Merge branch 'main' into main

Author: datapythonista

.circleci/config.yml

@@ -14,9 +14,82 @@ jobs:
     steps:
       - checkout
       - run: .circleci/setup_env.sh
-      - run: PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH ci/run_tests.sh
+      - run: >
+          PATH=$HOME/miniconda3/envs/pandas-dev/bin:$HOME/miniconda3/condabin:$PATH
+          LD_PRELOAD=$HOME/miniconda3/envs/pandas-dev/lib/libgomp.so.1:$LD_PRELOAD
+          ci/run_tests.sh
+  build-aarch64:
+    parameters:
+      cibw-build:
+        type: string
+    machine:
+      image: ubuntu-2004:202101-01
+    resource_class: arm.large
+    environment:
+      ENV_FILE: ci/deps/circle-38-arm64.yaml
+      TRIGGER_SOURCE: << pipeline.trigger_source >>
+    steps:
+      - checkout
+      - run:
+          name: Check if build is necessary
+          command: |
+            # Check if tag is defined or TRIGGER_SOURCE is scheduled
+            if [[ -n "$CIRCLE_TAG" ]]; then
+                echo 'export IS_PUSH="true"' >> "$BASH_ENV"
+            elif [[ $TRIGGER_SOURCE == "scheduled_pipeline" ]]; then
+                echo 'export IS_SCHEDULE_DISPATCH="true"' >> "$BASH_ENV"
+            # Look for the build label/[wheel build] in commit
+            # grep takes a regex, so need to escape brackets
+            elif (git log --format=oneline -n 1 $CIRCLE_SHA1) | grep -q '\[wheel build\]'; then
+                : # Do nothing
+            elif ! (curl https://api.github.com/repos/pandas-dev/pandas/issues/$CIRCLE_PR_NUMBER | jq '.labels' | grep -q 'Build'); then
+                circleci-agent step halt
+            fi
+      - run:
+          name: Build aarch64 wheels
+          command: |
+            pip3 install cibuildwheel==2.9.0
+            cibuildwheel --output-dir wheelhouse
+          environment:
+            CIBW_BUILD: << parameters.cibw-build >>
+
+      - run:
+          name: Install Anaconda Client & Upload Wheels
+          command: |
+            echo "Install Mambaforge"
+            MAMBA_URL="https://github.com/conda-forge/miniforge/releases/download/4.14.0-0/Mambaforge-4.14.0-0-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
+
+            source ci/upload_wheels.sh
+            set_upload_vars
+            upload_wheels
+      - store_artifacts:
+          path: wheelhouse/
 
 workflows:
   test:
+    # Don't run trigger this one when scheduled pipeline runs
+    when:
+      not:
+        equal: [ scheduled_pipeline, << pipeline.trigger_source >> ]
     jobs:
       - test-arm
+  build-wheels:
+    jobs:
+      - build-aarch64:
+          filters:
+            tags:
+              only: /^v.*/
+          matrix:
+            parameters:
+              cibw-build: ["cp38-manylinux_aarch64", "cp39-manylinux_aarch64", "cp310-manylinux_aarch64", "cp311-manylinux_aarch64"]

.github/workflows/32-bit-linux.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
     paths-ignore:
       - "doc/**"
@@ -52,3 +54,7 @@ jobs:
           name: Test results
           path: test-data.xml
         if: failure()
+    concurrency:
+      # https://github.community/t/concurrecy-not-work-for-push/183068/7
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-32bit
+      cancel-in-progress: true

.github/workflows/code-checks.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
 
 env:

