cml.yaml

name: DVC Workflow

on:
  pull_request:
    branches:
    - main
    paths:
    - '**/*.dvc'
    - '.dvc/**'

jobs:
  run_data_checker:
    runs-on: ${{ matrix.operating-system }}
    strategy:
      matrix:
        operating-system: [ "ubuntu-latest", "windows-latest", "macos-latest" ]
        python-version: [ "3.12", "3.11" ]
    steps:
    - name: Checkout code
      uses: actions/checkout@v4

    - name: Set up Python
      uses: actions/setup-python@v5
      with:
        python-version: ${{ matrix.python-version }}
        cache: 'pip'
        cache-dependency-path: pyproject.toml

    - name: Install dependencies
      run: |
        pip install -r requirements.txt
        pip install -r requirements_dev.txt
        pip list

    - name: Pull data
      run: |
        dvc pull --no-run-cache

    - name: Check data statistics
      run: |
        python data_stats.py