ -54,7 +56,7 @@ jobs:
             /opt/python/cp311-cp311/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 pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+            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
             python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
             python -m pip list --no-cache-dir
             export PANDAS_CI=1
@@ -89,29 +91,24 @@ jobs:
           name: Build aarch64 wheels
           no_output_timeout: 30m # Sometimes the tests won't generate any output, make sure the job doesn't get killed by that
           command: |
-            pip3 install cibuildwheel==2.18.1
-            cibuildwheel --prerelease-pythons --output-dir wheelhouse
+            pip3 install cibuildwheel==2.20.0
+            cibuildwheel --output-dir wheelhouse
 
           environment:
             CIBW_BUILD: << parameters.cibw-build >>
 
       - run:
           name: Install Anaconda Client & Upload Wheels
+          shell: /bin/bash -exo pipefail
           command: |
-            echo "Install Mambaforge"
-            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Mambaforge-24.3.0-0-Linux-aarch64.sh"
-            echo "Downloading $MAMBA_URL"
-            wget -q $MAMBA_URL -O minimamba.sh
-            chmod +x minimamba.sh
-
-            MAMBA_DIR="$HOME/miniconda3"
-            rm -rf $MAMBA_DIR
-            ./minimamba.sh -b -p $MAMBA_DIR
-
-            export PATH=$MAMBA_DIR/bin:$PATH
-
-            mamba install -y -c conda-forge anaconda-client
-
+            MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
+            wget -q $MINI_URL -O Miniforge3.sh
+            chmod +x Miniforge3.sh
+            MINI_DIR="$HOME/miniconda3"
+            rm -rf $MINI_DIR
+            ./Miniforge3.sh -b -p $MINI_DIR
+            export PATH=$MINI_DIR/bin:$PATH
+            conda install -y -c conda-forge anaconda-client
             source ci/upload_wheels.sh
             set_upload_vars
             upload_wheels

.devcontainer.json

@@ -8,7 +8,6 @@
 	// Use 'settings' to set *default* container specific settings.json values on container create.
 	// You can edit these settings after create using File > Preferences > Settings > Remote.
 	"settings": {
-		"terminal.integrated.shell.linux": "/bin/bash",
 		"python.pythonPath": "/usr/local/bin/python",
 		"python.formatting.provider": "black",
 		"python.linting.enabled": true,

.gitattributes

@@ -68,7 +68,7 @@ ci export-ignore
 doc export-ignore
 gitpod export-ignore
 MANIFEST.in export-ignore
-scripts export-ignore
+scripts/** export-ignore
 typings export-ignore
 web export-ignore
 CITATION.cff export-ignore
@@ -82,3 +82,7 @@ setup.py export-ignore
 # csv_dir_path fixture checks the existence of the directory
 # exclude the whole directory to avoid running related tests in sdist
 pandas/tests/io/parser/data export-ignore
+
+# Include cibw script in sdist since it's needed for building wheels
+scripts/cibw_before_build.sh -export-ignore
+scripts/cibw_before_test.sh -export-ignore

.github/actions/setup-conda/action.yml

@@ -14,3 +14,9 @@ runs:
         condarc-file: ci/.condarc
         cache-environment: true
         cache-downloads: true
+
+    - name: Uninstall pyarrow
+      if: ${{ env.REMOVE_PYARROW == '1' }}
+      run: |
+        micromamba remove -y pyarrow
+      shell: bash -el {0}

.github/workflows/code-checks.yml

@@ -51,6 +51,11 @@ jobs:
     # TODO: The doctests have to be run first right now, since the Cython doctests only work
     # with pandas installed in non-editable mode
     # This can be removed once pytest-cython doesn't require C extensions to be installed inplace
+
+    - name: Extra installs
+      # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
+      run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
+
     - name: Run doctests
       run: cd ci && ./code_checks.sh doctests
       if: ${{ steps.build.outcome == 'success' && always() }}

.github/workflows/docbuild-and-upload.yml

@@ -46,6 +46,10 @@ jobs:
     - name: Build Pandas
       uses: ./.github/actions/build_pandas
 
