Merge branch 'main' into reduction_dtypes_II

Author: topper-123

.circleci/setup_env.sh

@@ -54,10 +54,7 @@ if pip list | grep -q ^pandas; then
     pip uninstall -y pandas || true
 fi
 
-echo "Build extensions"
-python setup.py build_ext -q -j4
-
 echo "Install pandas"
-python -m pip install --no-build-isolation --no-use-pep517 -e .
+python -m pip install --no-build-isolation -ve .
 
 echo "done"

.github/actions/build_pandas/action.yml

@@ -1,5 +1,9 @@
 name: Build pandas
 description: Rebuilds the C extensions and installs pandas
+inputs:
+  editable:
+    description: Whether to build pandas in editable mode (default true)
+    default: true
 runs:
   using: composite
   steps:
@@ -12,9 +16,9 @@ runs:
 
     - name: Build Pandas
       run: |
-        python setup.py build_ext -j $N_JOBS
-        python -m pip install -e . --no-build-isolation --no-use-pep517 --no-index
+        if [[ ${{ inputs.editable }} == "true" ]]; then
+          pip install -e . --no-build-isolation -v
+        else
+          pip install . --no-build-isolation -v
+        fi
       shell: bash -el {0}
-      env:
-        # https://docs.github.com/en/actions/using-github-hosted-runners/about-github-hosted-runners#supported-runners-and-hardware-resources
-        N_JOBS: ${{ runner.os == 'macOS' && 3 || 2 }}

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

@@ -3,23 +3,14 @@ inputs:
   environment-file:
     description: Conda environment file to use.
     default: environment.yml
-  environment-name:
-    description: Name to use for the Conda environment
-    default: test
-  extra-specs:
-    description: Extra packages to install
-    required: false
 runs:
   using: composite
   steps:
     - name: Install ${{ inputs.environment-file }}
-      uses: mamba-org/provision-with-micromamba@v15
+      uses: mamba-org/setup-micromamba@v1
       with:
         environment-file: ${{ inputs.environment-file }}
-        environment-name: ${{ inputs.environment-name }}
-        extra-specs: ${{ inputs.extra-specs }}
-        channels: conda-forge
-        channel-priority: 'strict'
+        environment-name: test
         condarc-file: ci/condarc.yml
-        cache-env: true
+        cache-environment: true
         cache-downloads: true

.github/workflows/code-checks.yml

@@ -63,8 +63,24 @@ jobs:
     - name: Build Pandas
       id: build
       uses: ./.github/actions/build_pandas
+      with:
+        editable: false
 
     # The following checks are independent of each other and should still be run if one fails
+
+    # 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: Run doctests
+      run: cd ci && ./code_checks.sh doctests
+      if: ${{ steps.build.outcome == 'success' && always() }}
+
+    - name: Install pandas in editable mode
+      id: build-editable
+      uses: ./.github/actions/build_pandas
+      with:
+        editable: true
+
     - name: Check for no warnings when building single-page docs
       run: ci/code_checks.sh single-docs
       if: ${{ steps.build.outcome == 'success' && always() }}
@@ -73,10 +89,6 @@ jobs:
       run: ci/code_checks.sh code
       if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Run doctests
-      run: ci/code_checks.sh doctests
-      if: ${{ steps.build.outcome == 'success' && always() }}
-
     - name: Run docstring validation
       run: ci/code_checks.sh docstrings
       if: ${{ steps.build.outcome == 'success' && always() }}

.github/workflows/codeql.yml

@@ -18,6 +18,7 @@ jobs:
       actions: read
       contents: read
       security-events: write
+    if: github.repository_owner == 'pandas-dev'
 
     strategy:
       fail-fast: false

.github/workflows/package-checks.yml

@@ -14,6 +14,10 @@ on:
 permissions:
   contents: read
 
+defaults:
+  run:
+    shell: bash -el {0}
+
 jobs:
   pip:
     if: ${{ github.event.label.name == 'Build' || contains(github.event.pull_request.labels.*.name, 'Build') || github.event_name == 'push'}}
@@ -40,13 +44,38 @@ jobs:
         with:
           python-version: '3.10'
 
