"""把 B4 按「中枢末笔是否已确认」拆开——之前的统计把两种混在一起了。

用户指出：B4 有两种，**没确认的会出现然后消失，确认的不会**。而我在 step63/68
里统计的是 `find_fast_bsp3` 的全部输出，它的返回列里根本没有确认标志
（entry_idx/direction/bo_idx/pb_idx/lag/depth/zg/zd/width_pct/occ/zone_i），
**两种被混在一起了**，所以「额外信号 74%」这个数字不能直接拿来说实盘。

确认状态在更上游，`zones_from_zs_list`：

    sure_key = str(getattr(key_bi, "sure_time", "") or "")
    end_key  = str(getattr(key_bi, "end_time", "") or "")
    avail = ts_of.get(sure_key) or ts_of.get(end_key)   # ← 静默退回 end_time

`ChanBI` 初始 `is_sure=False / sure_time=None`，确认时才 `set_is_sure(True, ...)`。
所以**末笔未确认时 available_ts 退回 end_time，而 end_time 随笔延伸而移动**，
中枢的可用时刻跟着漂 —— 这正是「出现然后消失」的那一种。笔一旦确认，
`sure_time` 固定，中枢不再动。

这也解释了 §5.41 的数量级：中枢层面确认时刻只被改 6.5%，而我在信号层面看到 74%。

本脚本按 `zs.bi_list[-1].is_sure` 把信号拆成两组，分别看：
  额外率  未确认组应显著高（会出现然后消失），已确认组应接近 0
  收益    若亏损集中在未确认组，那么修法就是**信号侧加一道 is_sure 门**，
          而不是动出场参数或放弃 B4

⚠️ 同时要查的第二件事：**实盘路径到底交易哪一种。** `shadow_signal.py` 的三道
滤网是同向 + 阶梯 + ATR 门控，**没有 is_sure 这一道**。若未确认组确实是亏损源，
且实盘没有挡它，那这道门就是要补的东西。
"""
from __future__ import annotations

import argparse
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")
HERE = Path(__file__).resolve().parent
sys.path.insert(0, str(HERE))
sys.path.insert(0, str(HERE.parent))

OUT = HERE / "out" / "step70_sure.feather"
SL, SCALE_AT, RUNNER, RSTOP, MAXB = 2.0, 3.0, 8.0, 2.0, 48
WIN, MAX_GROW, GATE_BP = 2001, 500, 8.0


def _sure_map(zs_list) -> dict:
    """(zg, zd) -> 末笔是否已确认。zones_from_zs_list 会按 available_ts 重排，
    索引对不上，所以用中枢边界当键接回去。"""
    m = {}
    for zs in zs_list:
        bis = getattr(zs, "bi_list", []) or []
        if not bis:
            continue
        m[(round(float(zs.zg), 10), round(float(zs.zd), 10))] = \
            bool(getattr(bis[-1], "is_sure", False))
    return m


def replay(sym: str, ltf: str, htf: str, rows: int,
           steps: int) -> pd.DataFrame | None:
    from chanlun import TF_DF
    from chanlun.analysis.fast_bsp import (
        ensure_timestamp,
        find_fast_bsp3,
        zones_from_zs_list,
    )
    from lib.data import fetch_ohlcv
    from lib.fx_signal import extract_fx_signals, signals_to_frame
    from lib.nested_bsp import attach_htf_context, htf_fx_timeline

    try:
        df = fetch_ohlcv(f"{sym}/USDT:USDT", ltf, rows)
        if df is None or len(df) < WIN + steps + 100:
            return None
        df = df.iloc[-(WIN + steps):].reset_index(drop=True)

        full = TF_DF(df, 1, ltf)
        cdf = ensure_timestamp(full.dataframe)
        zsf = full.cal_bi_zs_list_pure(full.bi_list)
        if not zsf:
            return None
        sig_full = find_fast_bsp3(cdf, zones_from_zs_list(zsf, cdf))
        full_keys = {(int(r.entry_idx), int(r.direction))
                     for r in sig_full.itertuples()} if not sig_full.empty \
            else set()

