Merge branch 'main' into concat_error

Author: jahn96

.circleci/config.yml

@@ -16,6 +16,7 @@ jobs:
       - run:
           name: Install Environment and Run Tests
           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: |
             MINI_URL="https://github.com/conda-forge/miniforge/releases/download/24.3.0-0/Miniforge3-24.3.0-0-Linux-aarch64.sh"
             wget -q $MINI_URL -O Miniforge3.sh
@@ -33,6 +34,7 @@ jobs:
             fi
             python -m pip install --no-build-isolation -ve . --config-settings=setup-args="--werror"
             PATH=$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:
@@ -89,8 +91,8 @@ 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 >>

.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,

.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
@@ -58,6 +59,9 @@ jobs:
             # 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"
@@ -85,9 +89,10 @@ jobs:
       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:
@@ -134,8 +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

.github/workflows/wheels.yml

@@ -158,11 +158,10 @@ 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' }}

.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"]

ci/code_checks.sh

@@ -70,8 +70,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --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` \
-        -i "pandas.MultiIndex.get_level_values SA01" \
-        -i "pandas.MultiIndex.get_loc_level PR07" \
         -i "pandas.MultiIndex.names SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
         -i "pandas.MultiIndex.sortlevel PR07,SA01" \
@@ -165,10 +163,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.center RT03,SA01" \
         -i "pandas.Series.str.decode PR07,RT03,SA01" \
         -i "pandas.Series.str.encode PR07,RT03,SA01" \
-        -i "pandas.Series.str.find RT03" \
-        -i "pandas.Series.str.fullmatch RT03" \
-        -i "pandas.Series.str.get RT03,SA01" \
-        -i "pandas.Series.str.index RT03" \
         -i "pandas.Series.str.ljust RT03,SA01" \
         -i "pandas.Series.str.lower RT03" \
         -i "pandas.Series.str.lstrip RT03" \
@@ -177,8 +171,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.str.partition RT03" \
         -i "pandas.Series.str.repeat SA01" \
         -i "pandas.Series.str.replace SA01" \
-        -i "pandas.Series.str.rfind RT03" \
-        -i "pandas.Series.str.rindex RT03" \
         -i "pandas.Series.str.rjust RT03,SA01" \
         -i "pandas.Series.str.rpartition RT03" \
         -i "pandas.Series.str.rstrip RT03" \
@@ -267,9 +259,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.extensions.ExtensionArray.tolist RT03,SA01" \
         -i "pandas.api.extensions.ExtensionArray.unique RT03,SA01" \
         -i "pandas.api.extensions.ExtensionArray.view SA01" \
-        -i "pandas.api.indexers.VariableOffsetWindowIndexer PR01,SA01" \
         -i "pandas.api.interchange.from_dataframe RT03,SA01" \
-        -i "pandas.api.types.is_any_real_numeric_dtype SA01" \
         -i "pandas.api.types.is_bool PR01,SA01" \
         -i "pandas.api.types.is_bool_dtype SA01" \
         -i "pandas.api.types.is_categorical_dtype SA01" \
@@ -291,13 +281,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_iterator PR07,SA01" \
         -i "pandas.api.types.is_list_like SA01" \
         -i "pandas.api.types.is_named_tuple PR07,SA01" \
-        -i "pandas.api.types.is_numeric_dtype SA01" \
         -i "pandas.api.types.is_object_dtype SA01" \
-        -i "pandas.api.types.is_period_dtype SA01" \
         -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
-        -i "pandas.api.types.is_sparse SA01" \
-        -i "pandas.api.types.is_timedelta64_ns_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.BooleanArray SA01" \