-      - name: Install required dependencies
-        run: |
-          python -m pip install --upgrade pip setuptools wheel python-dateutil pytz numpy cython
-          python -m pip install versioneer[toml]
-        shell: bash -el {0}
-
       - name: Pip install with extra
         run: |
-          python -m pip install -e .[${{ matrix.extra }}] --no-build-isolation
+          python -m pip install .[${{ matrix.extra }}] -v
         shell: bash -el {0}
+  conda_forge_recipe:
+    if: ${{ github.event.label.name == 'Build' || contains(github.event.pull_request.labels.*.name, 'Build') || github.event_name == 'push'}}
+    runs-on: ubuntu-22.04
+    strategy:
+      matrix:
+        python-version: ['3.9', '3.10', '3.11']
+      fail-fast: false
+    name: Test Conda Forge Recipe - Python ${{ matrix.python-version }}
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-conda-forge-recipe-${{ matrix.python-version }}
+      cancel-in-progress: true
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: mamba-org/setup-micromamba@v1
+        with:
+          environment-name: recipe-test
+          create-args: >-
+            python=${{ matrix.python-version }}
+            boa
+            conda-verify
+          cache-downloads: true
+          cache-environment: true
+
+      - name: Build conda package
+        run: conda mambabuild ci --no-anaconda-upload --verify --strict-verify --output --output-folder .

.github/workflows/stale-pr.yml

@@ -11,6 +11,7 @@ jobs:
   stale:
     permissions:
       pull-requests: write
+    if: github.repository_owner == 'pandas-dev'
     runs-on: ubuntu-22.04
     steps:
     - uses: actions/stale@v8

.github/workflows/unit-tests.yml

@@ -229,11 +229,10 @@ jobs:
         run: |
           /opt/python/cp39-cp39/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
-          python -m pip install --no-cache-dir --no-deps -U pip wheel setuptools
+          python -m pip install -U pip wheel setuptools meson[ninja]==1.0.1 meson-python==0.13.1
           python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17 hypothesis>=6.46.1
-          python setup.py build_ext -q -j$(nproc)
-          python -m pip install --no-cache-dir --no-build-isolation --no-use-pep517 -e .
-          python -m pip list
+          python -m pip install --no-cache-dir --no-build-isolation -e .
+          python -m pip list --no-cache-dir
           export PANDAS_CI=1
           python -m pytest -m 'not slow and not network and not clipboard and not single_cpu' pandas --junitxml=test-data.xml
     concurrency:
@@ -268,10 +267,9 @@ jobs:
         run: |
           /opt/python/cp39-cp39/bin/python -m venv ~/virtualenvs/pandas-dev
           . ~/virtualenvs/pandas-dev/bin/activate
-          python -m pip install --no-cache-dir --no-deps -U pip wheel setuptools
+          python -m pip install -U pip wheel setuptools meson-python==0.13.1 meson[ninja]==1.0.1
           python -m pip install --no-cache-dir versioneer[toml] cython numpy python-dateutil pytz pytest>=7.0.0 pytest-xdist>=2.2.0 pytest-asyncio>=0.17 hypothesis>=6.46.1
-          python setup.py build_ext -q -j$(nproc)
-          python -m pip install --no-cache-dir --no-build-isolation --no-use-pep517 -e .
+          python -m pip install --no-cache-dir --no-build-isolation -e .
           python -m pip list --no-cache-dir
 
       - name: Run Tests
@@ -347,8 +345,7 @@ jobs:
 
       - name: Build Pandas
         run: |
-          python setup.py build_ext -q -j4
-          python -m pip install -e . --no-build-isolation --no-use-pep517 --no-index
+          python -m pip install -e . --no-build-isolation --no-index
 
       - name: Build Version
         run: |

.github/workflows/wheels.yml

@@ -40,7 +40,7 @@ jobs:
   build_wheels:
     name: Build wheel for ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
     if: >-
-      github.event_name == 'schedule' ||
+      (github.event_name == 'schedule' && github.repository_owner == 'pandas-dev') ||
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'pull_request' &&
       contains(github.event.pull_request.labels.*.name, 'Build')) ||
@@ -56,7 +56,6 @@ jobs:
         - [ubuntu-20.04, manylinux_x86_64]
         - [macos-11, macosx_*]
         - [windows-2019, win_amd64]
-        - [windows-2019, win32]
         # TODO: support PyPy?
         python: [["cp39", "3.9"], ["cp310", "3.10"],  ["cp311", "3.11"]]#  "pp39"]
     env:

.gitignore

@@ -36,6 +36,7 @@
 *.py[ocd]
 *.so
 .build_cache_dir
+.mesonpy-native-file.ini
 MANIFEST
 
