research: B4 时点干净，但实盘做的不是回测那批单（实盘口径 PF 0.73 vs 回测 4.21）
step63 因果回放：B4 的时点完全干净——100% 召回、100% 准时、零滞后， 一类那个把 PF 从 2.35 打到 0.92 的坑（§3.396）B4 没有。 但回放多产出 592 个全量口径里不存在的信号，PF 0.46 / t −5.03。 step68 按实盘口径复测（2001 根滚动窗口、每 500 根 init_stream、只做当根收盘， 逐行对齐 shadow_signal.py），并把三道滤网全测一遍： 无过滤 789 笔，额外占比 75%，PF 0.64 三道全开 195 笔，额外占比 74%，PF 0.73 滤网把成交量砍掉 75% 却几乎不改变额外信号占比——按同比例刷掉好的和坏的。 拆开看：回测里也有的 51 笔 PF 4.21/t+5.90，回测里没有的 144 笔 PF 0.26/t−6.21。 即回测报的 4.21 拿不到：那 51 笔要事后全量重算才能识别，实盘当下分不出来。 机制是重画——实时算出的中枢，数据变多后被修正掉。与 §3.396 同类： 一类错在时点，B4 错在存在性。 顺带闭掉一条待办：2001 根窗口与 2万→4万根增长窗口跑出完全相同的 789/197/592， 窗口左边界效应判为否。 限定：本轮是 5m/30m 而实盘跑 1m，需单独复验；同向过滤器被开了未来函数后门 （HTF 时间线用全量算），真实盘只会更差。 Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
jackyu66git
@@ -0,0 +1,246 @@
|
||||
"""B4 主线的因果回放：实盘信号的时点是不是干净的。
|
||||
|
||||
step59 在一类上抓到一个会骗人的坑：`sure_time` 是引擎**事后**标注的确认时刻，
|
||||
不等于可执行时刻，用它当 entry 的回测 PF 虚高一倍以上。B4 正在跑真钱，
|
||||
必须过同一关。
|
||||
|
||||
**先验比一类好，但方向要说清**（§5.41 的代码审计）：
|
||||
|
||||
一类 `sure_time` 直接当**入场时刻** -> 早了就是虚高，回测被高估
|
||||
B4 `available_ts` 只是**扫描起点** -> 晚了只会漏信号，回测偏保守
|
||||
|
||||
§5.41 实测全量的 `available_ts` 系统性**更晚**（`bis[-1]` 取的是中枢结束而非
|
||||
形成，中位晚 62 分钟）。所以预期是「回测保守」而非「回测虚高」。但那是 300
|
||||
时点抽样 + 代码审计，不是逐根验证，而且留了个未知：
|
||||
**实盘会产出更多、更早的信号，那部分的质量不在回测统计里。**
|
||||
|
||||
本脚本逐根重放，同时量两边：
|
||||
|
||||
准时率 全量信号在其 entry_idx 当根就能算出来的比例
|
||||
迟到 首现晚于 entry_idx 的，实盘只能在更差的价位追
|
||||
额外信号 回放发得出、全量却没有的 —— §5.41 预言存在，但没人统计过它们赚不赚
|
||||
|
||||
⚠️ 性能：每根扫全部中枢跑不完。一个中枢只能在其 available_ts 之后 scan 根内
|
||||
出信号，所以每根只需把窗口内的中枢喂给 `find_fast_bsp3`。这是等价裁剪，
|
||||
不改变结果。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
import warnings
|
||||
from concurrent.futures import ProcessPoolExecutor, as_completed
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
warnings.filterwarnings("ignore")
|
||||
HERE = Path(__file__).resolve().parent
|
||||
sys.path.insert(0, str(HERE))
|
||||
sys.path.insert(0, str(HERE.parent))
|
||||
|
||||
OUT = HERE / "out" / "step63_b4_replay.feather"
|
||||
SL, SCALE_AT, RUNNER, RSTOP, MAXB = 2.0, 3.0, 8.0, 2.0, 48
|
||||
SCAN = 200
|
||||
|
||||
|
||||
def replay(sym: str, tf: str, rows: int, warm: int,
|
||||
steps: int) -> pd.DataFrame | None:
|
||||
from chanlun import TF_DF
|
||||
from chanlun.analysis.fast_bsp import (
|
||||
ensure_timestamp,
|
||||
find_fast_bsp3,
|
||||
zones_from_zs_list,
|
||||
)
|
||||
from lib.data import fetch_ohlcv
|
||||
|
||||
try:
|
||||
df = fetch_ohlcv(f"{sym}/USDT:USDT", tf, rows)
|
||||
if df is None or len(df) < warm + steps + 100:
|
||||
return None
|
||||
df = df.iloc[-(warm + steps):].reset_index(drop=True)
|
||||
|
||||
# ---- 全量口径：回测就是这么算的 ----
|
||||
full = TF_DF(df, 1, tf)
|
||||
cdf = ensure_timestamp(full.dataframe)
|
||||
zs_full = full.cal_bi_zs_list_pure(full.bi_list)
|
||||
if not zs_full:
|
||||
return None
|
||||
sig_full = find_fast_bsp3(cdf, zones_from_zs_list(zs_full, cdf))
|
||||
full_keys = {(int(r.entry_idx), int(r.direction))
|
||||
for r in sig_full.itertuples()} if not sig_full.empty \
|
||||
else set()
|
||||
|
||||
# ---- 回放口径：逐根重算 zones 再扫 ----
|
||||
chan = TF_DF(df.iloc[:warm].copy(), 1, tf)
|
||||
