research: 极值点波动率(step61)，观察成立但既不解释滞后也不解释亏损
用户提出一二类长在极值点、该区域波动大、这可能是确认慢的原因。拆成三条 子命题分别测。 ① 成立：5m 上 B1 的 atr_z 中位 1.224、74% 高于基准，而所有笔端点的基准恰好 落在 50%（构造正确的旁证）。但二类是镜像——B2/S2 的 atr_z 中位 0.94~0.97、 仅四成高于基准，长在低波动区，因为它是首轮反转冲动之后的回抽。所以 「一二类都在极值点」对一类成立、对二类不成立。 ② 只沾边：corr(atr_z, lag_bars) 仅 +0.10，滞后中位在四个 atr_z 分档里是 8/7/8/9 根，几乎不动。滞后是结构性的，笔要等分型确认，与波动率基本无关。 ③ 回落属实但不是死因：入场后 48 根平均 ATR 是入场时的 0.896，目标确实按虚高 ATR 定、绝对价格高估约 10%。但一类只有 9.4% 走到 3ATR 减仓（三类 30.7%）， 81.3% 直接止损、超时仅 17.9%。若死因是目标够不着，超时占比该很高。所以一类 不是走不动，是入场后立刻反向——与 §3.397 的诊断一致。
This commit is contained in:
jackyu66git
@@ -0,0 +1,252 @@
|
||||
"""极值点的波动率：它是不是既拖慢了确认，又让目标够不着？
|
||||
|
||||
用户的观察：一二类买卖点长在极值点上，那个区域波动天然很大，这可能正是确认
|
||||
慢的原因。
|
||||
|
||||
这个假设若成立会同时解释两件事，而且机制不同：
|
||||
|
||||
确认慢 波动大 -> 分型/笔要更多根才稳定下来 -> sure_time 更晚
|
||||
赚不到 ATR 被造成极值的那根插针抬高 -> 止损 2×虚高ATR 其实宽松，
|
||||
但目标 3/8 ATR 变得够不着，因为入场后波动率会均值回复下来
|
||||
|
||||
第二条尤其要紧：它意味着交易不是「被打掉」，而是「永远走不到目标」，
|
||||
与 §3.397 判定的「趋势继续」是**不同的失败模式**，应对办法也不同
|
||||
（该换波动率口径，而不是换方向）。
|
||||
|
||||
三个量：
|
||||
atr_z 极值处 ATR / 该点之前 200 根的中位 ATR —— 是否真的偏高
|
||||
atr_fwd 入场后 48 根的平均 ATR / 入场时 ATR —— 是否均值回复
|
||||
与滞后相关 atr_z 高的信号，lag_bars 是否更长
|
||||
"""
|
||||
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" / "step61_vol.feather"
|
||||
SL, SCALE_AT, RUNNER, RSTOP, MAXB = 2.0, 3.0, 8.0, 2.0, 48
|
||||
BASE_WIN = 200
|
||||
|
||||
|
||||
def collect(sym: str, tf: str, rows: int) -> pd.DataFrame | None:
|
||||
from chanlun import TF_DF
|
||||
from chanlun.core.ChanEnum import Chan_BSP_TYPE
|
||||
from lib.data import fetch_ohlcv
|
||||
from lib.exit_model import cfg_name, walk_exits
|
||||
|
||||
try:
|
||||
df = fetch_ohlcv(f"{sym}/USDT:USDT", tf, rows)
|
||||
if df is None or len(df) < 5_000:
|
||||
return None
|
||||
chan = TF_DF(df, 1, tf, lean=False)
|
||||
cdf = chan.dataframe
|
||||
bz = chan.cal_bi_zs_list_pure(chan.bi_list)
|
||||
if not bz:
|
||||
return None
|
||||
bsp = chan.find_all_bsp(chan.bi_list, bz) or []
|
||||
|
||||
dser = pd.to_datetime(cdf["date"])
|
||||
if dser.dt.tz is not None:
|
||||
dser = dser.dt.tz_localize(None)
|
||||
didx = pd.DatetimeIndex(dser)
|
||||
n = len(cdf)
|
||||
|
||||
def to_i(ts) -> int:
|
||||
t = pd.Timestamp(ts)
|
||||
return int(didx.searchsorted(t.tz_localize(None) if t.tz else t))
|
||||
|
||||
atr = cdf["atr"].to_numpy(float)
|
||||
cl = cdf["close"].to_numpy(float)
|
||||
# 基准 ATR 只用**该点之前**的窗口，含当根会把要检验的那根插针算进去
|
||||
base = (pd.Series(atr).rolling(BASE_WIN, min_periods=50)
|
||||
.median().shift(1).to_numpy())
|
||||
|
||||
rec = []
|
||||
# 对照组：所有笔端点，与 §3.397 同源
|
||||
for bi in chan.bi_list:
|
||||
if not getattr(bi, "is_sure", False) or bi.end_klc is None:
|
||||
continue
|
||||
i = to_i(bi.end_klc.end_time)
|
||||
if not (0 <= i < n) or not np.isfinite(base[i]) or base[i] <= 0:
|
||||
continue
|
||||
rec.append({"kind": "笔端点", "dir": 0, "i_ext": i, "i_sure": -1,
|
||||
"atr_z": atr[i] / base[i], "lag_bars": -1})
|
||||
|
||||
