BLD: Build wheels using cibuildwheel

.github/workflows/wheels.yml

@@ -0,0 +1,180 @@
+# Workflow to build wheels for upload to PyPI.
+# Inspired by numpy's cibuildwheel config https://github.com/numpy/numpy/blob/main/.github/workflows/wheels.yml
+#
+# In an attempt to save CI resources, wheel builds do
+# not run on each push but only weekly and for releases.
+# Wheel builds can be triggered from the Actions page
+# (if you have the perms) on a commit to master.
+#
+# Alternatively, you can add labels to the pull request in order to trigger wheel
+# builds.
+# The label(s) that trigger builds are:
+# - Build
+name: Wheel builder
+
+on:
+  schedule:
+  #        ┌───────────── minute (0 - 59)
+  #        │  ┌───────────── hour (0 - 23)
+  #        │  │ ┌───────────── day of the month (1 - 31)
+  #        │  │ │ ┌───────────── month (1 - 12 or JAN-DEC)
+  #        │  │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
+  #        │  │ │ │ │
+  - cron: "27 3 */1 * *"
+  push:
+  pull_request:
+      types: [labeled, opened, synchronize, reopened]
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build_wheels:
+    name: Build wheel for ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
+    if: >-
+      github.event_name == 'schedule' ||
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'pull_request' &&
+      contains(github.event.pull_request.labels.*.name, 'Build')) ||
+      (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') && ( ! endsWith(github.ref, 'dev0')))
+    runs-on: ${{ matrix.buildplat[0] }}
+    strategy:
+      # Ensure that a wheel builder finishes even if another fails
+      fail-fast: false
+      matrix:
+        # Github Actions doesn't support pairing matrix values together, let's improvise
+        # https://github.com/github/feedback/discussions/7835#discussioncomment-1769026
+        buildplat:
+        - [ubuntu-20.04, manylinux_x86_64]
+        - [macos-11, macosx_*]
+        - [windows-2019, win_amd64]
+        - [windows-2019, win32]
+        # TODO: support PyPy?
+        python: [["cp38", "3.8"], ["cp39", "3.9"], ["cp310", "3.10"],  ["cp311", "3.11-dev"]]# "pp38", "pp39"]
+    env:
+      IS_32_BIT: ${{ matrix.buildplat[1] == 'win32' }}
+      IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
+      IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
+    steps:
+      - name: Checkout pandas
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          # versioneer.py requires the latest tag to be reachable. Here we
+          # fetch the complete history to get access to the tags.
+          # A shallow clone can work when the following issue is resolved:
+          # https://github.com/actions/checkout/issues/338
+          fetch-depth: 0
+
+      - name: Build wheels
+        uses: pypa/cibuildwheel@v2.9.0
+        env:
+          CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
+          CIBW_ENVIRONMENT: IS_32_BIT='${{ env.IS_32_BIT }}'
+          # We can't test directly with cibuildwheel, since we need to have to wheel location
+          # to mount into the docker image
+          CIBW_TEST_COMMAND_LINUX: "python {project}/ci/test_wheels.py"
+          CIBW_TEST_COMMAND_MACOS: "python {project}/ci/test_wheels.py"
+          CIBW_TEST_REQUIRES: hypothesis==6.52.1 pytest>=6.2.5 pytest-xdist pytest-asyncio>=0.17
+          CIBW_REPAIR_WHEEL_COMMAND_WINDOWS: "python ci/fix_wheels.py {wheel} {dest_dir}"
+          CIBW_ARCHS_MACOS: x86_64 universal2
+          CIBW_BUILD_VERBOSITY: 3
+
+      # Used to push the built wheels
+      - uses: actions/setup-python@v3
+        with:
+          python-version: ${{ matrix.python[1] }}
+
+      - name: Test wheels (Windows 64-bit only)
+        if: ${{ matrix.buildplat[1] == 'win_amd64' }}
+        shell: cmd
+        run: |
+          python ci/test_wheels.py wheelhouse
+
+      - uses: actions/upload-artifact@v3
+        with:
+          name: ${{ matrix.python[0] }}-${{ startsWith(matrix.buildplat[1], 'macosx') && 'macosx' || matrix.buildplat[1] }}
+          path: ./wheelhouse/*.whl
+
+      - name: Upload wheels
+        if: success()
+        shell: bash
+        env:
+          PANDAS_STAGING_UPLOAD_TOKEN: ${{ secrets.PANDAS_STAGING_UPLOAD_TOKEN }}
+          PANDAS_NIGHTLY_UPLOAD_TOKEN: ${{ secrets.PANDAS_NIGHTLY_UPLOAD_TOKEN }}
+        run: |
+          source ci/upload_wheels.sh
+          set_upload_vars
+          # trigger an upload to
+          # https://anaconda.org/scipy-wheels-nightly/pandas
+          # for cron jobs or "Run workflow" (restricted to main branch).
+          # Tags will upload to
+          # https://anaconda.org/multibuild-wheels-staging/pandas
+          # The tokens were originally generated at anaconda.org
+          upload_wheels
+  build_sdist:
+    name: Build sdist
+    if: >-
+      github.event_name == 'schedule' ||
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'pull_request' &&
+      contains(github.event.pull_request.labels.*.name, 'Build')) ||
+      (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') && ( ! endsWith(github.ref, 'dev0')))
+    runs-on: ubuntu-latest
+    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' }}
+    steps:
+      - name: Checkout pandas
+        uses: actions/checkout@v3
+        with:
+          submodules: true
+          # versioneer.py requires the latest tag to be reachable. Here we
+          # fetch the complete history to get access to the tags.
+          # A shallow clone can work when the following issue is resolved:
+          # https://github.com/actions/checkout/issues/338
+          fetch-depth: 0
+      # Used to push the built wheels
+      - uses: actions/setup-python@v3
+        with:
+          # Build sdist on lowest supported Python
+          python-version: '3.8'
+      - name: Build sdist
+        run: |
+          pip install build
+          python -m build --sdist
+      - name: Test the sdist
+        run: |
+          # TODO: Don't run test suite, and instead build wheels from sdist
+          # by splitting the wheel builders into a two stage job
+          # (1. Generate sdist 2. Build wheels from sdist)
+          # This tests the sdists, and saves some build time
+          python -m pip install dist/*.gz
+          pip install hypothesis==6.52.1 pytest>=6.2.5 pytest-xdist pytest-asyncio>=0.17
+          cd .. # Not a good idea to test within the src tree
+          python -c "import pandas; print(pandas.__version__);
+          pandas.test(extra_args=['-m not clipboard and not single_cpu', '--skip-slow', '--skip-network', '--skip-db', '-n=2']);
+          pandas.test(extra_args=['-m not clipboard and single_cpu', '--skip-slow', '--skip-network', '--skip-db'])"
+      - uses: actions/upload-artifact@v3
+        with:
+          name: sdist
+          path: ./dist/*
+
+      - name: Upload sdist
+        if: success()
+        shell: bash
+        env:
+          PANDAS_STAGING_UPLOAD_TOKEN: ${{ secrets.PANDAS_STAGING_UPLOAD_TOKEN }}
+          PANDAS_NIGHTLY_UPLOAD_TOKEN: ${{ secrets.PANDAS_NIGHTLY_UPLOAD_TOKEN }}
+        run: |
+          source ci/upload_wheels.sh
+          set_upload_vars
+          # trigger an upload to
+          # https://anaconda.org/scipy-wheels-nightly/pandas
+          # for cron jobs or "Run workflow" (restricted to main branch).
+          # Tags will upload to
+          # https://anaconda.org/multibuild-wheels-staging/pandas
+          # The tokens were originally generated at anaconda.org
+          upload_wheels

