CI: Run code checks with Pixi

.github/workflows/code-checks.yml

@@ -10,25 +10,22 @@ on:
       - main
       - 3.0.x
 
-env:
-  ENV_FILE: environment.yml
+defaults:
+  run:
+    shell: bash -euox pipefail {0}
 
 permissions: {}
 
-# pre-commit run by https://pre-commit.ci/
 jobs:
-  docstring_typing_manual_hooks:
-    name: Docstring validation, typing, and other manual pre-commit hooks
+  doctest:
+    name: Doctests
     runs-on: ubuntu-24.04
     permissions:
       contents: read
-    defaults:
-      run:
-        shell: bash -el {0}
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-code-checks
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-doctests
       cancel-in-progress: true
 
     steps:
@@ -37,51 +34,70 @@ jobs:
       with:
         fetch-depth: 0
 
-    - name: Set up Conda
-      uses: ./.github/actions/setup-conda
-
-    - name: Build Pandas
-      id: build
-      uses: ./.github/actions/build_pandas
+    - name: Create virtual environment with Pixi
+      uses: ./.github/actions/setup-pixi
+      with:
+        environment: "doctests"
 
-    # The following checks are independent of each other and should still be run if one fails
-    - 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: Build pandas
+      run: |
+        pixi run \
+          --environment doctests \
+          build-pandas \
+          --editable \
+          -Csetup-args="--werror"
 
     - name: Run doctests
-      run: cd ci && ./code_checks.sh doctests
-      if: ${{ steps.build.outcome == 'success' && always() }}
+      run: pixi run --environment doctests ci-doctests
 
-    - name: Run checks on imported code
-      run: ci/code_checks.sh code
-      if: ${{ steps.build.outcome == 'success' && always() }}
+    - name: Run scripts tests
+      run: pixi run --environment doctests ci-scripts-tests
 
-    - name: Use existing environment for type checking
-      run: |
-        echo $PATH >> $GITHUB_PATH
-        echo "PYTHONHOME=$PYTHONHOME" >> $GITHUB_ENV
-        echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
-      if: ${{ steps.build.outcome == 'success' && always() }}
+  type-checking:
+    name: Type Checking
+    runs-on: ubuntu-24.04
+    permissions:
+      contents: read
+
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-typechecking
+      cancel-in-progress: true
 
-    - name: Typing
-      uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
+    steps:
+    - name: Checkout
+      uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
       with:
-        extra_args: --verbose --hook-stage manual --all-files
-      if: ${{ steps.build.outcome == 'success' && always() }}
+        fetch-depth: 0
+
+    - name: Create virtual environment with Pixi
+      uses: ./.github/actions/setup-pixi
+      with:
+        environment: "typing"
+
+    - name: Build pandas
+      run: |
+        pixi run \
+          --environment typing \
+          build-pandas \
+          --editable \
+          -Csetup-args="--werror"
+
+    # - name: Use existing environment for type checking
+    #   run: |
+    #     echo $PATH >> $GITHUB_PATH
+    #     echo "PYTHONHOME=$PYTHONHOME" >> $GITHUB_ENV
+    #     echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
+    #   if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Run docstring validation script tests
-      run: pytest scripts
-      if: ${{ steps.build.outcome == 'success' && always() }}
+    - name: Typing Checks
+      run: pixi run --environment typing ci-typing
 
   asv-benchmarks:
     name: ASV Benchmarks
     runs-on: ubuntu-24.04
     permissions:
       contents: read
-    defaults:
-      run:
-        shell: bash -euox pipefail {0}
 
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
@@ -124,19 +140,15 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          fetch-depth: 0
 
       - name: Setup Python
         id: setup_python
         uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
         with:
           python-version: '3.11'
           cache: 'pip'
+          pip-install: '-r requirements-dev.txt'
           cache-dependency-path: 'requirements-dev.txt'
 
