"""Compare fixed classifiers under a declared cost contract; no policy selection."""
import argparse
import hashlib
import json
from pathlib import Path
from baseline import (load_rows, split_rows, fit_scaler, train_logistic,
                      predict_logistic, majority_label, DATA_SHA256, SALT)
from costs import score

ROOT = Path(__file__).resolve().parent


def record():
    parts = split_rows(load_rows())
    scaler = fit_scaler(parts['training'])
    model = train_logistic(parts['training'], scaler)
    majority = majority_label(parts['training'])
    validation = parts['validation']
    cases = [{'id': hashlib.sha256(row['key'].encode()).hexdigest(), 'label': row['label']}
             for row in validation]
    fixed = {'majority': [majority] * len(cases),
             'logistic': [predict_logistic(model, scaler, row) for row in validation]}
    contract = json.loads((ROOT / 'costs.json').read_text())
    results = {}
    for name, labels in fixed.items():
        predictions = [{'id': case['id'], 'label': label} for case, label in zip(cases, labels)]
        results[name] = score(cases, predictions, contract['matrix'])
    return {'data_sha256': DATA_SHA256, 'split_salt': SALT, 'split': 'validation',
            'cases': len(cases), 'cost_contract': contract, 'results': results}


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--save', type=Path, help='Write a new local result JSON')
    parser.add_argument('--check', action='store_true', help='Compare with the bundled result')
    args = parser.parse_args()
    result = record()
    if args.check and result != json.loads((ROOT / 'result.json').read_text()):
        raise SystemExit('current result differs from the bundled record')
    if args.save:
        args.save.write_text(json.dumps(result, indent=2) + '\n')
    print(f"validation: {result['cases']} ID-aligned cases; fixed majority and logistic classifiers")
    for name, row in result['results'].items():
        print(f"{name}: accuracy={row['metrics']['accuracy']:.4f}; errors={len(row['errors'])}; "
              f"cost={row['total_cost']:g}; cost/case={row['cost_per_case']:.6f}")
    print('Cost unit:', result['cost_contract']['unit'])
    print('Costs are declared scenario assumptions. No monetary impact or threshold improvement was measured.')


if __name__ == '__main__':
    main()