want = {Chan_BSP_TYPE.B1: ("B1", 1), Chan_BSP_TYPE.S1: ("S1", -1),
|
||||
Chan_BSP_TYPE.B2: ("B2", 1), Chan_BSP_TYPE.S2: ("S2", -1),
|
||||
Chan_BSP_TYPE.B3: ("B3", 1), Chan_BSP_TYPE.S3: ("S3", -1)}
|
||||
for b in bsp:
|
||||
tag = want.get(b.type)
|
||||
if tag is None or b.sure_time is None:
|
||||
continue
|
||||
name, d = tag
|
||||
i_ext, i_sure = to_i(b.klc.end_time), to_i(b.sure_time)
|
||||
if not (0 <= i_ext < n and 0 <= i_sure < n):
|
||||
continue
|
||||
if not np.isfinite(base[i_ext]) or base[i_ext] <= 0:
|
||||
continue
|
||||
rec.append({"kind": name, "dir": d, "i_ext": i_ext,
|
||||
"i_sure": i_sure, "atr_z": atr[i_ext] / base[i_ext],
|
||||
"lag_bars": i_sure - i_ext})
|
||||
|
||||
r = pd.DataFrame(rec)
|
||||
# 入场后的实现波动率：目标够不够得着，取决于入场**之后**的 ATR
|
||||
ok = r.i_sure >= 0
|
||||
fwd = np.full(len(r), np.nan)
|
||||
for k, i in zip(np.where(ok)[0], r.i_sure[ok].values):
|
||||
j = min(int(i) + 1 + MAXB, n)
|
||||
if j > int(i) + 1 and atr[int(i)] > 0:
|
||||
fwd[k] = np.nanmean(atr[int(i) + 1:j]) / atr[int(i)]
|
||||
r["atr_fwd"] = fwd
|
||||
|
||||
sig = r[ok & (r.i_sure < n - 2)].copy()
|
||||
sig = sig[np.isfinite(atr[sig.i_sure.values])
|
||||
& (atr[sig.i_sure.values] > 0)]
|
||||
if not sig.empty:
|
||||
cfg = cfg_name(SL, RUNNER, MAXB, RSTOP)
|
||||
res = walk_exits(cdf, pd.DataFrame({
|
||||
"entry_idx": sig.i_sure.values,
|
||||
"direction": sig.dir.values}), [SL], [RUNNER], [MAXB],
|
||||
scale_at=SCALE_AT, runners=(RUNNER,), runner_stops=(RSTOP,))
|
||||
if len(res) == len(sig):
|
||||
for c in ("g", "r", "c", "b"):
|
||||
sig[c] = res[f"{cfg}_{c}"].to_numpy()
|
||||
sig["atr_pct"] = (atr[sig.i_sure.values]
|
||||
/ cl[sig.i_sure.values])
|
||||
r = r.merge(sig[["i_ext", "kind", "g", "r", "c", "b",
|
||||
"atr_pct"]], on=["i_ext", "kind"], how="left")
|
||||
r["sym"], r["tf"] = sym, tf
|
||||
return r
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f" {sym} {tf} 失败: {type(e).__name__}: {e}", flush=True)
|
||||
return None
|
||||
|
||||
|
||||
def report(d: pd.DataFrame) -> None:
|
||||
from lib.exit_model import fee_of, taker_notional
|
||||
|
||||
for tf, x in d.groupby("tf"):
|
||||
print("\n" + "#" * 96)
|
||||
print(f"########## {tf} · 极值点的波动率 ##########")
|
||||
|
||||
print("\n【一】极值处 ATR 是不是真的偏高（atr_z = 当点ATR / 前200根中位ATR）")
|
||||
rows = []
|
||||
for kind in ["笔端点", "B1", "S1", "B2", "S2", "B3", "S3"]:
|
||||
g = x[x.kind == kind]
|
||||
if len(g) < 30:
|
||||
continue
|
||||
rows.append({
|
||||
"信号": kind, "样本": len(g),
|
||||
"atr_z中位": round(g.atr_z.median(), 3),
|
||||
"P75": round(g.atr_z.quantile(.75), 3),
|
||||
"P90": round(g.atr_z.quantile(.90), 3),
|
||||
"高于基准占比": f"{(g.atr_z > 1).mean()*100:.0f}%",
|
||||
})
|
||||
print(pd.DataFrame(rows).to_string(index=False))
|
||||
|
||||
print("\n【二】波动大是不是确认更慢（按 atr_z 四分位看 lag_bars）")
|
||||
y = x[x.kind.isin(["B1", "S1"]) & (x.lag_bars >= 0)].copy()
|
||||
if len(y) >= 100:
|
||||
q = pd.qcut(y.atr_z, 4, labels=["Q1低", "Q2", "Q3", "Q4高"],
