Deploy GitHub Pages #2810
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Deploy GitHub Pages | |
| on: | |
| push: | |
| branches: [ main, review ] | |
| pull_request: | |
| branches: [ review ] | |
| types: [opened, synchronize, reopened] | |
| schedule: | |
| # Update every hour | |
| - cron: '0 * * * *' | |
| workflow_dispatch: | |
| permissions: | |
| id-token: write | |
| contents: read | |
| pages: write | |
| concurrency: | |
| group: "pages" | |
| cancel-in-progress: false | |
| jobs: | |
| build-and-deploy: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Setup Python | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: '3.9' | |
| - name: Install Python dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install requests python-dateutil | |
| - name: Generate submission data | |
| env: | |
| GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} | |
| run: | | |
| python << 'EOF' | |
| import json | |
| import os | |
| import glob | |
| import requests | |
| from pathlib import Path | |
| from datetime import datetime, timezone | |
| def fetch_pr_data(submissions): | |
| """Fetch PR data from GitHub API and match with submissions to detect track""" | |
| token = os.environ.get('GITHUB_TOKEN') | |
| repo = os.environ.get('GITHUB_REPOSITORY', 'PlotSenseAI/PlotSenseAI-Hackathon-Submissions') | |
| headers = {'Authorization': f'token {token}'} if token else {} | |
| # Create submission ID to track mapping | |
| submission_map = {sub['id']: sub.get('track', 'Unknown') for sub in submissions} | |
| # Fetch open PRs targeting review branch | |
| open_prs_url = f'https://api.github.com/repos/{repo}/pulls?state=open&base=review&per_page=100' | |
| merged_prs_url = f'https://api.github.com/repos/{repo}/pulls?state=closed&base=review&per_page=100' | |
| pr_data = { | |
| 'open_prs': [], | |
| 'merged_prs': [], | |
| 'total_open': 0, | |
| 'total_merged': 0, | |
| 'ml_track': {'open': 0, 'merged': 0}, | |
| 'dev_track': {'open': 0, 'merged': 0} | |
| } | |
| def extract_track_from_pr(pr_title, pr_number): | |
| """Extract track from PR title by matching submission ID or inferring from title""" | |
| import re | |
| # Method 1: Try to find submission ID in format PSH2025-XXX | |
| match = re.search(r'PSH2025-\d{3}', pr_title) | |
| if match: | |
| submission_id = match.group(0) | |
| track = submission_map.get(submission_id) | |
| if track and track != 'Unknown': | |
| return track | |
| # Method 2: Try to fetch PR files to check which folder they're in | |
| try: | |
| files_url = f'https://api.github.com/repos/{repo}/pulls/{pr_number}/files' | |
| files_response = requests.get(files_url, headers=headers, timeout=10) | |
| if files_response.status_code == 200: | |
| files = files_response.json() | |
| for file in files: | |
| filename = file.get('filename', '') | |
| if 'plotsense-2025-ml' in filename: | |
| return 'PlotSense ML' | |
| elif 'plotsense-2025-dev' in filename: | |
| return 'PlotSense Dev' | |
| except Exception as e: | |
| print(f"Could not fetch files for PR #{pr_number}: {e}") | |
| # Method 3: Infer from PR title keywords | |
| title_lower = pr_title.lower() | |
| if 'ml track' in title_lower or 'machine learning' in title_lower or 'plotsense ml' in title_lower: | |
| return 'PlotSense ML' | |
| elif 'dev track' in title_lower or 'development' in title_lower or 'plotsense dev' in title_lower: | |
| return 'PlotSense Dev' | |
| return 'Unknown' | |
| try: | |
| # Get open PRs | |
| response = requests.get(open_prs_url, headers=headers, timeout=10) | |
| if response.status_code == 200: | |
| open_prs = response.json() | |
| for pr in open_prs: | |
| track = extract_track_from_pr(pr['title'], pr['number']) | |
| pr_data['open_prs'].append({ | |
| 'number': pr['number'], | |
| 'title': pr['title'], | |
| 'user': pr['user']['login'], | |
| 'created_at': pr['created_at'], | |
| 'html_url': pr['html_url'], | |
| 'state': 'open', | |
