update_data.yml

name: Update KRX Marcap Dataset

on:
  schedule:
    # Runs at 18:30 KST (09:30 UTC) Monday through Friday
    - cron: '30 9 * * 1-5'
  workflow_dispatch: # Allows manual triggering from GitHub UI

jobs:
  update-data:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.11'

      - name: Install uv
        run: curl -LsSf https://astral.sh/uv/install.sh | sh

      - name: Install dependencies
        run: |
          uv pip install --system pandas numpy requests pyarrow

      - name: Run Update Script
        env:
          KRX_ID: ${{ secrets.KRX_ID }}
          KRX_PW: ${{ secrets.KRX_PW }}
          # START_YEAR is omitted to auto-default to current year in GHA environment
        run: |
          python krx_marcap.py

      - name: Commit and Push changes
        run: |
          git config --global user.name "github-actions[bot]"
          git config --global user.email "github-actions[bot]@users.noreply.github.com"
          git add data/
          git diff-index --quiet HEAD || (git commit -m "auto-update dataset [skip ci]" && git push origin master)