Gahow Wang
0e378efa67
Event-driven long-only simulator with next-open fills, CN tradability (halts, limit-up/down, stamp duty), PIT S&P 500 / CSI 300 membership, rebalance-phase averaging, factor IC scans, maximin stepwise composite search across 5-year blocks, walk-forward LightGBM/ridge combiners, overlays, and deflated Sharpe. Fetchers pull 20y US OHLCV from Yahoo and CSI 300/500 ever-members (membership snapshot from baostock, bars from Yahoo). Research data lives in data/research/ (ignored). Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
79 lines
3.6 KiB
Python
79 lines
3.6 KiB
Python
"""
|
|
Export phase-averaged equity curves of the final candidates and baselines for
|
|
the report (weekly samples), plus the US/CN correlation of the new strategies.
|
|
|
|
PYTHONPATH=. uv run python -m research.lab.export_curves
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
import warnings
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
from research.lab.evaluate import phase_runs, score_for
|
|
from research.lab.factor_scan import RESULTS, load
|
|
from research.lab.report import stats
|
|
|
|
warnings.filterwarnings("ignore")
|
|
|
|
SETS = {
|
|
"us": ("2006-09-27", "2026-09-24", {
|
|
"新: overnight+recovery": ("overnight_mom+rec_126", dict(top_n=10, every=10, buffer=2.0)),
|
|
"现: rec_mfilt+deep_upvol 月频": ("baseline:rec_mfilt+deep_upvol", dict(top_n=10, every=21)),
|
|
"现: mom7m+rec126 月频": ("baseline:mom7m+rec126", dict(top_n=10, every=21)),
|
|
"等权 S&P 500 (PIT)": ("ew", dict(top_n=10000, every=5)),
|
|
}),
|
|
"cn_hs300": ("2010-01-04", "2026-09-24", {
|
|
"新: 低风险动量4因子": ("amp_cut_mom+low_beta+pv_corr+sharpe_mom", dict(top_n=15, every=10, buffer=2.0)),
|
|
"新: low_beta+sharpe_mom": ("low_beta+sharpe_mom", dict(top_n=20, every=10, buffer=1.0)),
|
|
"现: down_resil+qual_mom 双周": ("baseline:down_resil+qual_mom", dict(top_n=10, every=10)),
|
|
"现: up_cap+quality_mom 周频": ("baseline:up_cap+quality_mom", dict(top_n=10, every=5)),
|
|
"等权 CSI 300 (PIT)": ("ew", dict(top_n=10000, every=5)),
|
|
}),
|
|
}
|
|
|
|
|
|
def main() -> None:
|
|
out, daily = {}, {}
|
|
for market, (a, b, cands) in SETS.items():
|
|
p, _ = load(market)
|
|
curves = {}
|
|
for name, (combo, kw) in cands.items():
|
|
s = score_for(p, combo, market)
|
|
runs = phase_runs(p, s, a, b, **kw)
|
|
rets = pd.concat([r.returns.loc[a:b] for r in runs], axis=1).mean(axis=1)
|
|
daily[(market, name)] = rets
|
|
eq = (1 + rets).cumprod()
|
|
wk = eq.resample("W-FRI").last().dropna()
|
|
dd = eq / eq.cummax() - 1
|
|
curves[name] = {"dates": [d.strftime("%Y-%m-%d") for d in wk.index],
|
|
"equity": [round(float(v), 4) for v in wk.values],
|
|
"drawdown": [round(float(v), 4) for v in dd.resample("W-FRI").min().dropna().values],
|
|
"stats": {k: float(v) for k, v in stats(eq).items()}}
|
|
print(market, name, {k: round(v, 3) for k, v in curves[name]["stats"].items()}, flush=True)
|
|
out[market] = curves
|
|
us = daily[("us", "新: overnight+recovery")]
|
|
cn = daily[("cn_hs300", "新: 低风险动量4因子")]
|
|
# compound each market on its own calendar before joining: the exchanges
|
|
# have different holidays, and an inner join on days would drop returns
|
|
m = pd.concat([us, cn], axis=1, keys=["us", "cn"]).dropna().loc["2016-09-27":]
|
|
mon = pd.concat({k: (1 + v.loc["2016-09-27":]).resample("ME").prod() - 1
|
|
for k, v in (("us", us), ("cn", cn))}, axis=1).dropna()
|
|
cross = {"daily_corr": float(m.corr().iloc[0, 1]), "monthly_corr": float(mon.corr().iloc[0, 1])}
|
|
for col in ["us", "cn", "5050"]:
|
|
r = mon.mean(axis=1) if col == "5050" else mon[col]
|
|
eq = (1 + r).cumprod()
|
|
cross[col] = {"cagr": float(eq.iloc[-1] ** (12 / len(r)) - 1),
|
|
"sharpe_monthly": float(r.mean() / r.std() * np.sqrt(12)),
|
|
"mdd_monthly": float((eq / eq.cummax() - 1).min())}
|
|
out["cross"] = cross
|
|
print("cross", out["cross"])
|
|
with open(os.path.join(RESULTS, "curves.json"), "w") as fh:
|
|
json.dump(out, fh, ensure_ascii=False, default=float)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|