.github/workflows/deprecation-tracking-bot.yml

@@ -0,0 +1,31 @@
+name: Deprecations Bot
+
+on:
+  pull_request:
+    branches:
+      - main
+    types:
+      [closed]
+
+
+permissions:
+  contents: read
+
+jobs:
+  deprecation_update:
+    permissions:
+      issues: write
+    if: >-
+      contains(github.event.pull_request.labels.*.name, 'Deprecate') && github.event.pull_request.merged == true
+    runs-on: ubuntu-22.04
+    env:
+      DEPRECATION_TRACKER_ISSUE: 50578
+    steps:
+    - name: Checkout
+      run: |
+        echo "Adding deprecation PR number to deprecation tracking issue"
+        export PR=${{ github.event.pull_request.number }}
+        BODY=$(curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" https://api.github.com/repos/${{ github.repository }}/issues/${DEPRECATION_TRACKER_ISSUE} |
+          python3 -c "import sys, json, os; x = {'body': json.load(sys.stdin)['body']}; pr = os.environ['PR']; x['body'] += f'\n- [ ] #{pr}'; print(json.dumps(x))")
+        echo ${BODY}
+        curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -X PATCH -d "${BODY}" https://api.github.com/repos/${{ github.repository }}/issues/${DEPRECATION_TRACKER_ISSUE}

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

@@ -4,12 +4,14 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
 
 env:
@@ -87,3 +89,10 @@ jobs:
         name: website
         path: web/build
         retention-days: 14
+
+    - name: Trigger web/doc preview
+      run: curl -X POST https://pandas.pydata.org/preview/submit/$RUN_ID/$PR_ID/
+      env:
+        RUN_ID: ${{ github.run_id }}
+        PR_ID: ${{ github.event.pull_request.number }}
+      if: github.event_name == 'pull_request'

.github/workflows/macos-windows.yml

@@ -4,20 +4,21 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
     paths-ignore:
       - "doc/**"
+      - "web/**"
 
 env:
   PANDAS_CI: 1
   PYTEST_TARGET: pandas
   PATTERN: "not slow and not db and not network and not single_cpu"
-  ERROR_ON_WARNINGS: "1"
-
 
 permissions:
   contents: read

.github/workflows/package-checks.yml

@@ -4,10 +4,12 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
     types: [ labeled, opened, synchronize, reopened ]
 

.github/workflows/preview-docs.yml

@@ -0,0 +1,22 @@
+name: Preview docs
+on:
+  issue_comment:
+    types: created
+
+permissions:
+  contents: read
+
+jobs:
+  preview_docs:
+    permissions:
+      issues: write
+      pull-requests: write
+    runs-on: ubuntu-22.04
+    steps:
+    - if: github.event.comment.body == '/preview'
+      run: |
+        if curl --output /dev/null --silent --head --fail "https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"; then
+          curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "Website preview of this PR available at: https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
+        else
+          curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "No preview found for PR #${{ github.event.issue.number }}. Did the docs build complete?"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
+        fi

.github/workflows/python-dev.yml

@@ -33,6 +33,7 @@ on:
       - None
     paths-ignore:
       - "doc/**"
+      - "web/**"
 
 env:
   PYTEST_WORKERS: "auto"

.github/workflows/sdist.yml

@@ -4,14 +4,17 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
     types: [labeled, opened, synchronize, reopened]
     paths-ignore:
       - "doc/**"
+      - "web/**"
 
 permissions:
   contents: read
@@ -92,5 +95,4 @@ jobs:
     - name: Import pandas
       run: |
         cd ..
-        conda list
         python -c "import pandas; pandas.show_versions();"

.github/workflows/ubuntu.yml

@@ -4,16 +4,16 @@ on:
   push:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
   pull_request:
     branches:
       - main
+      - 2.0.x
       - 1.5.x
     paths-ignore:
       - "doc/**"
-
-env:
-  PANDAS_CI: 1
+      - "web/**"
 
