update-data.yml

name: Update Data

on:
  workflow_dispatch:  # Manual trigger
  push:
    branches: [ main ]
  schedule:
    - cron: '0 12 * * *'  # 6 AM Chicago (CST), 7 AM during CDT

permissions:
  contents: write
  pages: write
  id-token: write

jobs:

  create:
    if: ${{ github.event_name == 'workflow_dispatch'
          || github.event_name == 'schedule'
          || contains(github.event.head_commit.message, 'data update') }}
    name: create dataset
    runs-on: ubuntu-latest
    permissions:
      contents: write
    outputs:
      pushed: ${{ steps.commit.outputs.pushed }}
    steps:
      - name: Checkout
        uses: actions/checkout@v3
      - name: Set up Python 3.10
        uses: actions/setup-python@v4
        with:
          python-version: '3.10'
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt
      - name: clean dir
        run: |
          rm -rf data
          mkdir data
      - name: Run script
        run: |
          python scripts/create_dataset.py
          ls data
      - name: check if successful, then commit
        id: commit
        run: |
          if [ -f done ]; then
            echo "generated dataset successfully"
            git config user.name github-actions
            git config user.email github-actions@github.com
            git add -A data/
            if git diff --cached --quiet; then
              echo "no data changes to commit"
              echo "pushed=false" >> $GITHUB_OUTPUT
            else
              git commit -m "Update data"
              git push
              echo "pushed=true" >> $GITHUB_OUTPUT
            fi
          else
            echo "failed to generate dataset"
            echo "pushed=false" >> $GITHUB_OUTPUT
          fi

  deploy:
    needs: create
    if: needs.create.outputs.pushed == 'true'
    uses: ./.github/workflows/deploy.yml