-      - name: Install requirements-dev.txt
-        run: pip install -r requirements-dev.txt
-
       - name: Check Pip Cache Hit
         run: echo ${{ steps.setup_python.outputs.cache-hit }}

.github/workflows/unit-tests.yml

@@ -167,6 +167,13 @@ jobs:
           ${{ ! (matrix.name == 'Freethreading' || matrix.name == 'Minimum Versions') && '-Csetup-args="--werror"' || '' }}
       shell: bash -euox pipefail {0}
 
+    - name: Import check
+      run: |
+        pixi run \
+          --environment ${{ matrix.environment }} \
+          ci-check-import
+      shell: bash -euox pipefail {0}
+
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
       id: test-not-single-cpu

.pre-commit-config.yaml

@@ -132,7 +132,7 @@ repos:
     -   id: mypy
         # note: assumes python env is setup and activated
         name: mypy
-        entry: mypy
+        entry: python -m mypy
         language: system
         pass_filenames: false
         types: [python]

ci/import_pandas_check.py

@@ -0,0 +1,31 @@
+import sys
+
+import pandas  # noqa: F401
+
+blocklist = {
+    "bs4",
+    "gcsfs",
+    "html5lib",
+    "http",
+    "ipython",
+    "jinja2",
+    "hypothesis",
+    "lxml",
+    "matplotlib",
+    "openpyxl",
+    "py",
+    "pytest",
+    "s3fs",
+    "scipy",
+    "tables",
+    "urllib.request",
+    "xlrd",
+    "xlsxwriter",
+}
+
+# GH#28227 for some of these check for top-level modules, while others are
+#  more specific (e.g. urllib.request)
+import_mods = {m.split(".")[0] for m in sys.modules} | set(sys.modules)
+mods = blocklist & import_mods
+if mods:
+    raise Exception(f"pandas should not import {', '.join(mods)}")

doc/source/development/contributing_codebase.rst

@@ -18,15 +18,9 @@ tools will be run to check your code for stylistic errors.
 Generating any warnings will cause the test to fail.
 Thus, good style is a requirement for submitting code to pandas.
 
-There are a couple of tools in pandas to help contributors verify their changes
+``pre-commit``, which we go into detail on in the next section, helps contributors verify their changes
 before contributing to the project
 
-- ``./ci/code_checks.sh``: a script validates the doctests, imported modules,
-  and notebooks. It is possible to run the checks independently by
-  using the parameters ``code``, ``doctests``, and ``notebooks``
-  (e.g. ``./ci/code_checks.sh doctests``).
-- ``pre-commit``, which we go into detail on in the next section.
-
 In addition, because a lot of people use our library, it is important that we
 do not make sudden changes to the code that could have the potential to break
 a lot of user code as a result, that is, we need it to be as *backwards compatible*

pandas/core/frame.py

@@ -1996,8 +1996,8 @@ def to_dict(
 
         >>> from collections import OrderedDict, defaultdict
         >>> df.to_dict(into=OrderedDict)
-        OrderedDict([('col1', OrderedDict([('row1', 1), ('row2', 2)])),
-                     ('col2', OrderedDict([('row1', 0.5), ('row2', 0.75)]))])
+        OrderedDict({'col1': OrderedDict({'row1': 1, 'row2': 2}),
+                     'col2': OrderedDict({'row1': 0.5, 'row2': 0.75})})
 
         If you want a `defaultdict`, you need to initialize it:
 

pandas/core/series.py

@@ -1852,7 +1852,7 @@ def to_dict(
         {0: 1, 1: 2, 2: 3, 3: 4}
         >>> from collections import OrderedDict, defaultdict
         >>> s.to_dict(into=OrderedDict)
-        OrderedDict([(0, 1), (1, 2), (2, 3), (3, 4)])
+        OrderedDict({0: 1, 1: 2, 2: 3, 3: 4})
         >>> dd = defaultdict(list)
         >>> s.to_dict(into=dd)
         defaultdict(<class 'list'>, {0: 1, 1: 2, 2: 3, 3: 4})