Chan/research/step33_no_touch.py

"""Step 33：去掉「回抽必须触及中枢边界」这一条，在最优配置下完整验证。

step32 的消融实验里，不要求回抽触及边界的档位（C）信号多 43%、PF 持平、
中位数几乎翻倍。原因是它把「突破后一去不回头」的强势段也收了进来。
本步在三个最优级别对上、叠加大级别同向与中枢阶梯过滤后完整对比，
并检查稳健性（分年、分品种、尾部），确认不是样本波动。
"""
from __future__ import annotations

import argparse
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"}


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
    from lib.nested_level import build_htf_zones

    sym, ltf = task
    htf = BEST[ltf]
    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 = build_htf_zones(cdf, ltf, chan=chan_l).reset_index(drop=True)
        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, htf, 10**9)
        if df_h is None or len(df_h) < 300:
            return None
        chan_h = TF_DF(df_h, 1, htf)
        s = signals_to_frame(extract_fx_signals(chan_h, chan_h.dataframe))
        tl = htf_fx_timeline(s, chan_h.dataframe)

        out = []
        for name, req in (("要求回抽触边界(现用)", True), ("不要求回抽触边界", False)):
            sig = find_fast_bsp3(cdf, zones, require_touch=req)
            if sig.empty or len(sig) < 20:
                continue
            sig = sig.merge(z[["zone_i", "z_above", "z_below"]], on="zone_i", how="left")
            sig = attach_htf_context(sig, cdf, tl, "h1")
            sig = sig.drop_duplicates("entry_idx")
            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", "lag", "depth"):
                if c in m.columns:
                    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}", "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),
            "滞后": f"{g['lag'].mean():.1f}" if "lag" in g else "—",
            "胜率": f"{(r > 0).mean() * 100:.1f}%",
            "均收益": f"{r.mean() * 100:+.3f}%",
            "中位": f"{np.median(r) * 100:+.3f}%",
            "PF": f"{w.sum() / abs(o.sum()):.2f}" if len(o) else "inf",
            "偏度": f"{pd.Series(r).skew():.2f}",
            "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:
    ap = argparse.ArgumentParser()
    ap.add_argument("--reuse", action="store_true")
    args = ap.parse_args()
    cache = HERE / "out" / "step33_notouch.csv"

    if args.reuse and cache.exists():
        allt = pd.read_csv(cache, parse_dates=["date"])
        print(f"[复用] {len(allt)} 笔\n")
    else:
        tasks = [(s, l) for l in BEST for s in ("BTC", "ETH", "SOL")]
        print(f"[验证] {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.to_csv(cache, index=False)

    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"]]

    print("=" * 118)
    print("########## 1. 最终配置对比（同向+阶梯，全级别合并）##########")
    print(pd.DataFrame([r for r in [stat(g, m) for m, g in fin.groupby("mode")] if r]
                       ).to_string(index=False))

    print("\n########## 2. 分级别 ##########")
    for ltf, g in fin.groupby("ltf"):
        rows = [stat(x, f"{ltf} {m}") for m, x in g.groupby("mode")]
        print(pd.DataFrame([r for r in rows if r]).to_string(index=False))

    print("\n########## 3. 分年（看是否某一年独大）##########")
    for m, g in fin.groupby("mode"):
        g = g.copy()
        g["y"] = g["date"].dt.year
        rows = [stat(x, str(y), minn=20) for y, x in g.groupby("y")]
        rows = [r for r in rows if r]
        if rows:
            print(f"-- {m} --")
            print(pd.DataFrame(rows).to_string(index=False))

    print("\n########## 4. 分品种 ##########")
    for m, g in fin.groupby("mode"):
        rows = [stat(x, s, minn=20) for s, x in g.groupby("symbol")]
        rows = [r for r in rows if r]
        if rows:
            print(f"-- {m} --")
            print(pd.DataFrame(rows).to_string(index=False))

    print("\n########## 5. 资金曲线 ##########")
    for m, g in fin.groupby("mode"):
        g = g.sort_values("date")
        r = g["gross"].to_numpy() - FEE - SLIP
        lev = np.clip(0.01 / np.clip(g["risk_pct"].to_numpy(), 0.002, None), 0, 20)
        pnl = r * lev
        eq = np.cumprod(1 + pnl)
        yrs = (g["date"].max() - g["date"].min()).days / 365.25
        dd = (1 - eq / np.maximum.accumulate(eq)).max()
        print(f"  {m:>18}: n={len(r):>4} 年{len(r) / yrs:>3.0f}笔  "
              f"年化 {(eq[-1] ** (1 / yrs) - 1) * 100:+7.1f}%  回撤 {dd * 100:5.1f}%  "
              f"Sharpe {pnl.mean() / pnl.std(ddof=1) * np.sqrt(len(pnl) / yrs):5.2f}")


if __name__ == "__main__":
    main()