"""Step 50：信号根的成交量是否预测质量 ——「有资金的趋势才是好趋势」。

用户假设：开仓时刻的成交量越大，说明有真金白银在推，趋势更可信。

这个假设满足 §3.31 立的纪律：信号根已收盘，其成交量在开仓那一刻可知，
是合规的可交易信息，不像「我是簇里第几个」那样含未来。

只测两件事，不做穷举（组合空间大，多测必出假阳性）：
  主假设   相对成交量越高，毛R 与滑点余量越好
  次假设   它与 §3.31 的「有前序信号」是同一件事，还是两件独立的事

口径与 step48/49 一致。发现期（2026-01-30 起）与样本外分开报，
主假设若只在其中一边成立就不算通过。
"""
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", 340)

SL = 2.0
GATE_BP = 8.0
WIN_MIN = 5
OUT = HERE / "out" / "step50_volume.feather"
IS_START = pd.Timestamp("2026-01-30", tz="Asia/Shanghai")


def collect(sym: str, rows: int):
    import warnings as _w
    _w.filterwarnings("ignore")
    sys.path.insert(0, str(HERE))
    sys.path.insert(0, str(HERE.parent))
    from step48_signal_timing import collect as _c
    return _c(sym, rows)


def prep(d: pd.DataFrame) -> pd.DataFrame:
    from lib.exit_model import fee_of, taker_notional

    d = d.sort_values("date").reset_index(drop=True)
    t = d.date.values.astype("datetime64[m]").astype(np.int64)
    d["prev"] = np.searchsorted(t, t, "left") - np.searchsorted(t, t - WIN_MIN, "left")
    net = d.g.values - fee_of(d.r.values, d.c.values)
    d["net"] = net
    d["gR"] = d.g.values / (SL * d.atr_pct.values)
    d["R"] = net / (SL * d.atr_pct.values)
    d["tn"] = taker_notional(d.r.values, d.c.values)
    return d


def stat(g: pd.DataFrame, lab: str, denom: int) -> dict:
    if len(g) < 25:
        return {"分组": lab, "笔数": len(g), "备注": "样本不足"}
    w, o = g.net[g.net > 0].sum(), -g.net[g.net <= 0].sum()
    return {"分组": lab, "笔数": len(g), "占比": f"{len(g)/denom*100:.0f}%",
            "胜率": f"{(g.net > 0).mean()*100:.1f}%",
            "毛R": round(g.gR.mean(), 3), "净均R": round(g.R.mean(), 3),
            "PF": round(w / o, 2) if o > 0 else np.inf,
            "余量bp": round(g.net.mean() / g.tn.mean() * 1e4, 2)}


def by_volume(d: pd.DataFrame, col: str, label: str) -> None:
    x = d[d[col].notna() & np.isfinite(d[col])]
    if len(x) < 200:
        print(f"  {label}: 样本不足")
        return
    x = x.copy()
    x["bin"] = pd.qcut(x[col], 4, labels=["量最低", "量中低", "量中高", "量最高"])
    rows = [stat(g, str(b), len(x)) for b, g in x.groupby("bin", observed=True)]
    t = pd.DataFrame(rows)
    med = x.groupby("bin", observed=True)[col].median().round(2).to_dict()
    t.insert(1, f"{col}中位", [med.get(b) for b in t["分组"]])
    print(f"\n--- {label} ---")
    print(t.to_string(index=False))


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--symbols", default="BTC,BNB,ETH,SOL,LINK,LTC,AVAX,XRP,DOGE,ADA")
    ap.add_argument("--rows", type=int, default=800_000)
    ap.add_argument("--workers", type=int, default=3)
    ap.add_argument("--reuse", action="store_true")
    args = ap.parse_args()

    if args.reuse and OUT.exists():
        d = pd.read_feather(OUT)
    else:
        syms = [s.strip() for s in args.symbols.split(",")]
        print(f"[信号根成交量] {len(syms)} 币 × {args.rows} 根 1m\n", flush=True)
        parts = []
        with ProcessPoolExecutor(max_workers=args.workers) as ex:
            fut = {ex.submit(collect, s, args.rows): s for s in syms}
            for i, f in enumerate(as_completed(fut), 1):
                r = f.result()
                print(f"  [{i}/{len(syms)}] {fut[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)
        d.to_feather(OUT)

