"""影子交易器的报表:首日延迟门槛 + 滑点对延迟曲线。

两份产物对应计划里的两件事。

### 延迟门槛(提前止损用)

跑满 24 小时先看这个。若**总延迟已令预期漂移超过余量**,说明方案在这台机器
上就不成立,不必等两周样本再停。余量取 bitget_baseline.py 的实测值:
BTC −0.13bp(本就为负,只作参照)、ETH +4.02bp、SOL +2.92bp。

漂移按随机游走折算:σ_1m · √(t/60)。这是下限——入场条件是「收盘突破转强」,
那一刻价格正朝我们方向跑,延迟造成的是系统性追价,不会正负抵消。所以实测
滑点理应比这个折算值更差,两者对照本身就是个校验。

### 滑点对延迟曲线

把延迟当自变量:0.5s / 1s / 2s / 5s 各一个滑点值,外加「actual」= 本机实际
算完的时刻。这样即便本机算得慢,也能读出「若延迟压到 X 秒,滑点是多少」,
决策不被当前实现拖累。

    .venv/bin/python research/live/shadow_report.py
"""
from __future__ import annotations

from pathlib import Path

import numpy as np
import pandas as pd

HERE = Path(__file__).resolve().parent
OUT = HERE.parent / "out"
SYMS = ("BTC", "ETH", "SOL")
BUDGET_BP = {"BTC": -0.13, "ETH": 4.02, "SOL": 2.92}


def vol_bp() -> dict[str, float]:
    v = {}
    for s in SYMS:
        f = HERE / "cache" / f"bitget_{s}_1m_30d.feather"
        if not f.exists():
            f = HERE / "cache" / f"bitget_{s}_1m_210d.feather"
        if not f.exists():
            continue
        c = np.log(pd.read_feather(f)["close"].to_numpy(float))
        v[s] = float(np.nanstd(np.diff(c)) * 1e4)
    return v


def latency_gate(lat: pd.DataFrame, vols: dict) -> None:
    print("########## 一、延迟门槛 ##########")
    span_h = (lat["t_close_ms"].max() - lat["t_close_ms"].min()) / 3.6e6
    print(f"样本跨度 {span_h:.1f} 小时 · 共 {len(lat)} 根\n")
    print(f"{'币':<5}{'根数':>6}{'数据ms':>9}{'计算ms':>9}{'总延迟ms':>10}"
          f"{'P90ms':>8}{'折算漂移bp':>12}{'余量bp':>9}{'占余量':>9}")
    verdicts = {}
    for s in SYMS:
        g = lat[lat["sym"] == s]
        if g.empty:
            continue
        d = float(np.median(g["lag_data_ms"]))
        c = float(np.median(g["compute_ms"]))
        t = float(np.median(g["lag_signal_ms"]))
        p90 = float(np.percentile(g["lag_signal_ms"], 90))
        vol = vols.get(s)
        drift = vol * np.sqrt(t / 60_000) if vol else float("nan")
        b = BUDGET_BP[s]
        share = drift / b if b > 0 else float("nan")
        verdicts[s] = (drift, b)
        txt = f"{share * 100:.0f}%" if b > 0 else "—(负)"
        print(f"{s:<5}{len(g):>6}{d:>9.0f}{c:>9.0f}{t:>10.0f}{p90:>8.0f}"
              f"{drift:>12.2f}{b:>9.2f}{txt:>9}")

    print("\n判读：")
    for s, (drift, b) in verdicts.items():
        if b <= 0:
            print(f"  {s}: 余量本就为负，不作交易标的，仅作延迟参照")
        elif drift > b:
            print(f"  {s}: 折算漂移 {drift:.2f}bp 已超余量 {b:.2f}bp —— 停下改方案")
        elif drift > b * 0.6:
            print(f"  {s}: 折算漂移 {drift:.2f}bp 吃掉余量 {b:.2f}bp 的六成以上，"
                  f"需要压延迟或放弃")
        else:
            print(f"  {s}: 折算漂移 {drift:.2f}bp 对余量 {b:.2f}bp 尚有空间，继续收集")


def slippage_curve(sig: pd.DataFrame) -> None:
    print("\n\n########## 二、滑点对延迟曲线 ##########")
    if sig.empty:
        print("  尚无信号样本")
        return
    n_sig = sig.groupby(["sym", "kline_ts", "direction"]).ngroups
    n_agree = sig[sig["h1_agree"] == 1].groupby(
        ["sym", "kline_ts", "direction"]).ngroups
    print(f"信号总数 {n_sig}（其中 h1_agree=1 的 {n_agree} 个）\n")

    order = ["0.5s", "1.0s", "2.0s", "5.0s", "actual"]
    for scope, sub in (("全部信号", sig),
                       ("仅 h1_agree=1（主口径）", sig[sig["h1_agree"] == 1])):
        if sub.empty:
            continue
        print(f"--- {scope} ---")
        print(f"{'延迟':<8}{'仓位':>9}{'n':>5}{'滑点均值bp':>12}"
              f"{'中位bp':>9}{'漂移bp':>9}{'价差bp':>9}{'冲击bp':>9}")
        for lb in order:
            g0 = sub[sub["delay_label"] == lb]
            if g0.empty:
                continue
            for nt in sorted(sub["notional"].unique()):
                g = g0[g0["notional"] == nt]
                if g.empty:
                    continue
                print(f"{lb:<8}{int(nt):>9}{len(g):>5}"
                      f"{g['slip_bp'].mean():>12.2f}"
                      f"{g['slip_bp'].median():>9.2f}"
                      f"{g['drift_bp'].mean():>9.2f}"
                      f"{g['spread_bp'].mean():>9.2f}"
                      f"{g['impact_bp'].mean():>9.2f}")
        print()

    print("--- 分币种（仅 h1_agree=1，仓位 5000）---")
    m = sig[(sig["h1_agree"] == 1) & (sig["notional"] == 5000.0)]
    if m.empty:
        print("  尚无样本")
        return
    print(f"{'币':<5}{'延迟':<8}{'n':>5}{'滑点均值bp':>12}{'余量bp':>9}")
    for s in SYMS:
        for lb in order:
            g = m[(m["sym"] == s) & (m["delay_label"] == lb)]
            if g.empty:
                continue
            print(f"{s:<5}{lb:<8}{len(g):>5}{g['slip_bp'].mean():>12.2f}"
                  f"{BUDGET_BP[s]:>9.2f}")


def main() -> None:
    vols = vol_bp()
    print("1m 收益标准差（bp/分钟，Bitget 实测）："
          + " ".join(f"{s} {v:.2f}" for s, v in vols.items()) + "\n")

    f_lat = OUT / "shadow_latency.csv"
    if f_lat.exists() and f_lat.stat().st_size > 0:
        lat = pd.read_csv(f_lat)
        if not lat.empty:
            latency_gate(lat, vols)
    else:
        print("尚无延迟数据")

    f_sig = OUT / "shadow_signals.csv"
    if f_sig.exists() and f_sig.stat().st_size > 0:
        sig = pd.read_csv(f_sig)
        slippage_curve(sig)
    else:
        print("\n尚无信号数据")


if __name__ == "__main__":
    main()