 permissions:
   contents: read
@@ -29,7 +29,8 @@ jobs:
       matrix:
         env_file: [actions-38.yaml, actions-39.yaml, actions-310.yaml, actions-311.yaml]
         pattern: ["not single_cpu", "single_cpu"]
-        pyarrow_version: ["7", "8", "9", "10"]
+        pyarrow_version: ["8", "9", "10"]
+        pandas_ci: [1]
         include:
           - name: "Downstream Compat"
             env_file: actions-38-downstream_compat.yaml
@@ -38,7 +39,6 @@ jobs:
           - name: "Minimum Versions"
             env_file: actions-38-minimum_versions.yaml
             pattern: "not slow and not network and not single_cpu"
-            error_on_warnings: "0"
           - name: "Locale: it_IT"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -63,52 +63,45 @@ jobs:
             env_file: actions-310.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_copy_on_write: "1"
-            error_on_warnings: "0"
           - name: "Data Manager"
             env_file: actions-38.yaml
             pattern: "not slow and not network and not single_cpu"
             pandas_data_manager: "array"
-            error_on_warnings: "0"
           - name: "Pypy"
             env_file: actions-pypy-38.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
-            error_on_warnings: "0"
           - name: "Numpy Dev"
             env_file: actions-310-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "-W error::DeprecationWarning -W error::FutureWarning"
-            error_on_warnings: "0"
+            # TODO(cython3): Re-enable once next-beta(after beta 1) comes out
+            # There are some warnings failing the build with -werror
+            pandas_ci: 0
         exclude:
-          - env_file: actions-38.yaml
-            pyarrow_version: "7"
           - env_file: actions-38.yaml
             pyarrow_version: "8"
           - env_file: actions-38.yaml
             pyarrow_version: "9"
-          - env_file: actions-39.yaml
-            pyarrow_version: "7"
           - env_file: actions-39.yaml
             pyarrow_version: "8"
           - env_file: actions-39.yaml
             pyarrow_version: "9"
-          - env_file: actions-311.yaml
-            pyarrow_version: "7"
-          - env_file: actions-311.yaml
+          - env_file: actions-310.yaml
             pyarrow_version: "8"
-          - env_file: actions-311.yaml
+          - env_file: actions-310.yaml
             pyarrow_version: "9"
       fail-fast: false
     name: ${{ matrix.name || format('{0} pyarrow={1} {2}', matrix.env_file, matrix.pyarrow_version, matrix.pattern) }}
     env:
       ENV_FILE: ci/deps/${{ matrix.env_file }}
       PATTERN: ${{ matrix.pattern }}
       EXTRA_APT: ${{ matrix.extra_apt || '' }}
-      ERROR_ON_WARNINGS: ${{ matrix.error_on_warnings || '1' }}
       LANG: ${{ matrix.lang || '' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_DATA_MANAGER: ${{ matrix.pandas_data_manager || 'block' }}
       PANDAS_COPY_ON_WRITE: ${{ matrix.pandas_copy_on_write || '0' }}
+      PANDAS_CI: ${{ matrix.pandas_ci }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: ${{ contains(matrix.pattern, 'not single_cpu') && 'auto' || '1' }}
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}

.github/workflows/wheels.yml

@@ -86,7 +86,8 @@ jobs:
           activate-environment: test
           channels: conda-forge, anaconda
           channel-priority: true
-          mamba-version: "*"
+          # mamba fails to solve, also we really don't need this since we're just installing python
+          # mamba-version: "*"
 
       - name: Test wheels (Windows 64-bit only)
         if: ${{ matrix.buildplat[1] == 'win_amd64' }}
@@ -154,7 +155,8 @@ jobs:
           python-version: '3.8'
           channels: conda-forge
           channel-priority: true
-          mamba-version: "*"
+          # mamba fails to solve, also we really don't need this since we're just installing python
+          # mamba-version: "*"
 
       - name: Build sdist
         run: |
@@ -171,8 +173,8 @@ jobs:
           pip install hypothesis>=6.34.2 pytest>=7.0.0 pytest-xdist>=2.2.0 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'])"
+          pandas.test(extra_args=['-m not clipboard and not single_cpu and not slow and not network and not db', '-n 2']);
+          pandas.test(extra_args=['-m not clipboard and single_cpu and not slow and not network and not db'])"
       - uses: actions/upload-artifact@v3
         with:
           name: sdist