+    - name: Extra installs
+      # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
+      run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0
+
     - name: Test website
       run: python -m pytest web/
 

.github/workflows/unit-tests.yml

@@ -29,6 +29,7 @@ jobs:
         env_file: [actions-310.yaml, actions-311.yaml, actions-312.yaml]
         # Prevent the include jobs from overriding other jobs
         pattern: [""]
+        pandas_future_infer_string: ["0"]
         include:
           - name: "Downstream Compat"
             env_file: actions-311-downstream_compat.yaml
@@ -57,6 +58,12 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
+          - name: "Future infer strings"
+            env_file: actions-312.yaml
+            pandas_future_infer_string: "1"
+          - name: "Future infer strings (without pyarrow)"
+            env_file: actions-311.yaml
+            pandas_future_infer_string: "1"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -75,15 +82,17 @@ jobs:
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_CI: '1'
+      PANDAS_FUTURE_INFER_STRING: ${{ matrix.pandas_future_infer_string || '0' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}
       NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
       QT_QPA_PLATFORM: offscreen
+      REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_future_infer_string }}
       cancel-in-progress: true
 
     services:
@@ -130,8 +139,8 @@ jobs:
         fetch-depth: 0
 
     - name: Extra installs
-      run: sudo apt-get update && sudo apt-get install -y ${{ matrix.extra_apt }}
-      if: ${{ matrix.extra_apt }}
+      # https://pytest-qt.readthedocs.io/en/latest/troubleshooting.html#github-actions-azure-pipelines-travis-ci-and-gitlab-ci-cd
+      run: sudo apt-get update && sudo apt-get install -y libegl1 libopengl0 ${{ matrix.extra_apt || ''}}
 
     - name: Generate extra locales
       # These extra locales will be available for locale.setlocale() calls in tests
@@ -227,7 +236,7 @@ jobs:
           . ~/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 --config-settings=setup-args="-Dallow-noblas=true"
-          python -m pip install --no-cache-dir versioneer[toml] cython python-dateutil pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+          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 . --config-settings=setup-args="--werror"
           python -m pip list --no-cache-dir
           export PANDAS_CI=1
@@ -265,7 +274,7 @@ jobs:
           /opt/python/cp311-cp311/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 pytz pytest>=7.3.2 pytest-xdist>=2.2.0 hypothesis>=6.46.1
+          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
           python -m pip install --no-cache-dir --no-build-isolation -e . --config-settings=setup-args="--werror"
           python -m pip list --no-cache-dir
 
@@ -286,7 +295,7 @@ jobs:
     # In general, this will remain frozen(present, but not running) until:
     #    - The next unreleased Python version has released beta 1
     #      - This version should be available on GitHub Actions.
-    #    - Our required build/runtime dependencies(numpy, pytz, Cython, python-dateutil)
+    #    - Our required build/runtime dependencies(numpy, Cython, python-dateutil)
     #      support that unreleased Python version.
     #    To unfreeze, comment out the ``if: false`` condition, and make sure you update
     #    the name of the workflow and Python version in actions/setup-python ``python-version:``
@@ -339,7 +348,7 @@ jobs:
           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 pytz tzdata cython hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0 pytest-cov
+          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 -ve . --no-build-isolation --no-index --no-deps --config-settings=setup-args="--werror"
           python -m pip list
 
@@ -382,15 +391,14 @@ jobs:
           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 cython
           python -m pip install versioneer[toml]
-          python -m pip install python-dateutil pytz tzdata hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0 pytest-cov
+          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 -ve . --no-build-isolation --no-index --no-deps --config-settings=setup-args="--werror"
           python -m pip list
 
       - name: Run Tests
         uses: ./.github/actions/run-tests
-        env:
-          PYTHON_GIL: 0
 
+  # NOTE: this job must be kept in sync with the Pyodide build job in wheels.yml
   emscripten:
     # Note: the Python version, Emscripten toolchain version are determined
     # by the Pyodide version. The appropriate versions can be found in the

