from data_comparator import KSTCoordiComparator

def test_grouping():
    comparator = KSTCoordiComparator('data/sample-data.xlsx')
    if comparator.load_data():
        summary = comparator.get_comparison_summary()
        
        print("=== GROUPED BY TITLE TEST ===")
        print(f"Total unique titles: {len(summary['grouped_by_title']['title_summaries'])}")
        print()
        
        # Show top 5 titles with worst match percentages
        sorted_titles = sorted(
            summary['grouped_by_title']['title_summaries'].items(),
            key=lambda x: x[1]['match_percentage']
        )
        
        print("Top 5 titles needing attention (worst match %):")
        for i, (title, data) in enumerate(sorted_titles[:5]):
            print(f"{i+1}. {title}")
            print(f"   Total Episodes: {data['total_episodes']}")
            print(f"   Matched: {data['matched_count']} ({data['match_percentage']}%)")
            print(f"   KST Only: {data['kst_only_count']}")
            print(f"   Coordi Only: {data['coordi_only_count']}")
            print()

if __name__ == "__main__":
    test_grouping()