data_validation.yml

name: Data validation with deepchecks

on:
  push:
    branches: [ main ]
  pull_request:
    branches: [ main ]

permissions: write-all

jobs:
  run_data_checks:

    runs-on: ubuntu-latest
    env:
      DVC_USERNAME: ${{ secrets.DVC_USERNAME }}
      DVC_PASSWORD: ${{ secrets.DVC_PASSWORD }}

    steps:
    - uses: actions/checkout@v3
    
    - name: Set up Python 3.10
      uses: actions/setup-python@v3
      with:
        python-version: "3.10"
    
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install -r requirements.txt
    
    - name: Get data
      run: |
        # dvc remote add origin https://dagshub.com/eryk.lewinson/mario_vs_wario_v2.dvc
        dvc remote modify origin --local auth basic
        dvc remote modify origin --local user $DVC_USERNAME
        dvc remote modify origin --local password $DVC_PASSWORD
        dvc pull create_train_test_split -r origin

    - name: Remove the old validation report
      run:
        rm -f data_validation.html
        
    - name: Validate data with deepchecks
      run: |
        python src/validate_data.py
    
    - name: Commit the validation report file
      uses: stefanzweifel/git-auto-commit-action@v4
      with:
        commit_message: Added the data validation file
        
    - name: Create a comment
      uses: peter-evans/commit-comment@v1
      with:
        body: |
          Please check the data_validation.html file for a full validation report.