Chan/research/live/signal_sensitivity.py

"""对照实验：信号集对微小数据差异有多敏感。

venue_parity 量到 Bitget 与 Binance 的 1m 信号同根重合率只有 16%~41%，
而两家的 close 中位差仅 0.3bp、P95 约 2.5bp。在断言「换交易所会换掉一批信号」
之前，必须先排除另一种解释：**信号定义本身就对任何 2bp 级别的扰动极度敏感**。

这两种解释的后果完全不同：
  venue 差异   -> 换成 Bitget 自己的回测基线即可归因
  内在脆弱     -> Binance 回测的那份逐笔清单根本不可复现，滑点无从对照

做法：拿 Binance 原始数据当基线，注入不同幅度的 iid 噪声后重跑同一管线，
看重合率随噪声幅度的衰减曲线。噪声 0 必须给出 100%，否则说明管线不确定。

顺带单独测一档「tick 粗化」：把 Bitget SOL 的 0.001 精度四舍五入到 Binance
的 0.01，看重合率是否回升——若回升，SOL 的低重合就主要是精度差异造成的。

输出 out/signal_sensitivity.csv。
"""
from __future__ import annotations

import argparse
import os
import sys
import warnings
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
RESEARCH = HERE.parent
sys.path.insert(0, str(RESEARCH))
sys.path.insert(0, str(RESEARCH.parent))
pd.set_option("display.width", 240)

sys.path.insert(0, str(HERE))
from venue_parity import overlap, pipeline  # noqa: E402

SYMS = ("BTC", "ETH", "SOL")
LEVELS = (0.0, 0.25, 0.5, 1.0, 2.0, 4.0)   # bp
TICK = {"BTC": 0.1, "ETH": 0.01, "SOL": 0.01}


def perturb(df: pd.DataFrame, bp: float, tick: float, seed: int) -> pd.DataFrame:
    """给 OHLC 各自注入 iid 噪声，再修复 high/low 的包含关系并按 tick 归整。"""
    if bp <= 0:
        return df
    out = df.copy()
    rng = np.random.default_rng(seed)
    sd = bp / 1e4
    for c in ("open", "high", "low", "close"):
        v = out[c].to_numpy(dtype=float)
        out[c] = v * (1.0 + rng.normal(0.0, sd, size=len(v)))
    o, h, l, c = (out[x].to_numpy(dtype=float) for x in ("open", "high", "low", "close"))
    out["high"] = np.maximum.reduce([h, o, c])
    out["low"] = np.minimum.reduce([l, o, c])
    for x in ("open", "high", "low", "close"):
        out[x] = np.round(out[x] / tick) * tick
    return out


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--symbols", default="BTC,ETH,SOL")
    ap.add_argument("--seeds", type=int, default=2)
    ap.add_argument("--warmup", type=int, default=2000)
    args = ap.parse_args()

    from lib.data import load_local

    syms = [s.strip() for s in args.symbols.split(",")]
    period_ms = 60_000
    print(f"[信号敏感性] {syms} · 噪声档 {LEVELS} bp · 每档 {args.seeds} 个种子\n",
          flush=True)

    rows = []
    for sym in syms:
        # 与 venue_parity 用同一段窗口，便于两组数字直接对照
        cache = HERE / "cache" / f"bitget_{sym}_1m_30d.feather"
        if not cache.exists():
            print(f"{sym}: 缺 {cache.name}，先跑 venue_parity.py")
            continue
        bg = pd.read_feather(cache)
        lo, hi = int(bg.timestamp.min()), int(bg.timestamp.max())

        bn_l = load_local(f"{sym}/USDT:USDT", "1m")
        bn_h = load_local(f"{sym}/USDT:USDT", "5m")
        bn_l = bn_l[(bn_l.timestamp >= lo) & (bn_l.timestamp <= hi)].reset_index(drop=True)
        bn_h = bn_h[(bn_h.timestamp >= lo) & (bn_h.timestamp <= hi)].reset_index(drop=True)

        base = pipeline(bn_l, bn_h)
        cut = bn_l["timestamp"].to_numpy()[min(args.warmup, len(bn_l) - 1)]
        base = base[base.entry_ts >= cut]
        base_f = base[base["h1_agree"] == 1]
        print(f"── {sym}  基线 原始 {len(base)} 笔 / 过滤后 {len(base_f)} 笔",
              flush=True)

        for bp in LEVELS:
            n_seeds = 1 if bp == 0 else args.seeds
            acc = {"原始": [], "5m同向后": []}
            cnt = {"原始": [], "5m同向后": []}
            for k in range(n_seeds):
                pert = pipeline(perturb(bn_l, bp, TICK[sym], 1000 + k), bn_h)
                if pert.empty:
                    continue
                pert = pert[pert.entry_ts >= cut]
                pert_f = pert[pert["h1_agree"] == 1]
                for tag, a, b in (("原始", base, pert), ("5m同向后", base_f, pert_f)):
                    o = overlap(a, b, period_ms)
                    acc[tag].append(o["同根"])
                    cnt[tag].append(o["b"])
            for tag in ("原始", "5m同向后"):
                if not acc[tag]:
                    continue
                rows.append({"品种": sym, "口径": tag, "噪声bp": bp,
                             "基线笔数": len(base if tag == "原始" else base_f),
                             "扰动后笔数": round(float(np.mean(cnt[tag])), 1),
                             "同根重合": float(np.mean(acc[tag]))})
            print(f"   噪声 {bp:>4.2f}bp: 原始 {np.mean(acc['原始']) * 100:5.1f}% · "
                  f"过滤后 {np.mean(acc['5m同向后']) * 100:5.1f}%", flush=True)

    if not rows:
        print("无结果")
        return

    tb = pd.DataFrame(rows)
    print("\n" + "=" * 100)
    print("########## 噪声幅度 → 同根重合率 ##########")
    piv = tb[tb["口径"] == "5m同向后"].pivot_table(
        index="噪声bp", columns="品种", values="同根重合")
    print((piv * 100).round(1).to_string())
    print("  行是注入的 iid 噪声幅度（bp），值是与无噪声基线的同根重合率。")

    print("\n########## 与 venue_parity 的实测对照 ##########")
    print("  Bitget↔Binance 实测：close 中位差 0.05~0.33bp、P95 2.0~3.0bp，")
    print("  过滤后同根重合 BTC 40.9% / ETH 25.0% / SOL 15.9%。")
    print("  若上表在 1~2bp 档就掉到同一水平，说明主因是信号定义的内在脆弱，")
    print("  而不是 Bitget 这家交易所特殊。")

    out = RESEARCH / "out" / "signal_sensitivity.csv"
    tb.to_csv(out, index=False)
    print(f"\n产物写入 {out}")


if __name__ == "__main__":
    main()