    d["date"] = pd.to_datetime(d["date"])
    d = prep(d[(d.htf == 1.0) & d.lad & (d.atr_bp >= GATE_BP)].copy())
    oos, ins = d[d.date < IS_START], d[d.date >= IS_START]
    print(f"\n实盘口径 {len(d)} 笔  |  样本外 {len(oos)}  发现期 {len(ins)}")

    print("\n" + "=" * 104)
    print("########## 主假设：相对成交量越高越好？ ##########")
    for lab, part in (("样本外", oos), ("发现期", ins)):
        print(f"\n===== {lab} =====")
        by_volume(part, "vr10", f"{lab} / 量比 vs 前 10 根")
        by_volume(part, "vr60", f"{lab} / 量比 vs 前 60 根（换基准对照）")

    print("\n" + "=" * 104)
    print("########## 次假设：成交量与「有前序」是不是同一件事 ##########")
    x = d[d.vr10.notna() & np.isfinite(d.vr10)].copy()
    x["高量"] = x.vr10 >= x.vr10.median()
    x["有前序"] = x.prev >= 1
    print("\n2×2（全样本）")
    rows = []
    for hv in (False, True):
        for pv in (False, True):
            g = x[(x.高量 == hv) & (x.有前序 == pv)]
            rows.append(stat(g, f"{'高量' if hv else '低量'} × {'有前序' if pv else '无前序'}", len(x)))
    print(pd.DataFrame(rows).to_string(index=False))

    print("\n" + "=" * 104)
    print("########## 混淆排查：量效应是不是 ATR 效应换了张脸 ##########")
    y = d[d.vr60.notna() & np.isfinite(d.vr60)].copy()
    y["atrQ"] = pd.qcut(y.atr_bp, 4, labels=["ATR-Q1", "Q2", "Q3", "Q4"])
    rows = []
    for q, g in y.groupby("atrQ", observed=True):
        g = g.copy()
        g["vq"] = pd.qcut(g.vr60, 2, labels=["低量", "高量"])
        lo, hi = g[g.vq == "低量"], g[g.vq == "高量"]
        if min(len(lo), len(hi)) < 25:
            continue
        rows.append({"ATR分位": str(q), "笔数": len(g),
                     "低量毛R": round(lo.gR.mean(), 3), "高量毛R": round(hi.gR.mean(), 3),
                     "毛R差": round(hi.gR.mean() - lo.gR.mean(), 3),
                     "低量余量": round(lo.net.mean() / lo.tn.mean() * 1e4, 2),
                     "高量余量": round(hi.net.mean() / hi.tn.mean() * 1e4, 2),
                     "方向": "低量更好" if lo.gR.mean() > hi.gR.mean() else "高量更好"})
    print(pd.DataFrame(rows).to_string(index=False))

    print("\n########## 逐时段稳定性（与 step49 同一根标尺）##########")
    y["半年"] = y.date.dt.to_period("2Q").astype(str)
    rows = []
    for p, g in y.groupby("半年", observed=True):
        if len(g) < 120:
            continue
        g = g.copy()
        g["vq"] = pd.qcut(g.vr60, 2, labels=["低量", "高量"])
        lo, hi = g[g.vq == "低量"], g[g.vq == "高量"]
        rows.append({"时段": p, "笔数": len(g),
                     "低量毛R": round(lo.gR.mean(), 3), "高量毛R": round(hi.gR.mean(), 3),
                     "低量余量": round(lo.net.mean() / lo.tn.mean() * 1e4, 2),
                     "高量余量": round(hi.net.mean() / hi.tn.mean() * 1e4, 2),
                     "方向": "低量更好" if lo.gR.mean() > hi.gR.mean() else "高量更好"})
    t = pd.DataFrame(rows)
    print(t.to_string(index=False))
    if len(t):
        print(f"\n{len(t)} 个时段中 {(t.方向 == '低量更好').sum()} 个低量更好")

    print("\n两者的相关性")
    print(f"  有前序组 vr10 中位 {x[x.有前序].vr10.median():.2f}"
          f"  vs 无前序组 {x[~x.有前序].vr10.median():.2f}")
    print(f"  高量组里有前序占 {x[x.高量].有前序.mean()*100:.1f}%"
          f"  vs 低量组 {x[~x.高量].有前序.mean()*100:.1f}%")


if __name__ == "__main__":
    main()