.github/workflows/deploy-assets.yml

name: deploy-assets

on:
  workflow_dispatch:
    inputs:
      repo_id:
        description: "HF repo id (e.g. stephmnt/assets-credit-scoring-mlops)"
        required: true
        default: "stephmnt/assets-credit-scoring-mlops"
      repo_type:
        description: "HF repo type (dataset or model)"
        required: true
        default: "dataset"
  push:
    branches: ["main"]
    paths:
      - "data/*_final_model.pkl"

jobs:
  upload-assets:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

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

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          python -m pip install huggingface_hub

      - name: Upload assets to Hugging Face Hub
        env:
          HF_TOKEN: ${{ secrets.HF_TOKEN }}
          HF_REPO_ID: ${{ inputs.repo_id || 'stephmnt/assets-credit-scoring-mlops' }}
          HF_REPO_TYPE: ${{ inputs.repo_type || 'dataset' }}
        run: |
          python - <<'PY'
          import os
          from pathlib import Path
          from huggingface_hub import HfApi
          
          repo_id = os.environ["HF_REPO_ID"]
          repo_type = os.environ["HF_REPO_TYPE"]
          token = os.environ["HF_TOKEN"]
          
          candidates = sorted(Path("data").glob("*_final_model.pkl"))
          if not candidates:
              raise SystemExit("Missing model file: data/*_final_model.pkl")
          if len(candidates) > 1:
              names = ", ".join(path.name for path in candidates)
              raise SystemExit(f"Multiple *_final_model.pkl files found: {names}")
          model_path = candidates[0]
          
          api = HfApi()
          existing = api.list_repo_files(
              repo_id=repo_id,
              repo_type=repo_type,
              token=token,
          )
          to_delete = [
              name
              for name in existing
              if name.endswith("_final_model.pkl") and name != model_path.name
          ]
          for name in to_delete:
              api.delete_file(
                  path_in_repo=name,
                  repo_id=repo_id,
                  repo_type=repo_type,
                  token=token,
                  commit_message=f"Remove {name}",
              )
          for path in [model_path]:
              api.upload_file(
                  path_or_fileobj=str(path),
                  path_in_repo=path.name,
                  repo_id=repo_id,
                  repo_type=repo_type,
                  token=token,
                  commit_message=f"Update {path.name}",
              )
          print("Assets uploaded.")
          PY