        dh = fetch_ohlcv(f"{sym}/USDT:USDT", htf, rows)
        tl = None
        if dh is not None and len(dh) > 500:
            ch = TF_DF(dh, 1, htf)
            tl = htf_fx_timeline(
                signals_to_frame(extract_fx_signals(ch, ch.dataframe)),
                ch.dataframe)

        rec: dict[tuple, dict] = {}
        chan, anchor = None, 0
        for i in range(WIN, len(df)):
            if chan is None or (i - anchor) >= MAX_GROW:
                w = df.iloc[i - WIN + 1:i + 1].copy()
                chan = TF_DF(w, 1, ltf)
                chan.init_stream(w, 1, ltf)
                anchor = i
            else:
                chan.append_bar(df.iloc[i])
            try:
                zl = chan.cal_bi_zs_list_pure(chan.bi_list)
                if not zl:
                    continue
                sub = ensure_timestamp(chan.dataframe)
                z = zones_from_zs_list(zl, sub)
                if z is None or z.empty:
                    continue
                sm = _sure_map(zl)
                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))
                z["z_sure"] = [
                    sm.get((round(float(a), 10), round(float(b), 10)), False)
                    for a, b in zip(z["zg"], z["zd"])]
                s = find_fast_bsp3(sub, z)
                if s is None or s.empty:
                    continue
                last = len(sub) - 1
                s = s[s["entry_idx"].astype(int) == last]
                if s.empty or "zone_i" not in s.columns:
                    continue
                s = s.merge(z[["zone_i", "z_above", "z_below", "z_sure"]],
                            on="zone_i", how="left")
                if tl is not None:
                    s = attach_htf_context(s, sub, tl, "h1")
            except Exception:                                 # noqa: BLE001
                continue
            for r in s.itertuples():
                k = (i, int(r.direction))
                if k in rec:
                    continue
                push = getattr(r, "z_above" if r.direction == 1
                               else "z_below", None)
                ag = getattr(r, "h1_agree", 0)
                rec[k] = {
                    "sym": sym, "entry_idx": i, "direction": int(r.direction),
                    "in_full": k in full_keys,
                    "z_sure": bool(getattr(r, "z_sure", False)),
                    "ladder_ok": int(bool(pd.notna(push) and bool(push))),
                    "h1_agree": int(ag) if pd.notna(ag) else 0,
                }
        if not rec:
            return None
        r = pd.DataFrame(list(rec.values()))

        from lib.exit_model import cfg_name, walk_exits
        atr = cdf["atr"].to_numpy(float)
        cl = cdf["close"].to_numpy(float)
        r = r[(r.entry_idx < len(cdf) - 2)
              & np.isfinite(atr[r.entry_idx.values])
              & (atr[r.entry_idx.values] > 0)].reset_index(drop=True)
        if r.empty:
            return None
        res = walk_exits(cdf, pd.DataFrame({
            "entry_idx": r.entry_idx.values,
            "direction": r.direction.values}), [SL], [RUNNER], [MAXB],
            scale_at=SCALE_AT, runners=(RUNNER,), runner_stops=(RSTOP,))
        cfg = cfg_name(SL, RUNNER, MAXB, RSTOP)
        if len(res) != len(r):
            return None
        for c in ("g", "r", "c"):
            r[c] = res[f"{cfg}_{c}"].to_numpy()
        r["atr_pct"] = atr[r.entry_idx.values] / cl[r.entry_idx.values]
        r["gate_ok"] = (r.atr_pct * 1e4 >= GATE_BP).astype(int)
        r["pass_all"] = ((r.h1_agree == 1) & (r.ladder_ok == 1)
                         & (r.gate_ok == 1)).astype(int)
        return r
    except Exception as e:                                    # noqa: BLE001
        print(f"  {sym} 失败: {type(e).__name__}: {e}", flush=True)
        return None


