quant-trading/research/lab/registered.py

"""Fixed-budget validation of registered strategies on the shared execution engine."""
from __future__ import annotations

import copy
import hashlib
import json
from datetime import datetime, timezone
from pathlib import Path

import pandas as pd

import metrics
import data_manager
from backtest_runner import (ENGINE_VERSION, load_etf_panels, load_stock_panels, prepare_strategy,
                             replay_prepared)
from trader import ETF_STRATEGY_UNIVERSES, make_strategy
from strategies.robust_momentum import RobustMomentumStrategy
from research.lab.trials import append_trials


def _stats(equity):
    return {k: v for k, v in metrics.raw_summary(equity).items()
            if k in ('annualizedReturn', 'maxDrawdown', 'sharpeRatio', 'annualizedVolatility')}


def evaluate_registered(args):
    market = 'cn' if args.market.startswith('cn') else 'us'
    destination = Path(args.output or f'data/research/results/registered_{market}')
    destination.mkdir(parents=True, exist_ok=True)
    etf_names = [n for n in args.registered if n in ETF_STRATEGY_UNIVERSES]
    stock_names = [n for n in args.registered if n not in ETF_STRATEGY_UNIVERSES]
    stock = load_stock_panels(market, stock_names, None, refresh=False) if stock_names else None
    etfs = load_etf_panels(market, etf_names, refresh=False) if etf_names else None

    def source(name):
        """(panels, universe, membership) the strategy is replayed on, as in run_market."""
        if name in ETF_STRATEGY_UNIVERSES:
            return etfs, ETF_STRATEGY_UNIVERSES[name], None
        return stock['panels'], stock['stocks'], stock['member']

    ends = [p['close'].index[-1] for p in ([stock['panels']] if stock else []) + ([etfs] if etfs else [])]
    end = args.end or str(min(ends).date())
    start = args.start or '2018-01-01'
    profiles = ['baseline', 'resize20', 'buffer3'] + (['cash_shy'] if market == 'us' else [])
    protocol = {
        'created_at': datetime.now(timezone.utc).isoformat(), 'engine': ENGINE_VERSION,
        'market': market, 'strategies': args.registered, 'start': start, 'end': end,
        'profiles': profiles, 'one_way_costs': [.001, .0025], 'capital': 10000 if market == 'us' else 70000,
        'selection_rule': 'CAGR improves at both costs; drawdown deterioration <= 2pp; improves in >=2/3 time blocks',
        'role': 'historical development comparison; not independent OOS; do not auto-promote',
        'source_hashes': {str(p): hashlib.sha256(p.read_bytes()).hexdigest()
                          for p in [Path('execution.py'), Path('signals.py'), Path('backtest_runner.py')]
                          + sorted(Path('strategies').glob('*.py'))},
        'data_hashes': {str(p): hashlib.sha256(p.read_bytes()).hexdigest()
                        for p in ([Path('data') / f'{market}.csv', Path('data') / f'{market}_open.csv',
                                   Path('data/sp500_history.json' if market == 'us' else 'data/csi300_history.json')]
                                  if stock_names else [])
                        + ([Path('data/etfs.csv'), Path('data/etfs_open.csv')] if etf_names else [])},
    }
    protocol_path = destination / 'protocol.json'
    if protocol_path.exists():
        raise FileExistsError(f'Choose a new --output to preserve the completed study: {destination}')
    protocol_path.write_text(json.dumps(protocol, indent=2))
    rows, verdicts = [], []
    fees = {'tx_cost': .001, 'fixed_fee': 2 if market == 'us' else 5,
            'fee_base': 1.88 if market == 'us' else 0, 'fee_per_share': .009 if market == 'us' else 0}
    for name in args.registered:
        base_strategy = make_strategy(name, market)
        panels, universe, member = source(name)
        base_plan = prepare_strategy(name, market, panels, universe, member=member,
                                     start=start, end=end, strategy=base_strategy)
        if base_plan['warmup_rows'] < 315:
            raise ValueError('Registered comparison requires >=315 pre-window sessions; move --start or add history')
        dates = base_plan['prices'].index
        cuts = [0, len(dates)//3, 2*len(dates)//3, len(dates)]
        for profile in profiles:
            plan, band = base_plan, .1
            if profile == 'resize20':
                band = .2
            elif profile == 'buffer3':
                if not isinstance(base_strategy, RobustMomentumStrategy):
                    continue
                changed = copy.deepcopy(base_strategy); changed.buffer = 3.0
                plan = prepare_strategy(name, market, panels, universe, member=member,
                                         start=start, end=end, strategy=changed)
            elif profile == 'cash_shy':
                if 'SHY' not in panels['close']:
                    raise ValueError('SHY bars are required for a traded cash sleeve')
                plan = dict(base_plan)
                plan['prices'] = base_plan['prices'].copy()
                plan['prices']['SHY'] = panels['close']['SHY'].reindex(dates)
                if base_plan.get('volume') is not None:
                    plan['volume'] = base_plan['volume'].copy()
                    plan['volume']['SHY'] = panels['volume']['SHY'].reindex(dates)
                target = base_plan['targets'].reindex(columns=plan['prices'].columns, fill_value=0).copy()
                target['SHY'] += (1-target.sum(axis=1)).clip(lower=0)
                plan['targets'] = target
            for cost in protocol['one_way_costs']:
                run = replay_prepared(plan, protocol['capital'], **{**fees, 'tx_cost': cost}, resize_band=band)
                row = {'strategy': name, 'profile': profile, 'cost': cost, **_stats(run['equity']),
                       'orders': len(run['trade_log']), 'fees': sum(t['commission'] for t in run['trade_log']),
                       'minimum_cash': float(run['cash'].min()), 'blocks': []}
                for a, b in zip(cuts[:-1], cuts[1:]):
                    row['blocks'].append(_stats(run['equity'].iloc[a:b+1]))
                rows.append(row)
                append_trials(destination/'trials.jsonl', [row], protocol)
                print(name, profile, cost, f"CAGR {row['annualizedReturn']:.2%}",
                      f"DD {row['maxDrawdown']:.2%}", flush=True)
        baseline = {r['cost']: r for r in rows if r['strategy'] == name and r['profile'] == 'baseline'}
        for profile in profiles[1:]:
            candidates = [r for r in rows if r['strategy'] == name and r['profile'] == profile]
            if not candidates:
                continue
            passed = all(r['annualizedReturn'] > baseline[r['cost']]['annualizedReturn']
                         and r['maxDrawdown'] >= baseline[r['cost']]['maxDrawdown']-.02
                         and sum(a['annualizedReturn'] > b['annualizedReturn']
                                 for a,b in zip(r['blocks'],baseline[r['cost']]['blocks'])) >= 2
                         for r in candidates)
            verdicts.append({'strategy': name, 'profile': profile,
                             'verdict': 'candidate_for_forward_only' if passed else 'retain_baseline'})
    summary = {'protocol': protocol, 'comparisons': rows, 'decisions': verdicts,
               'boundary': 'Missing historical constituents and adjusted-share execution remain limitations.'}
    (destination/'results.json').write_text(json.dumps(summary, indent=2, allow_nan=False))
    pd.DataFrame([{k:v for k,v in r.items() if k!='blocks'} for r in rows]).to_csv(destination/'results.csv',index=False)
    print('Saved',destination/'results.json',flush=True)
    return summary