benchmark_data_updated #175
This file contains 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: Generate CSV Reports | |
| on: | |
| workflow_dispatch: | |
| repository_dispatch: | |
| types: [benchmark_data_updated] | |
| push: | |
| branches: | |
| - main | |
| jobs: | |
| generate-reports: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v2 | |
| - name: Set up Python | |
| uses: actions/setup-python@v2 | |
| with: | |
| python-version: '3.x' | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install pandas | |
| - name: Generate CSV reports | |
| run: | | |
| echo "import os | |
| import pandas as pd | |
| import re | |
| project_data = [] | |
| cloc_data = [] | |
| possible_technologies = ['CSV', 'Dockerfile', 'Gradle', 'Java', 'JSON', 'Maven', 'Properties', 'SQL', 'ECMAScript', 'XML', 'YAML', 'SUM'] | |
| for root, dirs, files in os.walk('.'): | |
| for file in files: | |
| if file == 'README.md' and 'model_re' in root: | |
| with open(os.path.join(root, file), 'r') as f: | |
| lines = f.readlines() | |
| project = root.split('/')[1] | |
| data = { | |
| '#Components': '', | |
| '#Source Files': '', | |
| 'Lines of Code': '', | |
| '#Technologies': '', | |
| 'Abstraction': '', | |
| 'Execution Time [s]': '' | |
| } | |
| technologies = {tech: {'files': '0', 'blank': '0', 'comment': '0', 'code': '0'} for tech in possible_technologies} | |
| for line in lines: | |
| if '|' in line and '---' not in line: | |
| parts = line.strip().split('|') | |
| if len(parts) == 4: | |
| key = parts[1].strip() | |
| value = parts[2].strip() | |
| if key == 'Execution Time [s]': | |
| # only mean time without standard deviation | |
| value = re.match(r'([\d.]+)', value).group(1) | |
| data[key] = value | |
| if len(parts) == 7: | |
| values = {} | |
| values['files'] = parts[2].replace('**', '').strip() | |
| values['blank'] = parts[3].replace('**', '').strip() | |
| values['comment'] = parts[4].replace('**', '').strip() | |
| values['code'] = parts[5].replace('**', '').strip() | |
| technology = parts[1].replace('**', '').replace(':', '').strip() | |
| if technology in technologies: | |
| technologies[technology] = values | |
| project_data.append({ | |
| 'project': project, | |
| 'components': data.get('#Components', ''), | |
| 'source_files': data.get('#Source Files', ''), | |
| 'lines_of_code': data.get('Lines of Code', ''), | |
| 'technologies': data.get('#Technologies', ''), | |
| 'abstraction': data.get('Abstraction', ''), | |
| 'execution_time': data.get('Execution Time [s]', '') | |
| }) | |
| project_cloc = {'project': project} | |
| for tech in possible_technologies: | |
| project_cloc.update({ | |
| f'{tech}_files': technologies[tech]['files'], | |
| f'{tech}_blank': technologies[tech]['blank'], | |
| f'{tech}_comment': technologies[tech]['comment'], | |
| f'{tech}_code': technologies[tech]['code'] | |
| }) | |
| cloc_data.append(project_cloc) | |
| df_project = pd.DataFrame(project_data) | |
| df_project = df_project[df_project['execution_time'] != ''].sort_values(by='project') # Filter and sort | |
| df_project.to_csv('project_data.csv', index=False) | |
| df_cloc = pd.DataFrame(cloc_data) | |
| df_cloc = df_cloc[df_cloc['project'].isin(df_project['project'])].sort_values(by='project') # Filter and sort | |
| df_cloc.to_csv('cloc_data.csv', index=False)" > generate_reports.py | |
| python generate_reports.py | |
| - name: Upload CSV reports | |
| uses: actions/upload-artifact@v3 | |
| with: | |
| name: reports | |
| path: | | |
| project_data.csv | |
| cloc_data.csv |