.pre-commit-config.yaml

@@ -53,6 +53,8 @@ repos:
     rev: 5.0.4
     hooks:
     -   id: flake8
+        # Need to patch os.remove rule in pandas-dev-flaker
+        exclude: ^ci/fix_wheels.py
         additional_dependencies: &flake8_dependencies
         - flake8==5.0.4
         - flake8-bugbear==22.7.1

ci/fix_wheels.py

@@ -0,0 +1,54 @@
+import os
+import shutil
+import sys
+import zipfile
+
+try:
+    _, wheel_path, dest_dir = sys.argv
+    # Figure out whether we are building on 32 or 64 bit python
+    is_32 = sys.maxsize <= 2**32
+    PYTHON_ARCH = "x86" if is_32 else "x64"
+except ValueError:
+    # Too many/little values to unpack
+    raise ValueError(
+        "User must pass the path to the wheel and the destination directory."
+    )
+# Wheels are zip files
+if not os.path.isdir(dest_dir):
+    print(f"Created directory {dest_dir}")
+    os.mkdir(dest_dir)
+shutil.copy(wheel_path, dest_dir)  # Remember to delete if process fails
+wheel_name = os.path.basename(wheel_path)
+success = True
+exception = None
+repaired_wheel_path = os.path.join(dest_dir, wheel_name)
+with zipfile.ZipFile(repaired_wheel_path, "a") as zipf:
+    try:
+        # TODO: figure out how licensing works for the redistributables
+        base_redist_dir = (
+            f"C:/Program Files (x86)/Microsoft Visual Studio/2019/"
+            f"Enterprise/VC/Redist/MSVC/14.29.30133/{PYTHON_ARCH}/"
+            f"Microsoft.VC142.CRT/"
+        )
+        zipf.write(
+            os.path.join(base_redist_dir, "msvcp140.dll"),
+            "pandas/_libs/window/msvcp140.dll",
+        )
+        zipf.write(
+            os.path.join(base_redist_dir, "concrt140.dll"),
+            "pandas/_libs/window/concrt140.dll",
+        )
+        if not is_32:
+            zipf.write(
+                os.path.join(base_redist_dir, "vcruntime140_1.dll"),
+                "pandas/_libs/window/vcruntime140_1.dll",
+            )
+    except Exception as e:
+        success = False
+        exception = e
+
+if not success:
+    os.remove(repaired_wheel_path)
+    raise exception
+else:
+    print(f"Successfully repaired wheel was written to {repaired_wheel_path}")

