Chan/research/live/latency_compare.py

"""把两侧 t_data − t_close 对齐，并折算成 bp，与滑点余量对照。

为什么要折算成 bp 才有意义：延迟本身不花钱，花钱的是延迟期间价格的漂移。
按随机游走，t 秒的价格标准差是 σ_1m · √(t/60)，其中 σ_1m 是本币 1m 收益
的标准差。入场方向上还有系统性追价（信号触发往往伴随同向动量），所以随机
漂移只是下限，真实成本更高——这也是为什么最终仍要用真实盘口测滑点。

余量（bitget_baseline.py 得出，Bitget 原生基线减去手续费后剩下的空间）：
    BTC -0.13bp   ETH +4.02bp   SOL +2.92bp
BTC 本就为负，留着只作延迟测量的参照物，不作交易标的。

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

import sys
from pathlib import Path

import numpy as np
import pandas as pd

HERE = Path(__file__).resolve().parent
RESEARCH = HERE.parent
sys.path.insert(0, str(RESEARCH))

OUT = RESEARCH / "out"
BUDGET_BP = {"BTC": -0.13, "ETH": 4.02, "SOL": 2.92}
SYMS = ("BTC", "ETH", "SOL")


def vol_bp_per_min() -> dict[str, float]:
    """从 Bitget 缓存算 1m 收益标准差，单位 bp。"""
    out = {}
    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
        df = pd.read_feather(f)
        r = np.log(df["close"].to_numpy(dtype=float))
        out[s] = float(np.nanstd(np.diff(r)) * 1e4)
    return out


def drift_bp(lag_ms: float, vol: float) -> float:
    """随机游走下，lag 毫秒对应的价格漂移标准差（bp）。"""
    return vol * np.sqrt(max(lag_ms, 0) / 60_000.0)


def load(tag: str) -> pd.DataFrame | None:
    f = OUT / f"latency_{tag}.csv"
    if not f.exists():
        return None
    df = pd.read_csv(f)
    return df if not df.empty else None


def describe(df: pd.DataFrame, name: str, vols: dict) -> None:
    print(f"\n########## {name}：t_data − t_close ##########")
    print(f"{'币':<5}{'n':>5}{'中位ms':>9}{'P90ms':>9}{'最大ms':>9}"
          f"{'中位漂移bp':>12}{'余量bp':>9}{'占余量':>9}")
    for s in SYMS:
        v = df[df["sym"] == s]["lag_ms"].to_numpy(dtype=float)
        if not len(v):
            continue
        med, p90 = float(np.median(v)), float(np.percentile(v, 90))
        vol = vols.get(s)
        d = drift_bp(med, vol) if vol else float("nan")
        b = BUDGET_BP[s]
        share = f"{d / b * 100:.0f}%" if b > 0 else "—(负)"
        print(f"{s:<5}{len(v):>5}{med:>9.0f}{p90:>9.0f}{v.max():>9.0f}"
              f"{d:>12.2f}{b:>9.2f}{share:>9}")


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

    a, b = load("ccxt"), load("hummingbot")
    if a is None or b is None:
        print(f"\n数据未就绪：ccxt={'有' if a is not None else '无'} "
              f"hummingbot={'有' if b is not None else '无'}")
        if a is not None:
            describe(a, "ccxt.pro", vols)
        if b is not None:
            describe(b, "Hummingbot", vols)
        return

    describe(a, "ccxt.pro", vols)
    describe(b, "Hummingbot", vols)

    # 逐根配对才能消掉「不同分钟市场活跃度不同」的干扰
    m = a.merge(b, on=["kline_ts", "sym"], suffixes=("_ccxt", "_hb"))
    print(f"\n########## 逐根配对（重叠 {len(m)} 根）##########")
    if m.empty:
        print("  两侧无重叠 K 线，无法配对；检查采集时间窗是否错开")
        return
    print(f"{'币':<5}{'n':>5}{'ccxt中位':>10}{'HB中位':>10}"
          f"{'差值中位':>10}{'HB更慢占比':>12}{'差值→bp':>10}")
    for s in SYMS:
        g = m[m["sym"] == s]
        if g.empty:
            continue
        d = (g["lag_ms_hb"] - g["lag_ms_ccxt"]).to_numpy(dtype=float)
        vol = vols.get(s)
        # 差值转 bp：比较两条路径各自漂移的差，而非直接对差值开方
        extra = (drift_bp(float(np.median(g["lag_ms_hb"])), vol)
                 - drift_bp(float(np.median(g["lag_ms_ccxt"])), vol)) if vol else float("nan")
        print(f"{s:<5}{len(g):>5}{np.median(g['lag_ms_ccxt']):>10.0f}"
              f"{np.median(g['lag_ms_hb']):>10.0f}{np.median(d):>10.0f}"
              f"{(d > 0).mean() * 100:>11.0f}%{extra:>10.2f}")

    print("\n判读：差值 → bp 若显著小于余量，说明选哪个运行时不影响结论，"
          "可直接用 Hummingbot（生产路径一致）；若接近或超过余量，"
          "则运行时本身就是成本项，需要单独优化或放弃 1m。")


if __name__ == "__main__":
    main()