Whistleblowing Framework (QSR Leader)

import pandas as pd
import numpy as np

def run_benford_audit(df_ap_transactions, amount_col='amount'):
    """
    Analyzes transaction distribution against Benford's Law.
    Flags vendors/employees exhibiting high chi-square deviation.
    """
    # 1. Extract the first digit (ignoring zeros, negatives, and decimals)
    df = df_ap_transactions[df_ap_transactions[amount_col] >= 1.0].copy()
    df['first_digit'] = df[amount_col].apply(lambda x: int(str(abs(x)).replace('.', '').lstrip('0')[0]))
    
    # 2. Calculate actual frequencies
    digit_counts = df['first_digit'].value_counts().reindex(range(1, 10), fill_value=0)
    total_count = len(df)
    
    # 3. Calculate Benford expected frequencies
    benford_probs = {d: np.log10(1 + 1/d) for d in range(1, 10)}
    expected_counts = {d: benford_probs[d] * total_count for d in range(1, 10)}
    
    # 4. Perform Chi-Square Goodness-of-Fit test
    chi_square_stats = {}
    for d in range(1, 10):
        observed = digit_counts[d]
        expected = expected_counts[d]
        chi_sq_val = ((observed - expected) ** 2) / expected
        chi_square_stats[d] = {
            'observed': observed,
            'expected': round(expected, 2),
            'deviation': round(observed - expected, 2),
            'chi_sq': round(chi_sq_val, 4)
        }
        
    total_chi_sq = sum(c['chi_sq'] for c in chi_square_stats.values())
    critical_value_99 = 20.09  # df=8, p=0.01
    
    return {
        'total_chi_sq': round(total_chi_sq, 2),
        'audit_verdict': 'SIGNIFICANT ANOMALY DETECTED' if total_chi_sq > critical_value_99 else 'NORMAL DISTRIBUTION',
        'details': chi_square_stats
    }