import pandas as pd

# Baca semua CSV untuk cek header
files = {
    '2019': r'c:\Users\syifa\TA-PROJEK\Data_Tracerstudy\Data_2019_Tracer_study.csv',
    '2020': r'c:\Users\syifa\TA-PROJEK\Data_Tracerstudy\Data_2020_Tracer_study.csv',
    '2021': r'c:\Users\syifa\TA-PROJEK\Data_Tracerstudy\Data_2021_Tracer_study.csv',
    '2022': r'c:\Users\syifa\TA-PROJEK\Data_Tracerstudy\Data_2022_Tracer_study.csv',
}

for tahun, filepath in files.items():
    try:
        df = pd.read_csv(filepath, sep=';', encoding='utf-8-sig')
        cols = list(df.columns)

        print(f'=== TAHUN {tahun} ===')
        print(f'Total rows: {len(df)}')

        # Cek kolom F5b dan F5c
        has_f5b = 'F5b' in cols or 'f5b' in [c.lower() for c in cols]
        has_f5c = 'F5c' in cols or 'f5c' in [c.lower() for c in cols]

        print(f'Kolom F5b ada: {has_f5b}')
        print(f'Kolom F5c ada: {has_f5c}')

        # Sample data dari F5b dan F5c
        if has_f5b:
            f5b_col = 'F5b' if 'F5b' in cols else [c for c in cols if c.lower() == 'f5b'][0]
            sample = df[f5b_col].iloc[0] if len(df) > 0 else None
            print(f'Sample F5b: {sample}')

            # Count non-empty
            non_empty = df[f5b_col].notna().sum()
            print(f'F5b non-empty: {non_empty}/{len(df)}')

        if has_f5c:
            f5c_col = 'F5c' if 'F5c' in cols else [c for c in cols if c.lower() == 'f5c'][0]
            sample = df[f5c_col].iloc[0] if len(df) > 0 else None
            print(f'Sample F5c: {sample}')

            # Count non-empty
            non_empty = df[f5c_col].notna().sum()
            print(f'F5c non-empty: {non_empty}/{len(df)}')

        print()
    except Exception as e:
        print(f'TAHUN {tahun}: ERROR - {e}')
        print()