"""Run an availability experiment on an authored synthetic user-return scenario."""
import argparse
import hashlib
import json
from pathlib import Path
from availability import assemble, feature_events

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


def record():
    raw = (ROOT / 'scenario.json').read_bytes()
    scenario = json.loads(raw)
    observations, events, labels = (scenario[k] for k in ('observations', 'events', 'labels'))
    current = assemble(observations, events, labels, scenario['assemble_at'])
    later = assemble(observations, events, labels, scenario['later_assemble_at'])
    diagnostics = [{'id': row['id'], 'as_known': feature_events(row, events),
                    'event_time_only': feature_events(row, events, require_arrival=False)}
                   for row in observations if row['id'] in {r['id'] for r in current['rows']}]
    before = {row['id']: row['feature_event_ids'] for row in current['rows']}
    after = {row['id']: row['feature_event_ids'] for row in later['rows']}
    return {'mode': 'synthetic data-availability inspection; no training or predictions',
            'input_sha256': hashlib.sha256(raw).hexdigest(), 'current': current, 'later': later,
            'diagnostics': diagnostics,
            'original_feature_ids_unchanged': all(ids == after[id] for id, ids in before.items())}


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--save', type=Path)
    parser.add_argument('--check', action='store_true')
    args = parser.parse_args()
    result = record()
    if args.check and result != json.loads((ROOT / 'result.json').read_text()):
        raise SystemExit('availability record differs from the bundled result')
    if args.save:
        args.save.write_text(json.dumps(result, indent=2) + '\n')
    print('Synthetic user-return cohort; features use arrival time, labels use readiness time')
    for name in ('current', 'later'):
        cohort = result[name]
        print(f"{cohort['as_of']}: eligible={len(cohort['rows'])}; "
              f"excluded={len(cohort['excluded'])}; reasons={json.dumps(cohort['exclusion_counts'], sort_keys=True)}")
    for row in result['diagnostics']:
        print(f"{row['id']}: known-before-prediction={len(row['as_known'])}; "
              f"retrospective-event-only={len(row['event_time_only'])}")
    print('Original feature IDs unchanged when more labels become ready:', result['original_feature_ids_unchanged'])
    print('Pending or missing labels are excluded, never converted to negative outcomes.')


if __name__ == '__main__':
    main()