ci/test_wheels.py

@@ -0,0 +1,58 @@
+import glob
+import os
+import platform
+import shutil
+import subprocess
+import sys
+
+if os.name == "nt":
+    py_ver = platform.python_version()
+    is_32_bit = os.getenv("IS_32_BIT") == "true"
+    try:
+        wheel_dir = sys.argv[1]
+        wheel_path = glob.glob(f"{wheel_dir}/*.whl")[0]
+    except IndexError:
+        # Not passed
+        wheel_path = None
+    print(f"IS_32_BIT is {is_32_bit}")
+    print(f"Path to built wheel is {wheel_path}")
+    if is_32_bit:
+        sys.exit(0)  # No way to test Windows 32-bit(no docker image)
+    if wheel_path is None:
+        raise ValueError("Wheel path must be passed in if on 64-bit Windows")
+    print(f"Pulling docker image to test Windows 64-bit Python {py_ver}")
+    subprocess.run(f"docker pull python:{py_ver}-windowsservercore", check=True)
+    pandas_base_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+    print(f"pandas project dir is {pandas_base_dir}")
+    dist_dir = os.path.join(pandas_base_dir, "dist")
+    print(f"Copying wheel into pandas_base_dir/dist ({dist_dir})")
+    os.mkdir(dist_dir)
+    shutil.copy(wheel_path, dist_dir)
+    print(os.listdir(dist_dir))
+    subprocess.run(
+        rf"docker run -v %cd%:c:\pandas "
+        f"python:{py_ver}-windowsservercore /pandas/ci/test_wheels_windows.bat",
+        check=True,
+        shell=True,
+        cwd=pandas_base_dir,
+    )
+else:
+    import pandas as pd
+
+    pd.test(
+        extra_args=[
+            "-m not clipboard and not single_cpu",
+            "--skip-slow",
+            "--skip-network",
+            "--skip-db",
+            "-n=2",
+        ]
+    )
+    pd.test(
+        extra_args=[
+            "-m not clipboard and single_cpu",
+            "--skip-slow",
+            "--skip-network",
+            "--skip-db",
+        ]
+    )

ci/test_wheels_windows.bat

@@ -0,0 +1,9 @@
+set test_command=import pandas as pd; print(pd.__version__); ^
+pd.test(extra_args=['-m not clipboard and not single_cpu', '--skip-slow', '--skip-network', '--skip-db', '-n=2']); ^
+pd.test(extra_args=['-m not clipboard and single_cpu', '--skip-slow', '--skip-network', '--skip-db'])
+
+python --version
+pip install pytz six numpy python-dateutil
+pip install hypothesis==6.52.1 pytest>=6.2.5 pytest-xdist pytest-asyncio>=0.17
+pip install --find-links=pandas/dist --no-index pandas
+python -c "%test_command%"

ci/upload_wheels.sh

@@ -0,0 +1,42 @@
+# Modified from numpy's https://github.com/numpy/numpy/blob/main/tools/wheels/upload_wheels.sh
+
+set_upload_vars() {
+    echo "IS_PUSH is $IS_PUSH"
+    echo "IS_SCHEDULE_DISPATCH is $IS_SCHEDULE_DISPATCH"
+    if [[ "$IS_PUSH" == "true" ]]; then
+        echo push and tag event
+        export ANACONDA_ORG="multibuild-wheels-staging"
+        export TOKEN="$PANDAS_STAGING_UPLOAD_TOKEN"
+        export ANACONDA_UPLOAD="true"
+    elif [[ "$IS_SCHEDULE_DISPATCH" == "true" ]]; then
+        echo scheduled or dispatched event
+        export ANACONDA_ORG="scipy-wheels-nightly"
+        export TOKEN="$PANDAS_NIGHTLY_UPLOAD_TOKEN"
+        export ANACONDA_UPLOAD="true"
+    else
+        echo non-dispatch event
+        export ANACONDA_UPLOAD="false"
+    fi
+}
+upload_wheels() {
+    echo ${PWD}
+    if [[ ${ANACONDA_UPLOAD} == true ]]; then
+        if [ -z ${TOKEN} ]; then
+            echo no token set, not uploading
+        else
+            conda install -q -y anaconda-client
+            # 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
+            elif compgen -G "./wheelhouse/*.whl"; then
+                echo "Found wheel"
+                anaconda -q -t ${TOKEN} upload --skip -u ${ANACONDA_ORG} ./wheelhouse/*.whl
+            else
+                echo "Files do not exist"
+                return 1
+            fi
+            echo "PyPI-style index: https://pypi.anaconda.org/$ANACONDA_ORG/simple"
+        fi
+    fi
+}