"""Step 18：两条存活路径的正面对比与尾部检验。

路径一  同级别中枢突破（step13）        1389 笔  PF 1.63
路径二  区间套快速三买（step17）        239 笔  PF 1.52

样本量差 6 倍，但真正决定能否上实盘的是尾部依赖：
step14 已发现路径一剔掉最赚的 5% 后 t 值就从 6.45 塌到 1.60。
本步用同一把尺子量路径二。
"""
from __future__ import annotations

import sys
import warnings
from pathlib import Path

import numpy as np
import pandas as pd

warnings.filterwarnings("ignore")
pd.set_option("display.width", 260)

OUT = Path(__file__).parent / "out"
FEE = 0.0008


def trim_curve(r: np.ndarray, label: str) -> list[dict]:
    rows = []
    for k in (0, 1, 2, 5, 10):
        v = r if k == 0 else r[r <= np.quantile(r, 1 - k / 100)]
        win, loss = v[v > 0], v[v <= 0]
        pf = win.sum() / abs(loss.sum()) if len(loss) and loss.sum() != 0 else np.inf
        sd = v.std(ddof=1)
        rows.append({
            "路径": label, "剔除最赚": f"{k}%", "笔数": len(v),
            "均收益": f"{v.mean() * 100:+.3f}%", "PF": f"{pf:.2f}",
            "t值": f"{v.mean() / (sd / np.sqrt(len(v))):+.2f}",
        })
    return rows


def profile(r: np.ndarray, label: str) -> dict:
    win, loss = r[r > 0], r[r <= 0]
    sd = r.std(ddof=1)
    return {
        "路径": label, "笔数": len(r),
        "胜率": f"{(r > 0).mean() * 100:.1f}%",
        "均收益": f"{r.mean() * 100:+.3f}%",
        "中位数": f"{np.median(r) * 100:+.3f}%",
        "PF": f"{win.sum() / abs(loss.sum()):.2f}",
        "偏度": f"{pd.Series(r).skew():.2f}",
        "t值": f"{r.mean() / (sd / np.sqrt(len(r))):+.2f}",
    }


def main() -> None:
    p1 = pd.read_csv(OUT / "step13_all_trades.csv", parse_dates=["date"])
    p2 = pd.read_csv(OUT / "step17_fast_bsp3_trades.csv", parse_dates=["date"])
    r1, r2 = p1["ret"].to_numpy(), p2["ret"].to_numpy()

    # 区间套的最优组合：1h 同向 + 浅回抽
    dq = p2["depth"].quantile(0.66)
    best = p2[(p2["h1_agree"] == 1) & (p2["depth"] >= dq)]
    r3 = best["ret"].to_numpy()

    print("########## 1. 总体画像 ##########")
    print(pd.DataFrame([
        profile(r1, "同级别中枢突破"),
        profile(r2, "区间套快速三买"),
        profile(r3, "区间套(同向+浅回抽)"),
    ]).to_string(index=False))
    print("\n  中位数为正说明多数交易在赚钱，为负则说明靠尾部。")

    print("\n########## 2. 尾部依赖检验 ##########")
    rows = trim_curve(r1, "中枢突破") + trim_curve(r2, "区间套三买")
    d = pd.DataFrame(rows).pivot(index="剔除最赚", columns="路径",
                                 values=["PF", "t值"])
    print(d.to_string())

    print("\n########## 3. 成本敏感性 ##########")
    rows = []
    for mult, name in [(1, "0.08%"), (2, "0.16%"), (3, "0.24%"), (5, "0.40%")]:
        for r, lab in ((r1, "中枢突破"), (r2, "区间套三买")):
            v = r - (mult - 1) * FEE
            win, loss = v[v > 0], v[v <= 0]
            sd = v.std(ddof=1)
            rows.append({
                "成本": name, "路径": lab,
                "PF": f"{win.sum() / abs(loss.sum()):.2f}",
                "t值": f"{v.mean() / (sd / np.sqrt(len(v))):+.2f}",
            })
    print(pd.DataFrame(rows).pivot(index="成本", columns="路径",
                                   values=["PF", "t值"]).to_string())

    print("\n########## 4. 收益分位对比 ##########")
    qs = [0.05, 0.25, 0.5, 0.75, 0.95]
    print(pd.DataFrame({
        "分位": [f"P{int(q * 100)}" for q in qs],
        "中枢突破": [f"{np.quantile(r1, q) * 100:+.2f}%" for q in qs],
        "区间套三买": [f"{np.quantile(r2, q) * 100:+.2f}%" for q in qs],
    }).to_string(index=False))

    print("\n########## 5. 交易频率 ##########")
    for r, t, lab in ((r1, p1, "中枢突破"), (r2, p2, "区间套三买")):
        yrs = (t["date"].max() - t["date"].min()).days / 365.25
        print(f"  {lab:>10}：{len(r) / yrs:.0f} 笔/年  "
              f"覆盖 {t['date'].min().date()} -> {t['date'].max().date()}")


if __name__ == "__main__":
    main()