calculate_csv_coverage_stats.py

#!/usr/bin/env python3
"""Calculate coverage statistics from GraphQL schema coverage CSV files."""

from pathlib import Path
from typing import Tuple, List
import pandas as pd
import sys


def process_csv_file(csv_path: Path) -> Tuple[int, int, float]:
  """
  Process a single CSV file and calculate coverage statistics.
  
  Args:
    csv_path: Path to the CSV file
    
  Returns:
    Tuple of (numerator, denominator, fraction)
    numerator: Number of rows with Covered=True
    denominator: Total number of data rows (excluding header)
    fraction: numerator / denominator
    
  Raises:
    ValueError: If the CSV file doesn't have the expected structure
  """
  df = pd.read_csv(csv_path)
  
  # Check if 'Covered' column exists
  if 'Covered' not in df.columns:
    raise ValueError(f"CSV file {csv_path} does not have a 'Covered' column")
  
  # Count rows where Covered is True
  numerator = int((df['Covered'] == True).sum())
  
  # Total number of data rows (excluding header)
  denominator = len(df)
  
  # Calculate fraction
  if denominator == 0:
    fraction = 0.0
  else:
    fraction = numerator / denominator
    
  return numerator, denominator, fraction


def calculate_statistics(csv_dir: Path) -> None:
  """
  Calculate and print coverage statistics for all CSV files in a directory.
  
  Args:
    csv_dir: Directory containing CSV files
  """
  # Find all CSV files, excluding lock files
  csv_files = [
    f for f in csv_dir.glob('*.csv')
    if not f.name.startswith('.~lock')
  ]
  
  if not csv_files:
    print(f"No CSV files found in {csv_dir}")
    return
    
  print(f"Processing {len(csv_files)} CSV file(s)...\n")
  
  fractions: List[float] = []
  total_numerator = 0
  total_denominator = 0
  
  for csv_file in sorted(csv_files):
    try:
      numerator, denominator, fraction = process_csv_file(csv_file)
      
      if denominator == 0:
        print(f"{csv_file.name}:")
        print(f"  WARNING: No data rows found, skipping...\n")
        continue
      
      print(f"{csv_file.name}:")
      print(f"  Covered entries: {numerator}")
      print(f"  Total entries: {denominator}")
      print(f"  Fraction: {fraction:.4f} ({numerator}/{denominator})\n")
      
      fractions.append(fraction)
      total_numerator += numerator
      total_denominator += denominator
      
    except Exception as e:
      print(f"{csv_file.name}:")
      print(f"  ERROR: {e}\n")
      continue
  
  if not fractions:
    print("No valid CSV files processed.")
    return
  
  # Calculate statistics
  avg_fraction = sum(fractions) / len(fractions)
  
  if total_denominator == 0:
    overall_fraction = 0.0
  else:
    overall_fraction = total_numerator / total_denominator
  
  print("=" * 50)
  print("STATISTICS:")
  print("=" * 50)
  print(f"1. Average of all fractions: {avg_fraction:.4f}")
  print(f"2. Overall fraction (sum of numerators / sum of denominators):")
  print(f"   {overall_fraction:.4f} ({total_numerator}/{total_denominator})")
  print("=" * 50)


def main() -> None:
  """Main entry point for the script."""
  # Get directory path from command line or use script's directory
  if len(sys.argv) > 1:
    csv_dir = Path(sys.argv[1])
    if not csv_dir.exists():
      print(f"Error: Directory '{csv_dir}' does not exist.")
      sys.exit(1)
    if not csv_dir.is_dir():
      print(f"Error: '{csv_dir}' is not a directory.")
      sys.exit(1)
  else:
    # Use script's directory
    csv_dir = Path(__file__).parent / 'results' / 'csv'
    if not csv_dir.exists():
      print(f"Error: Default directory '{csv_dir}' does not exist.")
      sys.exit(1)
  
  calculate_statistics(csv_dir)


if __name__ == "__main__":
  main()