Chan/research/step25_reentry.py

"""Step 25：同一中枢的二次、三次三买值不值得做。

此前每个中枢只取第一个入场点，首次三买被止损后再次突破回抽的机会被丢弃。
这既可能是漏掉的利润，也可能是避开了在失败中枢上反复挨打。本步实测。
"""
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", 300)

SL, TP, MAXB = 1.5, 3.0, 48
FEE, SLIP = 0.0004, 0.0001
MAX_OCC = 3


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, h1, h2 = task
    try:
        df_l = fetch_ohlcv(f"{sym}/USDT:USDT", 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)
        sig = find_fast_bsp3(cdf, zones, max_per_zone=MAX_OCC)
        if sig.empty or len(sig) < 10:
            return None
        for tf, pref in ((h1, "h1"), (h2, "h2")):
            df_h = fetch_ohlcv(f"{sym}/USDT:USDT", tf, 10**9)
            if df_h is None or len(df_h) < 300:
                continue
            chan_h = TF_DF(df_h, 1, tf)
            s = signals_to_frame(extract_fx_signals(chan_h, chan_h.dataframe))
            sig = attach_htf_context(sig, cdf, htf_fx_timeline(s, chan_h.dataframe), pref)

        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:
            return None
        m = sig.drop_duplicates("entry_idx").set_index("entry_idx")
        tr["symbol"], tr["ltf"] = sym, ltf
        tr["date"] = cdf["date"].to_numpy()[tr["entry_idx"].to_numpy()]
        for c in ("h1_agree", "h2_agree", "occ", "depth"):
            tr[c] = tr["entry_idx"].map(m[c]) if c in m.columns else np.nan
        return {"task": f"{sym} {ltf}", "trades": tr}
    except Exception as e:
        return {"task": f"{sym} {ltf}", "error": repr(e)[:200]}


def desc(r: np.ndarray, label: str) -> dict:
    if len(r) < 15:
        return {}
    w, o = r[r > 0], r[r <= 0]
    sd = r.std(ddof=1)
    return {
        "分组": label, "笔数": len(r),
        "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 curve(g: pd.DataFrame, label: str) -> dict:
    g = g.sort_values("date")
    r = g["ret_net"].to_numpy()
    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
    return {
        "方案": label, "笔数": len(r), "年笔数": f"{len(r) / yrs:.0f}",
        "年化": f"{(eq[-1] ** (1 / yrs) - 1) * 100:+.1f}%",
        "回撤": f"{(1 - eq / np.maximum.accumulate(eq)).max() * 100:.1f}%",
        "Sharpe": f"{pnl.mean() / pnl.std(ddof=1) * np.sqrt(len(pnl) / yrs):.2f}",
        "中位": f"{np.median(r) * 100:+.3f}%",
    }


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--pairs", default="5m:15m:1h,15m:1h:4h,30m:2h:4h")
    ap.add_argument("--symbols", default="BTC,ETH,SOL")
    ap.add_argument("--workers", type=int, default=6)
    ap.add_argument("--reuse", action="store_true")
    args = ap.parse_args()

    cache = HERE / "out" / "step25_reentry.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, *tuple(p.split(":")))
                 for p in args.pairs.split(",") if p
                 for s in args.symbols.split(",")]
        print(f"[二次入场] {len(tasks)} 个任务，每中枢最多 {MAX_OCC} 次\n", flush=True)
        res = []
        with ProcessPoolExecutor(max_workers=args.workers) 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']} — {len(r['trades'])} 笔", 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["ret_net"] = allt["gross"] - FEE - SLIP
    a = allt[allt["h1_agree"] == 1].copy()

    print("=" * 110)
    print("########## 1. 放开后每个中枢实际入场几次 ##########")
    rows = []
    for tf, g in a.groupby("ltf"):
        c = g["occ"].value_counts().sort_index()
        rows.append({
            "级别": tf, "总信号": len(g),
            "第1次": int(c.get(1, 0)), "第2次": int(c.get(2, 0)), "第3次": int(c.get(3, 0)),
            "新增占比": f"{(len(g) - c.get(1, 0)) / len(g) * 100:.0f}%",
        })
    print(pd.DataFrame(rows).to_string(index=False))

    print("\n########## 2. 第 N 次入场的质量（核心）##########")
    for tf, g in a.groupby("ltf"):
        rows = [desc(g[g.occ == k]["ret_net"].to_numpy(), f"{tf} 第{k}次")
                for k in (1, 2, 3)]
        rows = [r for r in rows if r]
        if rows:
            print(pd.DataFrame(rows).to_string(index=False))
    print("  第2/3次若明显差于第1次，说明失败中枢会继续失败，应维持只做首次。")

    print("\n########## 3. 组合层面：只做首次 vs 放开二次三次 ##########")
    def pick(g, maxocc):
        parts = []
        for tf in ("5m", "15m", "30m"):
            x = g[(g.ltf == tf) & (g.occ <= maxocc)]
            if x.empty:
                continue
            if tf == "5m":
                q = x["risk_pct"].quantile(0.67)
                x = x[(x["h2_agree"] == 1) & (x["risk_pct"] > q)]
            parts.append(x)
        return pd.concat(parts) if parts else pd.DataFrame()

    rows = [curve(pick(a, k), f"最多{k}次入场") for k in (1, 2, 3)]
    print(pd.DataFrame([r for r in rows if r]).to_string(index=False))

    print("\n########## 4. 仅 30m：第2次是否值得单独做 ##########")
    g = a[a.ltf == "30m"]
    rows = [desc(g[g.occ == 1]["ret_net"].to_numpy(), "30m 首次"),
            desc(g[g.occ >= 2]["ret_net"].to_numpy(), "30m 二次及以后")]
    print(pd.DataFrame([r for r in rows if r]).to_string(index=False))


if __name__ == "__main__":
    main()