def perf(g: pd.DataFrame) -> dict | None:
    from lib.exit_model import fee_of, taker_notional
    if len(g) < 15:
        return None
    net = g.g.values - fee_of(g.r.values, g.c.values)
    gR = g.g.values / (SL * g.atr_pct.values)
    w, o = net[net > 0].sum(), -net[net <= 0].sum()
    return {
        "笔数": len(g), "胜率": f"{(net > 0).mean()*100:.1f}%",
        "PF": round(w / o, 2) if o > 0 else np.inf,
        "余量bp": round(net.mean()
                       / taker_notional(g.r.values, g.c.values).mean() * 1e4, 2),
        "t值": round(gR.mean() / (gR.std(ddof=1) / np.sqrt(len(g))), 2),
    }


def report(d: pd.DataFrame) -> None:
    print("\n" + "=" * 92)
    print("【一】判据：额外信号是不是集中在「末笔未确认」那一组")
    print("=" * 92)
    rows = []
    for k, g in d.groupby(d.z_sure):
        rows.append({"中枢末笔": "已确认" if k else "未确认", "信号数": len(g),
                     "额外(全量没有)": int((~g.in_full).sum()),
                     "额外率": f"{(~g.in_full).mean()*100:.1f}%"})
    print(pd.DataFrame(rows).to_string(index=False))
    print("""
  用户的判断：「没确认的会出现然后消失，确认的不会」。
  若已确认组额外率接近 0 -> 判断成立，之前 74% 是把两种混在一起统计的结果。""")

    print("\n" + "=" * 92)
    print("【二】亏损是不是也集中在未确认组")
    print("=" * 92)
    rows = []
    for k, g in d.groupby(d.z_sure):
        nm = "已确认" if k else "未确认"
        for lab, x in [("全部", g), ("三道滤网后", g[g.pass_all == 1])]:
            s = perf(x)
            if s:
                rows.append({"中枢末笔": nm, "口径": lab, **s})
    print(pd.DataFrame(rows).to_string(index=False))

    print("\n" + "=" * 92)
    print("【三】若补一道 is_sure 门，实盘口径会变成什么样")
    print("=" * 92)
    rows = []
    for nm, x in [
        ("现状：三道滤网", d[d.pass_all == 1]),
        ("**加 is_sure 门**", d[(d.pass_all == 1) & d.z_sure]),
        ("  对照：仅未确认", d[(d.pass_all == 1) & ~d.z_sure]),
    ]:
        s = perf(x)
        if s:
            rows.append({"口径": nm, **s})
    print(pd.DataFrame(rows).to_string(index=False))
    print("""
  ⚠️ `shadow_signal.py` 的三道滤网是同向 + 阶梯 + ATR 门控，**没有 is_sure**。
  若加上这道门 PF 明显回升，那它就是要补进信号路径的东西。""")


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--symbols", default="BTC,ETH,SOL,LINK,DOGE")
    ap.add_argument("--ltf", default="5m")
    ap.add_argument("--htf", default="30m")
    ap.add_argument("--rows", type=int, default=45_000)
    ap.add_argument("--steps", type=int, default=20_000)
    ap.add_argument("--workers", type=int, default=5)
    ap.add_argument("--reuse", action="store_true")
    args = ap.parse_args()

    if args.reuse and OUT.exists():
        report(pd.read_feather(OUT))
        return
    syms = [s.strip() for s in args.symbols.split(",")]
    print(f"[确认态拆分] {len(syms)} 币 × {args.steps} 根 · {args.ltf}\n",
          flush=True)
    parts = []
    with ProcessPoolExecutor(max_workers=args.workers) as ex:
        fut = {ex.submit(replay, s, args.ltf, args.htf, args.rows,
                         args.steps): s for s in syms}
        for i, f in enumerate(as_completed(fut), 1):
            r = f.result()
            print(f"  [{i}/{len(syms)}] {fut[f]} "
                  f"{0 if r is None else len(r)}", flush=True)
            if r is not None:
                parts.append(r)
    if not parts:
        print("无结果")
        return
    d = pd.concat(parts, ignore_index=True)
    OUT.parent.mkdir(exist_ok=True)
    d.to_feather(OUT)
    report(d)


if __name__ == "__main__":
    main()