Spaces:
Running
Running
| import argparse | |
| import sys | |
| import os | |
| from sqlalchemy import func, and_ | |
| # Add project root to Python path | |
| project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), '..')) | |
| if project_root not in sys.path: | |
| sys.path.insert(0, project_root) | |
| from utils.database import get_db | |
| from data.models import Annotator, Annotation, AnnotationInterval, TTSData | |
| from utils.logger import Logger | |
| log = Logger() | |
| def generate_annotator_progress_report(): | |
| """ | |
| Generates and prints a progress report for each annotator. | |
| Progress is defined as the percentage of assigned TTSData items | |
| that have a non-empty annotation. | |
| """ | |
| with get_db() as db: | |
| try: | |
| annotators = db.query(Annotator).filter(Annotator.is_active == True).all() | |
| if not annotators: | |
| log.info("No active annotators found.") | |
| return | |
| log.info("--- Annotator Progress Report ---") | |
| for annotator in annotators: | |
| # Calculate total assigned items for the annotator | |
| total_assigned_query = db.query(func.sum(AnnotationInterval.end_index - AnnotationInterval.start_index + 1))\ | |
| .filter(AnnotationInterval.annotator_id == annotator.id) | |
| total_assigned_result = total_assigned_query.scalar() | |
| total_assigned = total_assigned_result if total_assigned_result is not None else 0 | |
| # Calculate completed items by this annotator within their assigned intervals | |
| # An item is considered completed if annotated_sentence is not None and not an empty string. | |
| completed_count_query = db.query(func.count(Annotation.id))\ | |
| .join(TTSData, Annotation.tts_data_id == TTSData.id)\ | |
| .join(AnnotationInterval, | |
| and_(AnnotationInterval.annotator_id == annotator.id, | |
| TTSData.id >= AnnotationInterval.start_index, | |
| TTSData.id <= AnnotationInterval.end_index))\ | |
| .filter(Annotation.annotator_id == annotator.id, | |
| Annotation.annotated_sentence != None, | |
| Annotation.annotated_sentence != "") | |
| completed_count_result = completed_count_query.scalar() | |
| completed_count = completed_count_result if completed_count_result is not None else 0 | |
| percentage_completed = 0 | |
| if total_assigned > 0: | |
| percentage_completed = (completed_count / total_assigned) * 100 | |
| log.info(f"Annotator: {annotator.name} (ID: {annotator.id})") | |
| log.info(f" Total Assigned Items: {total_assigned}") | |
| log.info(f" Completed Items: {completed_count}") | |
| log.info(f" Progress: {percentage_completed:.2f}%") | |
| log.info("-" * 30) | |
| except Exception as e: | |
| # For errors, we might still want the full log details | |
| log.error(f"Failed to generate annotator progress report: {e}") | |
| if __name__ == "__main__": | |
| # No arguments needed for this script, it reports on all active annotators | |
| # parser = argparse.ArgumentParser(description="Generate a progress report for all active annotators.") | |
| # args = parser.parse_args() # Not needed for now | |
| generate_annotator_progress_report() | |