chan.init_stream(df.iloc[:warm].copy(), 1, tf)
|
||||
first_seen: dict[tuple, int] = {}
|
||||
for i in range(warm, len(df)):
|
||||
chan.append_bar(df.iloc[i])
|
||||
try:
|
||||
zl = chan.cal_bi_zs_list_pure(chan.bi_list)
|
||||
if not zl:
|
||||
continue
|
||||
sub = ensure_timestamp(chan.dataframe)
|
||||
z = zones_from_zs_list(zl, sub)
|
||||
if z.empty:
|
||||
continue
|
||||
# 等价裁剪：available_ts 早于 scan 根之前的中枢，其扫描窗口
|
||||
# 已经过去，不可能在本根产出新信号
|
||||
lo = sub["timestamp"].to_numpy()[max(0, len(sub) - SCAN - 2)]
|
||||
z = z[z.available_ts >= lo]
|
||||
if z.empty:
|
||||
continue
|
||||
s = find_fast_bsp3(sub, z, scan=SCAN)
|
||||
except Exception: # noqa: BLE001
|
||||
continue
|
||||
if s is None or s.empty:
|
||||
continue
|
||||
for r in s.itertuples():
|
||||
k = (int(r.entry_idx), int(r.direction))
|
||||
if k not in first_seen:
|
||||
first_seen[k] = i
|
||||
|
||||
rec = []
|
||||
for k in set(full_keys) | set(first_seen):
|
||||
e, d = k
|
||||
if e < warm: # 预热段不计入
|
||||
continue
|
||||
seen = first_seen.get(k)
|
||||
rec.append({
|
||||
"sym": sym, "tf": tf, "entry_idx": e, "direction": d,
|
||||
"in_full": k in full_keys, "in_replay": seen is not None,
|
||||
"i_seen": -1 if seen is None else seen,
|
||||
"late": (np.nan if seen is None else seen - e),
|
||||
})
|
||||
if not rec:
|
||||
return None
|
||||
r = pd.DataFrame(rec)
|
||||
|
||||
# 实盘真正会做的：首现根入场（首现==entry_idx 即准时）
|
||||
from lib.exit_model import cfg_name, walk_exits
|
||||
atr = cdf["atr"].to_numpy(float)
|
||||
cl = cdf["close"].to_numpy(float)
|
||||
n = len(cdf)
|
||||
cfg = cfg_name(SL, RUNNER, MAXB, RSTOP)
|
||||
live = r[r.in_replay & (r.i_seen < n - 2)].copy()
|
||||
live = live[np.isfinite(atr[live.i_seen.values])
|
||||
& (atr[live.i_seen.values] > 0)]
|
||||
if not live.empty:
|
||||
res = walk_exits(cdf, pd.DataFrame({
|
||||
"entry_idx": live.i_seen.values,
|
||||
"direction": live.direction.values}), [SL], [RUNNER], [MAXB],
|
||||
scale_at=SCALE_AT, runners=(RUNNER,), runner_stops=(RSTOP,))
|
||||
if len(res) == len(live):
|
||||
for c in ("g", "r", "c"):
|
||||
live[c] = res[f"{cfg}_{c}"].to_numpy()
|
||||
live["atr_pct"] = (atr[live.i_seen.values]
|
||||
/ cl[live.i_seen.values])
|
||||
r = r.merge(live[["entry_idx", "direction", "g", "r", "c",
|
||||
"atr_pct"]],
|
||||
on=["entry_idx", "direction"], how="left")
|
||||
return r
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f" {sym} {tf} 失败: {type(e).__name__}: {e}", flush=True)
|
||||
return None
|
||||
|
||||
|
||||
def perf(g: pd.DataFrame) -> dict:
|
||||
from lib.exit_model import fee_of, taker_notional
|
||||
net = g.g.values - fee_of(g.r.values, g.c.values)
|
||||
gR = g.g.values / (SL * g.atr_pct.values)
|
||||
R = net / (SL * g.atr_pct.values)
|
||||
tn = taker_notional(g.r.values, g.c.values)
|
||||
w, o = net[net > 0].sum(), -net[net <= 0].sum()
|
||||
return {
|
||||
"笔数": len(g), "胜率": f"{(net > 0).mean()*100:.1f}%",
|
||||
"毛R": round(gR.mean(), 3), "净均R": round(R.mean(), 3),
|
||||
"PF": round(w / o, 2) if o > 0 else np.inf,
|
||||
"余量bp": round(net.mean() / tn.mean() * 1e4, 2),
|
