Add GitHub Actions workflow for auto data generation

- Add CLI module (scottish_budget_data/cli.py) for command-line usage
- Add GitHub Actions workflow that triggers on push to main
- Workflow runs Python pipeline and commits generated CSV files
- Prevents infinite loops with [skip ci] in commit message
- Update pyproject.toml with CLI entry point

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: vahid-ahmadi

.github/workflows/generate-data.yml

@@ -0,0 +1,62 @@
+name: Generate Dashboard Data
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'src/scottish_budget_data/**'
+      - 'data_inputs/**'
+      - '.github/workflows/generate-data.yml'
+  workflow_dispatch:
+
+jobs:
+  generate:
+    runs-on: ubuntu-latest
+    # Skip if commit was made by this action to prevent infinite loops
+    if: "!contains(github.event.head_commit.message, '[skip ci]') && !contains(github.event.head_commit.message, 'Auto-generate dashboard data')"
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        run: uv python install 3.11
+
+      - name: Install dependencies
+        env:
+          HUGGING_FACE_TOKEN: ${{ secrets.HUGGING_FACE_TOKEN }}
+        run: |
+          uv pip install --system policyengine-uk pandas numpy h5py
+
+      - name: Generate dashboard data
+        env:
+          HUGGING_FACE_TOKEN: ${{ secrets.HUGGING_FACE_TOKEN }}
+          PYTHONPATH: ${{ github.workspace }}/src
+        run: |
+          cd ${{ github.workspace }}
+          python -c "from scottish_budget_data import generate_all_data; generate_all_data()"
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          if git diff --quiet public/data/; then
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit and push changes
+        if: steps.check_changes.outputs.has_changes == 'true'
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add public/data/
+          git commit -m "Auto-generate dashboard data [skip ci]"
+          git push

pyproject.toml

@@ -12,7 +12,7 @@ dependencies = [
 ]
 
 [project.scripts]
-generate-data = "scottish_budget_data.pipeline:generate_all_data"
+scottish-budget-data = "scottish_budget_data.cli:main"
 
 [build-system]
 requires = ["setuptools>=61.0"]

src/scottish_budget_data/cli.py

@@ -0,0 +1,104 @@
+"""Command-line interface for Scottish Budget Data generation."""
+
+import argparse
+import sys
+from pathlib import Path
+
+from scottish_budget_data.pipeline import generate_all_data
+from scottish_budget_data.reforms import get_scottish_budget_reforms
+
+
+def parse_args(args: list[str] = None) -> argparse.Namespace:
+    """Parse command-line arguments."""
+    parser = argparse.ArgumentParser(
+        prog="scottish-budget-data",
+        description="Generate data for Scottish Budget dashboard.",
+    )
+
+    parser.add_argument(
+        "--output-dir",
+        type=Path,
+        default=Path("./public/data"),
+        help="Output directory for CSV files (default: ./public/data)",
+    )
+
+    parser.add_argument(
+        "--data-dir",
+        type=Path,
+        default=Path("./data"),
+        help="Directory containing input data files (default: ./data)",
+    )
+
+    parser.add_argument(
+        "--data-inputs-dir",
+        type=Path,
+        default=Path("./data_inputs"),
+        help="Directory containing reference data (default: ./data_inputs)",
+    )
+
+    parser.add_argument(
+        "--years",
+        nargs="+",
+        type=int,
+        default=[2026, 2027, 2028, 2029, 2030],
+        help="Years to calculate (default: 2026 2027 2028 2029 2030)",
+    )
+
+    parser.add_argument(
+        "--list-reforms",
+        action="store_true",
+        help="List all available reform IDs and exit",
+    )
+
+    return parser.parse_args(args)
+
+
+def print_reforms_list() -> None:
+    """Print a list of available reforms."""
+    print("\nAvailable Reforms:")
+    print("-" * 50)
+    for reform in get_scottish_budget_reforms():
+        print(f"  {reform.id}: {reform.name}")
+    print()
+
+
+def main(args: list[str] = None) -> int:
+    """Main entry point for CLI."""
+    parsed = parse_args(args)
+
+    if parsed.list_reforms:
+        print_reforms_list()
+        return 0
+
+    print("\n" + "=" * 50)
+    print("Scottish Budget Data Generator")
+    print("=" * 50)
+    print(f"Output: {parsed.output_dir}")
+    print(f"Years: {parsed.years}")
+
+    reforms = get_scottish_budget_reforms()
+    print(f"Reforms: {len(reforms)}")
+    print()
+
+    try:
+        generate_all_data(
+            reforms=reforms,
+            output_dir=parsed.output_dir,
+            data_dir=parsed.data_dir,
+            data_inputs_dir=parsed.data_inputs_dir,
+            years=parsed.years,
+        )
+        print("\n" + "=" * 50)
+        print("Data generation complete!")
+        print("=" * 50 + "\n")
+        return 0
+    except FileNotFoundError as e:
+        print(f"\nError: {e}")
+        return 1
+    except Exception as e:
+        print(f"\nUnexpected error: {e}")
+        raise
+
+
+if __name__ == "__main__":
+    sys.exit(main())