 # Python files #
@@ -76,6 +77,8 @@ coverage_html_report
 __pycache__
 # pytest-monkeytype
 monkeytype.sqlite3
+# meson editable install folder
+.mesonpy
 
 
 # OS generated files #

.pre-commit-config.yaml

@@ -83,6 +83,7 @@ repos:
     hooks:
     -   id: pylint
         stages: [manual]
+        args: [--load-plugins=pylint.extensions.redefined_loop_name]
     -   id: pylint
         alias: redefined-outer-name
         name: Redefining name from outer scope

asv_bench/asv.conf.json

@@ -41,7 +41,6 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
-        "numpy": [],
         "Cython": ["0.29.33"],
         "matplotlib": [],
         "sqlalchemy": [],
@@ -56,6 +55,9 @@
         "xlrd": [],
         "odfpy": [],
         "jinja2": [],
+        "meson": [],
+        "meson-python": [],
+        "python-build": [],
     },
     "conda_channels": ["conda-forge"],
     // Combinations of libraries/python versions can be excluded/included
@@ -125,7 +127,5 @@
     "regression_thresholds": {
     },
     "build_command":
-    ["python -m pip install versioneer[toml]",
-     "python setup.py build -j4",
-     "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}"],
+    ["python -m build -Cbuilddir=builddir --wheel --outdir {build_cache_dir} {build_dir}"]
 }

ci/code_checks.sh

@@ -65,13 +65,8 @@ fi
 ### DOCTESTS ###
 if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
-    MSG='Doctests' ; echo $MSG
-    # Ignore test_*.py files or else the unit tests will run
-    python -m pytest --doctest-modules --ignore-glob="**/test_*.py" pandas
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
-    MSG='Cython Doctests' ; echo $MSG
-    python -m pytest --doctest-cython pandas/_libs
+    MSG='Python and Cython Doctests' ; echo $MSG
+    python -c 'import pandas as pd; pd.test(run_doctests=True)'
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/condarc.yml

@@ -11,7 +11,7 @@ always_yes: true
 #   The number seconds conda will wait for your client to establish a
 #   connection to a remote url resource.
 #
-remote_connect_timeout_secs: 30.0
+remote_connect_timeout_secs: 30
 
 # remote_max_retries (int)
 #   The maximum number of retries each HTTP connection should attempt.

ci/deps/actions-310-numpydev.yaml

@@ -6,11 +6,16 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
+  - meson[ninja]=1.0.1
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0
   - pytest-cov
-  - pytest-xdist>=2.2.0
+  # Once pytest-cov > 4 comes out, unpin this
+  # Right now, a DeprecationWarning related to rsyncdir
+  # causes an InternalError within pytest
+  - pytest-xdist>=2.2.0, <3
   - hypothesis>=6.46.1
   - pytest-asyncio>=0.17.0
 

ci/deps/actions-310.yaml

@@ -7,6 +7,8 @@ dependencies:
   # build dependencies
   - versioneer[toml]
   - cython>=0.29.33
+  - meson[ninja]=1.0.1
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0

ci/deps/actions-311-pyarrownightly.yaml

@@ -6,7 +6,9 @@ dependencies:
 
   # build dependencies
   - versioneer[toml]
+  - meson[ninja]=1.0.1
   - cython>=0.29.33
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0

ci/deps/actions-311.yaml

@@ -7,6 +7,8 @@ dependencies:
   # build dependencies
   - versioneer[toml]
   - cython>=0.29.33
+  - meson[ninja]=1.0.1
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0

ci/deps/actions-39-downstream_compat.yaml

@@ -8,6 +8,8 @@ dependencies:
   # build dependencies
   - versioneer[toml]
   - cython>=0.29.33
+  - meson[ninja]=1.0.1
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0
@@ -69,7 +71,6 @@ dependencies:
   - pandas-datareader
   - pyyaml
   - py
-
   - pip:
     - pyqt5>=5.15.6
     - tzdata>=2022.1

ci/deps/actions-39-minimum_versions.yaml

@@ -9,6 +9,8 @@ dependencies:
   # build dependencies
   - versioneer[toml]
   - cython>=0.29.33
+  - meson[ninja]=1.0.1
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0

ci/deps/actions-39.yaml

@@ -7,6 +7,8 @@ dependencies:
   # build dependencies
   - versioneer[toml]
   - cython>=0.29.33
+  - meson[ninja]=1.0.1
+  - meson-python=0.13.1
 
   # test dependencies
   - pytest>=7.0.0