||||
"t值": round(gR.mean() / (gR.std(ddof=1) / np.sqrt(len(g))), 2),
|
||||
}
|
||||
|
||||
|
||||
def report(d: pd.DataFrame) -> None:
|
||||
print("\n" + "=" * 92)
|
||||
print("########## 一、准时率与额外信号 ##########")
|
||||
rows = []
|
||||
for tf, x in d.groupby("tf"):
|
||||
both = x[x.in_full & x.in_replay]
|
||||
rows.append({
|
||||
"tf": tf,
|
||||
"全量信号": int(x.in_full.sum()),
|
||||
"回放信号": int(x.in_replay.sum()),
|
||||
"召回": f"{len(both)/max(int(x.in_full.sum()),1)*100:.1f}%",
|
||||
"准时(首现==entry)": f"{(both.late == 0).mean()*100:.1f}%",
|
||||
"迟到中位": (f"{both.late[both.late > 0].median():.0f} 根"
|
||||
if (both.late > 0).any() else "—"),
|
||||
"额外信号": int((x.in_replay & ~x.in_full).sum()),
|
||||
})
|
||||
print(pd.DataFrame(rows).to_string(index=False))
|
||||
print("\n额外信号 = 回放发得出、全量没有的。§5.41 预言它们存在"
|
||||
"（实盘 available_ts 更早 -> 信号更多更早），本表给出数量。")
|
||||
|
||||
if "g" not in d.columns:
|
||||
return
|
||||
print("\n" + "=" * 92)
|
||||
print("########## 二、分组收益：回测口径 vs 实盘口径 ##########")
|
||||
for tf, x in d.groupby("tf"):
|
||||
y = x.dropna(subset=["g"])
|
||||
if len(y) < 30:
|
||||
continue
|
||||
print(f"\n--- {tf} ---")
|
||||
rows = []
|
||||
for nm, g in [
|
||||
("全部回放信号（=实盘会做的）", y[y.in_replay]),
|
||||
("其中 准时的", y[y.in_replay & (y.late == 0)]),
|
||||
("其中 迟到的", y[y.in_replay & (y.late > 0)]),
|
||||
("其中 额外的（全量没有）", y[y.in_replay & ~y.in_full]),
|
||||
("回测口径（全量∩回放）", y[y.in_full & y.in_replay]),
|
||||
]:
|
||||
if len(g) >= 30:
|
||||
rows.append({"分组": nm, **perf(g)})
|
||||
print(pd.DataFrame(rows).to_string(index=False))
|
||||
print("\n判读：若「全部回放信号」的 PF 不低于「回测口径」，说明 B4 的时点"
|
||||
"是干净的，\n且 §5.41 说的『回测偏保守』成立 —— 实盘拿到的反而更多。"
|
||||
"\n若额外信号那组显著更差，那就是回测没统计到的隐性成本。")
|
||||
|
||||
|
||||
def main() -> None:
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--symbols", default="BTC,ETH,SOL,LINK,DOGE")
|
||||
ap.add_argument("--tf", default="5m")
|
||||
ap.add_argument("--rows", type=int, default=45_000)
|
||||
ap.add_argument("--warm", type=int, default=20_000)
|
||||
ap.add_argument("--steps", type=int, default=20_000)
|
||||
ap.add_argument("--workers", type=int, default=5)
|
||||
ap.add_argument("--reuse", action="store_true")
|
||||
args = ap.parse_args()
|
||||
|
||||
if args.reuse and OUT.exists():
|
||||
report(pd.read_feather(OUT))
|
||||
return
|
||||
syms = [s.strip() for s in args.symbols.split(",")]
|
||||
print(f"[B4 因果回放] {len(syms)} 币 × {args.steps} 根逐根重放\n", flush=True)
|
||||
parts = []
|
||||
with ProcessPoolExecutor(max_workers=args.workers) as ex:
|
||||
fut = {ex.submit(replay, s, args.tf, args.rows, args.warm,
|
||||
args.steps): s for s in syms}
|
||||
for i, f in enumerate(as_completed(fut), 1):
|
||||
r = f.result()
|
||||
print(f" [{i}/{len(syms)}] {fut[f]} "
|
||||
f"{0 if r is None else len(r)} 个信号", flush=True)
|
||||
if r is not None:
|
||||
parts.append(r)
|
||||
if not parts:
|
||||
print("无结果")
|
||||
return
|
||||
d = pd.concat(parts, ignore_index=True)
|
||||
OUT.parent.mkdir(exist_ok=True)
|
||||
d.to_feather(OUT)
|
||||
report(d)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user