.github/workflows/wheels.yml

@@ -99,7 +99,25 @@ jobs:
         - [macos-14, macosx_arm64]
         - [windows-2022, win_amd64]
         # TODO: support PyPy?
-        python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"]]
+        python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"]]
+        include:
+        # TODO: Remove this plus installing build deps in cibw_before_build.sh
+        # and test deps in cibw_before_test.sh after pandas can be built with a released NumPy/Cython
+        - python: ["cp313", "3.13"]
+          cibw_build_frontend: 'pip; args: --no-build-isolation'
+        - python: ["cp313t", "3.13"]
+          cibw_build_frontend: 'pip; args: --no-build-isolation'
+        # Build Pyodide wheels and upload them to Anaconda.org
+        # NOTE: this job is similar to the one in unit-tests.yml except for the fact
+        # that it uses cibuildwheel instead of a standard Pyodide xbuildenv setup.
+        - buildplat: [ubuntu-22.04, pyodide_wasm32]
+          python: ["cp312", "3.12"]
+          cibw_build_frontend: 'build'
+        # TODO: Build free-threaded wheels for Windows
+        exclude:
+        - buildplat: [windows-2022, win_amd64]
+          python: ["cp313t", "3.13"]
+
     env:
       IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -140,12 +158,13 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.19.2
+        uses: pypa/cibuildwheel@v2.20.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
-          CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
+          CIBW_BUILD_FRONTEND: ${{ matrix.cibw_build_frontend || 'pip' }}
+          CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
 
       - name: Set up Python
         uses: mamba-org/setup-micromamba@v1
@@ -168,15 +187,17 @@ jobs:
       - name: Test Windows Wheels
         if: ${{ matrix.buildplat[1] == 'win_amd64' }}
         shell: pwsh
+        # TODO: Remove NumPy nightly install when there's a 3.13 wheel on PyPI
         run: |
           $TST_CMD = @"
-          python -m pip install hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0;
+          python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
+          ${{ matrix.python[1] == '3.13' && 'python -m pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy;' }}
           python -m pip install `$(Get-Item pandas\wheelhouse\*.whl);
           python -c `'import pandas as pd; pd.test(extra_args=[`\"--no-strict-data-files`\", `\"-m not clipboard and not single_cpu and not slow and not network and not db`\"])`';
           "@
           # add rc to the end of the image name if the Python version is unreleased
-          docker pull python:${{ matrix.python[1] == '3.12' && '3.12-rc' || format('{0}-windowsservercore', matrix.python[1]) }}
-          docker run --env PANDAS_CI='1' -v ${PWD}:C:\pandas python:${{ matrix.python[1] == '3.12' && '3.12-rc' || format('{0}-windowsservercore', matrix.python[1]) }} powershell -Command $TST_CMD
+          docker pull python:${{ matrix.python[1] == '3.13' && '3.13-rc' || format('{0}-windowsservercore', matrix.python[1]) }}
+          docker run --env PANDAS_CI='1' -v ${PWD}:C:\pandas python:${{ matrix.python[1] == '3.13' && '3.13-rc' || format('{0}-windowsservercore', matrix.python[1]) }} powershell -Command $TST_CMD
 
       - uses: actions/upload-artifact@v4
         with:

.gitpod.yml

@@ -14,7 +14,7 @@ tasks:
       cp gitpod/settings.json .vscode/settings.json
       git fetch --tags
       python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
-      pre-commit install
+      pre-commit install --install-hooks
     command: |
       python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
       echo "✨ Pre-build complete! You can close this terminal ✨ "

Dockerfile

@@ -2,7 +2,7 @@ FROM python:3.10.8
 WORKDIR /home/pandas
 
 RUN apt-get update && apt-get -y upgrade
-RUN apt-get install -y build-essential
+RUN apt-get install -y build-essential bash-completion
 
 # hdf5 needed for pytables installation
 # libgles2-mesa needed for pytest-qt
@@ -12,4 +12,6 @@ RUN python -m pip install --upgrade pip
 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"
 CMD ["/bin/bash"]