"""Step 36：Sharpe 8 的剩余嫌疑——中枢生效时刻的回退分支、多空对称性、时间样本外。 step35 已排除未来函数（后移入场平滑衰减）、滑点脆弱、持仓重叠虚高 t 值。 剩下三个必须查： 1 build_htf_zones 里 available_ts = sure_time or end_time。 一旦回退到 end_time 就是未来函数（笔端点早于笔确认）。统计回退比例， 并给出「只保留 sure_time 可用」的严格口径下的结果。 2 多空对称性。三个币六年整体上涨，若收益几乎全来自做多，那是 beta 不是 alpha。 3 时间样本外。tol、级别对、SL/TP 都是在全样本上挑的。 用 2019~2022 当样本内，2023~2026 当样本外，看衰减多少。 """ from __future__ import annotations import os import sys import warnings from concurrent.futures import ProcessPoolExecutor, as_completed from pathlib import Path import numpy as np import pandas as pd warnings.filterwarnings("ignore") for v in ("OMP_NUM_THREADS", "OPENBLAS_NUM_THREADS", "MKL_NUM_THREADS"): os.environ.setdefault(v, "1") HERE = Path(__file__).resolve().parent sys.path.insert(0, str(HERE)) sys.path.insert(0, str(HERE.parent)) pd.set_option("display.width", 320) SL, TP, MAXB = 1.5, 3.0, 48 FEE, SLIP = 0.0004, 0.0001 BEST = {"5m": "30m", "15m": "1h", "30m": "2h"} SPLIT = pd.Timestamp("2023-01-01", tz="Asia/Shanghai") def strict_zones(chan, cdf: pd.DataFrame) -> tuple[pd.DataFrame, dict]: """重算中枢表，区分 available_ts 来自 sure_time 还是回退到 end_time。""" zs_list = chan.cal_bi_zs_list_pure(chan.bi_list) ts_of = dict(zip(cdf["date"].dt.strftime("%Y-%m-%d %H:%M:%S"), cdf["timestamp"])) rows = [] cnt = {"总数": 0, "用sure_time": 0, "回退end_time": 0, "两者皆无": 0} for zs in zs_list: bis = getattr(zs, "bi_list", []) if not bis: continue cnt["总数"] += 1 last = bis[-1] s_ts = ts_of.get(str(getattr(last, "sure_time", "") or "")) e_ts = ts_of.get(str(getattr(last, "end_time", "") or "")) if s_ts is not None: cnt["用sure_time"] += 1 src = "sure" avail = s_ts elif e_ts is not None: cnt["回退end_time"] += 1 src = "fallback" avail = e_ts else: cnt["两者皆无"] += 1 continue rows.append({"zg": float(zs.zg), "zd": float(zs.zd), "available_ts": int(avail), "src": src}) out = pd.DataFrame(rows) if not out.empty: out = out.sort_values("available_ts").reset_index(drop=True) return out, cnt def run_one(task: tuple) -> dict | None: import warnings as _w _w.filterwarnings("ignore") sys.path.insert(0, str(HERE)) sys.path.insert(0, str(HERE.parent)) from chanlun import TF_DF from lib.breakout import run_trades from lib.data import fetch_ohlcv from lib.fast_bsp3 import find_fast_bsp3 from lib.fx_signal import extract_fx_signals, signals_to_frame from lib.nested_bsp import attach_htf_context, htf_fx_timeline sym, ltf = task pair = f"{sym}/USDT:USDT" try: df_l = fetch_ohlcv(pair, ltf, 10**9) if df_l is None or len(df_l) < 3000: return None chan_l = TF_DF(df_l, 1, ltf) cdf = chan_l.dataframe zones, cnt = strict_zones(chan_l, cdf) if zones.empty: return None z = zones.copy() pg, pdn = z["zg"].shift(), z["zd"].shift() z["z_above"], z["z_below"] = z["zd"] > pg, z["zg"] < pdn z["zone_i"] = np.arange(len(z)) df_h = fetch_ohlcv(pair, BEST[ltf], 10**9) if df_h is None or len(df_h) < 300: return None chan_h = TF_DF(df_h, 1, BEST[ltf]) s = signals_to_frame(extract_fx_signals(chan_h, chan_h.dataframe)) tl = htf_fx_timeline(s, chan_h.dataframe) out = [] for name, zsub in (("全部中枢", z), ("仅sure_time中枢", z[z["src"] == "sure"])): if zsub.empty: continue zz = zsub.reset_index(drop=True) zz["zone_i"] = np.arange(len(zz)) sig = find_fast_bsp3(cdf, zz, tol=-1.0) if sig.empty or len(sig) < 20: continue sig = sig.merge(zz[["zone_i", "z_above", "z_below"]], on="zone_i", how="left") sig = attach_htf_context(sig, cdf, tl, "h1") entries = list(zip(sig["entry_idx"].astype(int), sig["direction"].astype(int))) tr = run_trades(cdf, entries, SL, TP, MAXB, fee=0.0, entry_delay=1) if tr.empty: continue m = sig.set_index("entry_idx") tr["mode"], tr["symbol"], tr["ltf"] = name, sym, ltf