|
||||
duplicates="drop")
|
||||
print(pd.DataFrame([{
|
||||
"atr_z档": k, "笔数": len(g),
|
||||
"atr_z中位": round(g.atr_z.median(), 2),
|
||||
"滞后中位": round(g.lag_bars.median(), 1),
|
||||
"滞后均值": round(g.lag_bars.mean(), 1),
|
||||
} for k, g in y.groupby(q, observed=True)]).to_string(index=False))
|
||||
c = np.corrcoef(y.atr_z, y.lag_bars)[0, 1]
|
||||
print(f" 相关系数 corr(atr_z, lag_bars) = {c:+.3f}")
|
||||
print(" 正相关支持「波动大 -> 确认慢」；接近 0 则该假设不成立。")
|
||||
|
||||
print("\n【三】入场后波动率是否回落（atr_fwd = 后48根平均ATR / 入场ATR）")
|
||||
rows = []
|
||||
for kind in ["B1", "S1", "B3", "S3"]:
|
||||
g = x[(x.kind == kind)].dropna(subset=["atr_fwd"])
|
||||
if len(g) < 30:
|
||||
continue
|
||||
rows.append({
|
||||
"信号": kind, "样本": len(g),
|
||||
"atr_fwd中位": round(g.atr_fwd.median(), 3),
|
||||
"回落占比(<1)": f"{(g.atr_fwd < 1).mean()*100:.0f}%",
|
||||
})
|
||||
print(pd.DataFrame(rows).to_string(index=False))
|
||||
print(" <1 = 入场后波动率比入场那刻低，则按入场ATR定的 3/8 ATR 目标"
|
||||
"\n 在绝对价格上被高估，会系统性够不着。")
|
||||
|
||||
if "g" not in x.columns:
|
||||
continue
|
||||
print("\n【四】目标够不着的证据：出场原因分布（一类，按原方向）")
|
||||
z = x[x.kind.isin(["B1", "S1"])].dropna(subset=["g"])
|
||||
if len(z) >= 60:
|
||||
print((z.r.value_counts(normalize=True) * 100).round(1)
|
||||
.to_frame("占比%").to_string())
|
||||
print(f" 中位持仓 {z.b.median():.0f} 根 / 上限 {MAXB} 根")
|
||||
|
||||
print("\n【五】按 atr_z 分档看一类表现（原方向）")
|
||||
q = pd.qcut(z.atr_z, 4, labels=["Q1低", "Q2", "Q3", "Q4高"],
|
||||
duplicates="drop")
|
||||
rows = []
|
||||
for k, g in z.groupby(q, observed=True):
|
||||
net = g.g.values - fee_of(g.r.values, g.c.values)
|
||||
gR = g.g.values / (SL * g.atr_pct.values)
|
||||
tn = taker_notional(g.r.values, g.c.values)
|
||||
w, o = net[net > 0].sum(), -net[net <= 0].sum()
|
||||
rows.append({
|
||||
"atr_z档": k, "笔数": len(g),
|
||||
"atr_z中位": round(g.atr_z.median(), 2),
|
||||
"胜率": f"{(net > 0).mean()*100:.1f}%",
|
||||
"毛R": round(gR.mean(), 3),
|
||||
"PF": round(w / o, 2) if o > 0 else np.inf,
|
||||
"余量bp": round(net.mean() / tn.mean() * 1e4, 2),
|
||||
})
|
||||
print(pd.DataFrame(rows).to_string(index=False))
|
||||
|
||||
|
||||
def main() -> None:
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--symbols", default="BTC,ETH,SOL,LINK,DOGE")
|
||||
ap.add_argument("--tfs", default="5m,15m")
|
||||
ap.add_argument("--rows", type=int, default=200_000)
|
||||
ap.add_argument("--workers", type=int, default=3)
|
||||
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(",")]
|
||||
tfs = [t.strip() for t in args.tfs.split(",")]
|
||||
parts = []
|
||||
with ProcessPoolExecutor(max_workers=args.workers) as ex:
|
||||
fut = {ex.submit(collect, s, t, args.rows): (s, t)
|
||||
for s in syms for t in tfs}
|
||||
for i, f in enumerate(as_completed(fut), 1):
|
||||
r = f.result()
|
||||
s, t = fut[f]
|
||||
print(f" [{i}/{len(fut)}] {s} {t} "
|
||||
f"{0 if r is None else len(r)}", 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