Chan/research/step30_engine_vs_fast.py

"""Step 30：引擎原版三类买卖点 vs 自写的快速版，同条件对拍。

之前所有结论都建立在 research/lib/fast_bsp3.py 上，那是我另写的实现：
形态判定照搬引擎（回抽不跌回中枢上沿），但不等回拉笔 is_sure，
直接用K线收盘判定，因此滞后从 9~10 根压到 1~2 根。

早期测过引擎原版说它不赚钱，但那次用的是残缺数据、近距配对、且没有中枢阶梯过滤，
结论不能作数。本步在完全相同的条件下重测：
  同一套 pure 笔中枢、同一个大级别分型过滤、同一套阶梯方向过滤、
  同样的 1.5/3.0/48 出场与次根开盘成交。唯一的差别就是信号从哪来。
"""
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 chanlun.core.ChanEnum import Chan_BSP_DIR
    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

        # 两边共用同一套 pure 笔中枢
        zs_list = chan_l.cal_bi_zs_list_pure(chan_l.bi_list)
        if not zs_list:
            return None
        zg = [float(z.zg) for z in zs_list]
        zd = [float(z.zd) for z in zs_list]
        step_up = [False] + [zd[i] > zg[i - 1] for i in range(1, len(zs_list))]
        step_dn = [False] + [zg[i] < zd[i - 1] for i in range(1, len(zs_list))]
        ladder = {id(z): (step_up[i], step_dn[i]) for i, z in enumerate(zs_list)}

        zones = build_htf_zones(cdf, ltf, chan=chan_l).reset_index(drop=True)
        if zones.empty:
            return None

        # 大级别分型时间线
        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)

        idx_map = {k: i for i, k in
                   enumerate(cdf["date"].dt.strftime("%Y-%m-%d %H:%M:%S"))}
        out = []

        # ---- A 引擎原版 B3/S3 ----
        bsp_list = chan_l.find_all_bsp(chan_l.bi_list, zs_list) or []
        rows = []
        for b in bsp_list:
            t = str(b.type).replace("Chan_BSP_TYPE.", "")
            if t not in ("B3", "S3") or not b.is_sure or b.sure_time is None:
                continue
            ek, fk = str(b.sure_time), str(b.end_time)
            if ek not in idx_map:
                continue
            up, dn = ladder.get(id(getattr(b, "zs", None)), (False, False))
            d = 1 if b.dir == Chan_BSP_DIR.BUY else -1
            rows.append({"entry_idx": idx_map[ek], "direction": d,
                         "z_above": up, "z_below": dn,
                         "lag": idx_map[ek] - idx_map.get(fk, idx_map[ek])})
        eng = pd.DataFrame(rows).drop_duplicates("entry_idx")

        # ---- B 快速版 ----
        fast = find_fast_bsp3(cdf, zones)
        if not fast.empty:
            zmap = {i: id(z) for i, z in enumerate(zs_list)}
            fast["_zid"] = fast["zone_i"].map(zmap)
            fast["z_above"] = fast["_zid"].map(lambda k: ladder.get(k, (False, False))[0])
            fast["z_below"] = fast["_zid"].map(lambda k: ladder.get(k, (False, False))[1])
            fast = fast.drop_duplicates("entry_idx")

        for name, sig in (("A 引擎B3/S3", eng), ("B 快速三买", fast)):
            if sig is None or sig.empty or len(sig) < 15:
                continue
            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["src"], 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", "lag", "direction"):
                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) -> dict:
    r = g["gross"].to_numpy() - FEE - SLIP
    if len(r) < 15:
        return {}
    w, o = r[r > 0], r[r <= 0]
    sd = r.std(ddof=1)
    return {"信号源": label, "笔数": len(r),
            "滞后": f"{g['lag'].mean():.1f}" if "lag" in g and g["lag"].notna().any() 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}"}


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--symbols", default="BTC,ETH,SOL")
    ap.add_argument("--reuse", action="store_true")
    args = ap.parse_args()

    cache = HERE / "out" / "step30_engine_vs_fast.csv"
    if args.reuse and cache.exists():
        allt = pd.read_csv(cache, parse_dates=["date"])
        print(f"[复用] {len(allt)} 笔\n")
    else:
        syms = [s.strip() for s in args.symbols.split(",")]
        tasks = [(s, l) for l in BEST for s in syms]
        print(f"[对拍] {len(tasks)} 个任务\n", flush=True)
        res = []
        with ProcessPoolExecutor(max_workers=6) 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)

    print("=" * 118)
    print("########## 1. 原始信号（不加任何过滤）##########")
    print(pd.DataFrame([r for r in
                        [stat(g, s) for s, g in allt.groupby("src")] if r]).to_string(index=False))

    print("\n########## 2. 逐层加过滤，分级别 ##########")
    for ltf, g in allt.groupby("ltf"):
        rows = []
        for s, x in g.groupby("src"):
            rows.append(stat(x, f"{ltf} {s} 原始"))
            rows.append(stat(x[x.h1_agree == 1], f"{ltf} {s} +大级别同向"))
            rows.append(stat(x[(x.h1_agree == 1) & x.push], f"{ltf} {s} +同向+阶梯"))
        rows = [r for r in rows if r]
        if rows:
            print(pd.DataFrame(rows).to_string(index=False))

    print("\n########## 3. 最终配置对比（同向+阶梯，全级别合并）##########")
    rows = [stat(g[(g.h1_agree == 1) & g.push], s) for s, g in allt.groupby("src")]
    print(pd.DataFrame([r for r in rows if r]).to_string(index=False))

    print("\n########## 4. 资金曲线 ##########")
    for s, g in allt.groupby("src"):
        sub = g[(g.h1_agree == 1) & g.push].sort_values("date")
        if len(sub) < 30:
            continue
        r = sub["gross"].to_numpy() - FEE - SLIP
        lev = np.clip(0.01 / np.clip(sub["risk_pct"].to_numpy(), 0.002, None), 0, 20)
        pnl = r * lev
        eq = np.cumprod(1 + pnl)
        yrs = (sub["date"].max() - sub["date"].min()).days / 365.25
        dd = (1 - eq / np.maximum.accumulate(eq)).max()
        print(f"  {s:>12}: 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()