| 'track': track | |
| }) | |
| # Count by track | |
| if track == 'PlotSense ML': | |
| pr_data['ml_track']['open'] += 1 | |
| elif track == 'PlotSense Dev': | |
| pr_data['dev_track']['open'] += 1 | |
| pr_data['total_open'] = len(pr_data['open_prs']) | |
| # Get merged PRs | |
| response = requests.get(merged_prs_url, headers=headers, timeout=10) | |
| if response.status_code == 200: | |
| closed_prs = response.json() | |
| merged_prs = [pr for pr in closed_prs if pr.get('merged_at')] | |
| for pr in merged_prs: | |
| track = extract_track_from_pr(pr['title'], pr['number']) | |
| pr_data['merged_prs'].append({ | |
| 'number': pr['number'], | |
| 'title': pr['title'], | |
| 'user': pr['user']['login'], | |
| 'created_at': pr['created_at'], | |
| 'merged_at': pr['merged_at'], | |
| 'html_url': pr['html_url'], | |
| 'state': 'merged', | |
| 'track': track | |
| }) | |
| # Count by track | |
| if track == 'PlotSense ML': | |
| pr_data['ml_track']['merged'] += 1 | |
| elif track == 'PlotSense Dev': | |
| pr_data['dev_track']['merged'] += 1 | |
| pr_data['total_merged'] = len(pr_data['merged_prs']) | |
| print(f"Fetched {pr_data['total_open']} open PRs and {pr_data['total_merged']} merged PRs") | |
| print(f"ML Track: {pr_data['ml_track']['open']} open, {pr_data['ml_track']['merged']} merged") | |
| print(f"Dev Track: {pr_data['dev_track']['open']} open, {pr_data['dev_track']['merged']} merged") | |
| except Exception as e: | |
| print(f"Error fetching PR data: {e}") | |
| return pr_data | |
| def collect_submissions(): | |
| submissions = [] | |
| submission_files = [] | |
| for track_dir in ['submissions/plotsense-2025-ml', 'submissions/plotsense-2025-dev']: | |
| if os.path.exists(track_dir): | |
| for file_path in glob.glob(f"{track_dir}/*.json"): | |
| if not file_path.endswith('TEMPLATE.json'): | |
| submission_files.append(file_path) | |
| for file_path in submission_files: | |
| try: | |
| with open(file_path, 'r') as f: | |
| submission = json.load(f) | |
| file_stat = os.stat(file_path) | |
| submission['submitted_date'] = datetime.fromtimestamp( | |
| file_stat.st_mtime, tz=timezone.utc | |
| ).isoformat() | |
| submission['file_path'] = file_path | |
| if 'tech_stack' not in submission: | |
| if submission.get('track') == 'PlotSense ML': | |
| submission['tech_stack'] = ['Python', 'PlotSenseAI', 'Pandas', 'Scikit-learn'] | |
| else: | |
| submission['tech_stack'] = ['JavaScript', 'PlotSenseAI', 'React', 'Node.js'] | |
| submission['status'] = 'pending' | |
| required_fields = ['id', 'track', 'project_name', 'team_name', 'repo_url'] | |
| if all(field in submission and submission[field] for field in required_fields): | |
| submission['status'] = 'validated' | |
| submissions.append(submission) | |
| except (json.JSONDecodeError, FileNotFoundError) as e: | |
| print(f"Error processing {file_path}: {e}") | |
| continue | |
| return submissions | |
| def generate_metrics(submissions, pr_data): | |
| # Filter out submissions with Unknown track (used for testing) | |
| submissions = [s for s in submissions if s.get('track') != 'Unknown'] | |
| # Filter out PRs with Unknown track from PR data | |
| if pr_data: | |
| pr_data['open_prs'] = [pr for pr in pr_data.get('open_prs', []) if pr.get('track') != 'Unknown'] | |
| pr_data['merged_prs'] = [pr for pr in pr_data.get('merged_prs', []) if pr.get('track') != 'Unknown'] | |
| pr_data['total_open'] = len(pr_data['open_prs']) | |
| pr_data['total_merged'] = len(pr_data['merged_prs']) | |
| if not submissions and pr_data.get('total_open', 0) == 0 and pr_data.get('total_merged', 0) == 0: | |
| return { | |
| 'total_submissions': 0, | |
| 'total_teams': 0, | |
| 'tracks': {'PlotSense ML': 0, 'PlotSense Dev': 0}, | |
| 'status_counts': {'validated': 0, 'pending': 0, 'failed': 0}, | |
| 'tech_stack_usage': {}, | |
| 'team_sizes': {}, | |
| 'submission_timeline': [], | |
| 'prs': pr_data or { | |
| 'open_prs': [], | |
