run_data_pipeline.yml

name: Run data pipeline
on:
  workflow_run:
    workflows: ["Increase Data Version"]
    types:
      - completed 
  workflow_dispatch: 

jobs:
  run-dvc-pipeline:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout Repository
        uses: actions/checkout@v3  

      - name: Setup DVC
        uses: iterative/setup-dvc@v1 

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install python-box ensure pandas pathlib scikit-learn dagshub mlflow numpy

      - name: Run DVC pipeline | retrain model 
        run: |
          dvc repro data_update
          dvc repro data_validation
          dvc repro data_transformation
          dvc repro model_train
          dvc repro model_evaluation

      - name: Commit and push updated model
        run: |
          git config --global user.name 'github-actions'
          git config --global user.email 'github-actions@github.com'
          git add models/model.pkl
          git commit -m "[Github Action]: Update model with retrained model"
          git push