Chan/research/live/latency_attribute.py

"""把 1030ms 归因到具体环节。

前面的测量已经排除两个可能：
  · Bitget 换根首条推送就是 update，Hummingbot 没有因丢弃 snapshot 而等待
  · 容器内同进程里，Hummingbot 的 feed 只比原始 WS 慢 2~6ms，处理开销可忽略

剩下的变量是「位置」和「客户端」。本脚本对同一批 K 线三方对齐：

  host_ccxt       宿主机 ccxt.pro watch_ohlcv        latency_ccxt.csv
  host_raw        宿主机 原始 aiohttp WS             probe_raw_host.csv
  cont_raw        容器内 原始 aiohttp WS             probe_hb_vs_raw.csv
  cont_hb         容器内 Hummingbot candles feed     probe_hb_vs_raw.csv

据此可分离两件事：
  cont_raw − host_raw   容器网络的代价（同一份代码，只换位置）
  host_ccxt − host_raw  ccxt.pro 客户端的差异（同一位置，只换客户端）

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

from pathlib import Path

import numpy as np
import pandas as pd

OUT = Path(__file__).resolve().parents[1] / "out"
SYMS = ("BTC", "ETH", "SOL")


def load() -> pd.DataFrame | None:
    parts = []

    f = OUT / "latency_ccxt.csv"
    if f.exists():
        d = pd.read_csv(f)
        if not d.empty:
            parts.append(d[["kline_ts", "sym", "t_data_ms"]]
                         .rename(columns={"t_data_ms": "host_ccxt"}))

    f = OUT / "probe_raw_host.csv"
    if f.exists():
        d = pd.read_csv(f)
        if not d.empty:
            parts.append(d[["kline_ts", "sym", "raw_ms"]]
                         .rename(columns={"raw_ms": "host_raw"}))

    f = OUT / "probe_hb_vs_raw.csv"
    if f.exists():
        d = pd.read_csv(f)
        if not d.empty:
            parts.append(d[["kline_ts", "sym", "raw_ms", "hb_ms"]]
                         .rename(columns={"raw_ms": "cont_raw",
                                          "hb_ms": "cont_hb"}))

    if not parts:
        return None
    m = parts[0]
    for p in parts[1:]:
        m = m.merge(p, on=["kline_ts", "sym"], how="outer")
    return m


def main() -> None:
    m = load()
    if m is None or m.empty:
        print("四路数据均缺失")
        return

    cols = [c for c in ("host_ccxt", "host_raw", "cont_raw", "cont_hb")
            if c in m.columns]
    print(f"各路样本数（重叠前）：")
    for c in cols:
        print(f"  {c}: {int(m[c].notna().sum())}")

    print("\n########## 各路 t_data − t_close（ms，中位）##########")
    print(f"{'币':<5}" + "".join(f"{c:>11}" for c in cols))
    for s in SYMS:
        g = m[m["sym"] == s]
        line = f"{s:<5}"
        for c in cols:
            v = (g[c] - g["kline_ts"]).dropna()
            line += f"{np.median(v):>11.0f}" if len(v) else f"{'—':>11}"
        print(line)

    # 只在四路都有的 K 线上做差，避免不同子集的中位数互相错位
    full = m.dropna(subset=cols)
    print(f"\n########## 归因（仅四路齐全的 {len(full)} 根）##########")
    if full.empty:
        print("  无四路齐全的 K 线；检查三个采集窗口是否重叠")
        return
    pairs = []
    if "cont_raw" in cols and "host_raw" in cols:
        pairs.append(("容器网络代价", "cont_raw", "host_raw"))
    if "host_ccxt" in cols and "host_raw" in cols:
        pairs.append(("ccxt.pro 客户端差异", "host_ccxt", "host_raw"))
    if "cont_hb" in cols and "cont_raw" in cols:
        pairs.append(("Hummingbot 处理开销", "cont_hb", "cont_raw"))
    if "cont_hb" in cols and "host_ccxt" in cols:
        pairs.append(("合计：容器 HB vs 宿主 ccxt", "cont_hb", "host_ccxt"))

    print(f"{'环节':<26}" + "".join(f"{s:>9}" for s in SYMS))
    for name, a, b in pairs:
        line = f"{name:<26}"
        for s in SYMS:
            g = full[full["sym"] == s]
            if g.empty:
                line += f"{'—':>9}"
                continue
            line += f"{np.median(g[a] - g[b]):>9.0f}"
        print(line)
    print("\n（单位 ms，正数表示前者更慢）")


if __name__ == "__main__":
    main()