| 'merged_prs': [], | |
| 'total_open': 0, | |
| 'total_merged': 0, | |
| 'ml_track': {'open': 0, 'merged': 0}, | |
| 'dev_track': {'open': 0, 'merged': 0} | |
| } | |
| } | |
| # Calculate total submissions from PRs (open + merged), not JSON files | |
| total_pr_count = pr_data.get('total_open', 0) + pr_data.get('total_merged', 0) | |
| # Count unique teams from PRs | |
| all_prs = pr_data.get('open_prs', []) + pr_data.get('merged_prs', []) | |
| unique_teams = len(set(pr.get('user', '') for pr in all_prs if pr.get('user'))) | |
| metrics = { | |
| 'total_submissions': total_pr_count, | |
| 'total_teams': unique_teams if unique_teams > 0 else len(submissions), | |
| 'tracks': {}, | |
| 'status_counts': {'validated': 0, 'pending': 0, 'failed': 0}, | |
| 'tech_stack_usage': {}, | |
| 'team_sizes': {}, | |
| 'submission_timeline': [], | |
| 'prs': pr_data | |
| } | |
| # Count tracks from PRs | |
| for track in ['PlotSense ML', 'PlotSense Dev']: | |
| track_count = len([pr for pr in all_prs if pr.get('track') == track]) | |
| metrics['tracks'][track] = track_count | |
| for status in ['validated', 'pending', 'failed']: | |
| metrics['status_counts'][status] = len([s for s in submissions if s.get('status') == status]) | |
| for submission in submissions: | |
| if 'tech_stack' in submission: | |
| for tech in submission['tech_stack']: | |
| metrics['tech_stack_usage'][tech] = metrics['tech_stack_usage'].get(tech, 0) + 1 | |
| for submission in submissions: | |
| if 'team_members' in submission: | |
| size = len(submission['team_members']) | |
| metrics['team_sizes'][str(size)] = metrics['team_sizes'].get(str(size), 0) + 1 | |
| timeline = {} | |
| for submission in submissions: | |
| if 'submitted_date' in submission: | |
| date = submission['submitted_date'][:10] | |
| timeline[date] = timeline.get(date, 0) + 1 | |
| metrics['submission_timeline'] = [{'date': date, 'count': count} for date, count in sorted(timeline.items())] | |
| return metrics | |
| # Collect September 2025 submissions first | |
| submissions = collect_submissions() | |
| # Fetch PR data with submission context for track detection | |
| pr_data = fetch_pr_data(submissions) | |
| # Generate metrics with PR data | |
| metrics = generate_metrics(submissions, pr_data) | |
| # Create directory structure for September 2025 hackathon | |
| os.makedirs('docs/data/september-2025', exist_ok=True) | |
| # Save September 2025 data | |
| with open('docs/data/september-2025/submissions.json', 'w') as f: | |
| json.dump(submissions, f, indent=2, default=str) | |
| with open('docs/data/september-2025/metrics.json', 'w') as f: | |
| json.dump(metrics, f, indent=2, default=str) | |
| # Also save to legacy locations for backward compatibility | |
| os.makedirs('docs/data', exist_ok=True) | |
| with open('docs/data/submissions.json', 'w') as f: | |
| json.dump(submissions, f, indent=2, default=str) | |
| with open('docs/data/metrics.json', 'w') as f: | |
| json.dump(metrics, f, indent=2, default=str) | |
| print(f"Processed {len(submissions)} submissions for September 2025") | |
| print(f"Generated metrics: {metrics['total_submissions']} total submissions") | |
| # Future hackathons can be added here with similar logic | |
| # For example: | |
| # future_submissions = collect_future_submissions() | |
| # os.makedirs('docs/data/future-hackathon', exist_ok=True) | |
| # with open('docs/data/future-hackathon/submissions.json', 'w') as f: | |
| # json.dump(future_submissions, f, indent=2, default=str) | |
| EOF | |
| - name: Setup GitHub Pages | |
| if: github.event_name != 'pull_request' | |
| uses: actions/configure-pages@v4 | |
| - name: Upload artifacts | |
| if: github.event_name != 'pull_request' | |
| uses: actions/upload-pages-artifact@v3 | |
| with: | |
| path: 'docs' | |
| - name: Deploy to GitHub Pages | |
| if: github.event_name != 'pull_request' | |
| id: deployment | |
| uses: actions/deploy-pages@v4 |