tr["date"] = cdf["date"].to_numpy()[tr["entry_idx"].to_numpy()] for c in ("h1_agree", "z_above", "z_below", "direction"): tr[c if c != "direction" else "dir_sig"] = tr["entry_idx"].map(m[c]) out.append(tr) if not out: return None return {"task": f"{sym} {ltf}", "cnt": {"task": f"{sym} {ltf}", **cnt}, "trades": pd.concat(out, ignore_index=True)} except Exception as e: return {"task": f"{sym} {ltf}", "error": repr(e)[:250]} def stat(g: pd.DataFrame, label: str, minn: int = 25) -> dict: r = g["gross"].to_numpy() - FEE - SLIP if len(r) < minn: return {} w, o = r[r > 0], r[r <= 0] sd = r.std(ddof=1) t10 = r[r <= np.quantile(r, 0.90)] return {"分组": label, "笔数": len(r), "胜率": f"{(r > 0).mean() * 100:.1f}%", "中位": f"{np.median(r) * 100:+.3f}%", "PF": f"{w.sum() / abs(o.sum()):.2f}" if len(o) else "inf", "t值": f"{r.mean() / (sd / np.sqrt(len(r))):+.2f}", "剔10%PF": f"{t10[t10 > 0].sum() / abs(t10[t10 <= 0].sum()):.2f}"} def main() -> None: tasks = [(s, l) for l in BEST for s in ("BTC", "ETH", "SOL")] print(f"[偏差审计] {len(tasks)} 个任务\n", flush=True) res = [] with ProcessPoolExecutor(max_workers=5) as ex: futs = {ex.submit(run_one, t): t for t in tasks} for i, f in enumerate(as_completed(futs), 1): r = f.result() if r is None or "error" in (r or {}): print(f" [{i}] 跳过 {(r or {}).get('error', '')}", flush=True) continue res.append(r) print(f" [{i}/{len(tasks)}] {r['task']}", flush=True) if not res: return allt = pd.concat([r["trades"] for r in res], ignore_index=True) allt["date"] = pd.to_datetime(allt["date"]) allt["push"] = np.where(allt["dir_sig"] == 1, allt["z_above"], allt["z_below"]) allt["push"] = allt["push"].fillna(False).astype(bool) fin = allt[(allt["h1_agree"] == 1) & allt["push"]] allt.to_csv(HERE / "out" / "step36_bias.csv", index=False) print("=" * 110) print("########## 1. 中枢生效时刻：有多少走了 end_time 回退分支 ##########") c = pd.DataFrame([r["cnt"] for r in res]) c["级别"] = c["task"].str.split().str[1] g = c.groupby("级别")[["总数", "用sure_time", "回退end_time", "两者皆无"]].sum() g["回退占比"] = (g["回退end_time"] / g["总数"] * 100).round(1).astype(str) + "%" print(g.to_string()) print("\n########## 2. 剔掉回退中枢后结果是否站得住 ##########") print(pd.DataFrame([r for r in [stat(g_, m) for m, g_ in fin.groupby("mode")] if r] ).to_string(index=False)) strict = fin[fin["mode"] == "仅sure_time中枢"] print("\n########## 3. 多空对称性（严格口径）##########") rows = [stat(strict[strict["dir_sig"] == d], n) for d, n in ((1, "做多(三买)"), (-1, "做空(三卖)"))] print(pd.DataFrame([r for r in rows if r]).to_string(index=False)) print(" 若做空也显著为正，说明不是单纯吃上涨 beta。") print("\n########## 4. 时间样本外：2019~2022 挑参数，2023~2026 验证 ##########") rows = [stat(strict[strict["date"] < SPLIT], "样本内 2019~2022"), stat(strict[strict["date"] >= SPLIT], "样本外 2023~2026")] print(pd.DataFrame([r for r in rows if r]).to_string(index=False)) print("\n########## 5. 样本外分级别与分品种 ##########") oos = strict[strict["date"] >= SPLIT] rows = [stat(x, f"OOS {k}", minn=20) for k, x in oos.groupby("ltf")] rows += [stat(x, f"OOS {k}", minn=20) for k, x in oos.groupby("symbol")] print(pd.DataFrame([r for r in rows if r]).to_string(index=False)) print("\n########## 6. 样本外资金曲线（固定名义1倍，不复利）##########") for label, g_ in (("样本内", strict[strict["date"] < SPLIT]), ("样本外", oos)): g_ = g_.sort_values("date") r = g_["gross"].to_numpy() - FEE - SLIP yrs = (g_["date"].max() - g_["date"].min()).days / 365.25 eq = 1 + np.cumsum(r) dd = (np.maximum.accumulate(eq) - eq).max() print(f" {label}: n={len(r):>4} 年{len(r) / yrs:>3.0f}笔 " f"年化 {(eq[-1] - 1) / yrs * 100:+6.1f}% 回撤 {dd * 100:5.1f}% " f"Sharpe {r.mean() / r.std(ddof=1) * np.sqrt(len(r) / yrs):5.2f}") if __name__ == "__main__": main()