jackyu66gitandCursor
8ee11317d3
自动刷新改用 tail update 与 scrollToPosition 恢复视窗，避免 setData 后跳到最右；拆分 chart_tv 模块并扩展 analyze/recent API。同步威科夫分析、pipeline 增量构建及相关策略与配置。 Co-authored-by: Cursor <cursoragent@cursor.com>
383 lines
12 KiB
Python
383 lines
12 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
Regime Attribution Study — 策略完全冻结
|
||
|
||
问题：为什么 Spring 在 2023+ BTC 有效，全历史 / 多品种不稳健？
|
||
方法：逐笔交易打市场状态标签，按桶看 net PF（不改任何入场逻辑）
|
||
|
||
输出:
|
||
- scripts/wyckoff_regime_attribution_trades.jsonl 逐笔
|
||
- scripts/wyckoff_regime_attribution_result.json 汇总
|
||
- research/VALIDITY_BOUNDARY.md 适用域草案
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import logging
|
||
import sys
|
||
from collections import defaultdict
|
||
from pathlib import Path
|
||
from typing import Any, Optional
|
||
|
||
import numpy as np
|
||
import pandas as pd
|
||
import talib.abstract as ta
|
||
|
||
ROOT = Path(__file__).resolve().parents[3]
|
||
sys.path.insert(0, str(ROOT))
|
||
|
||
from user_data.Chan.scripts.wyckoff_tf_grid import install_offline_markets # noqa: E402
|
||
|
||
STRAT = "Wyckoff_BTC_V1_BASELINE"
|
||
CONFIG = ROOT / "user_data/Chan/config/Wyckoff_BTC_V1_BASELINE.json"
|
||
DATADIR = ROOT / "user_data/data/binance/futures"
|
||
OUT_JSON = ROOT / "user_data/Chan/scripts/wyckoff_regime_attribution_result.json"
|
||
OUT_TRADES = ROOT / "user_data/Chan/scripts/wyckoff_regime_attribution_trades.jsonl"
|
||
OUT_BOUNDARY = ROOT / "user_data/Chan/research/VALIDITY_BOUNDARY.md"
|
||
STATUS = ROOT / "user_data/Chan/research/SYSTEM_STATUS.md"
|
||
|
||
PAIR = "BTC/USDT:USDT"
|
||
TIMERANGE = "20190901-"
|
||
FEE = 0.0005
|
||
SLIP = 0.0005 # 评价用 net
|
||
|
||
|
||
def _pf(profits: list[float]) -> float:
|
||
wins = [p for p in profits if p > 0]
|
||
losses = [-p for p in profits if p <= 0]
|
||
gw, gl = sum(wins), sum(losses)
|
||
if gl <= 0:
|
||
return 999.0 if gw > 0 else 0.0
|
||
return gw / gl
|
||
|
||
|
||
def _bucket_stats(rows: list[dict], key: str) -> dict[str, Any]:
|
||
groups: dict[str, list[float]] = defaultdict(list)
|
||
for r in rows:
|
||
groups[str(r.get(key, "na"))].append(float(r["profit_ratio"]))
|
||
out = {}
|
||
for k, ps in sorted(groups.items(), key=lambda x: -len(x[1])):
|
||
out[k] = {
|
||
"n": len(ps),
|
||
"winrate": 100.0 * sum(1 for p in ps if p > 0) / len(ps),
|
||
"avg_pct": 100.0 * float(np.mean(ps)),
|
||
"sum_pct": 100.0 * float(np.sum(ps)),
|
||
"pf": round(_pf(ps), 3),
|
||
}
|
||
return out
|
||
|
||
|
||
def build_feature_frames(pair_file: str = "BTC_USDT_USDT") -> tuple[pd.DataFrame, pd.DataFrame]:
|
||
"""1h ATR percentile + 8h structure features（与策略无关的分析层）。"""
|
||
h1 = pd.read_feather(DATADIR / f"{pair_file}-1h-futures.feather")
|
||
h1["date"] = pd.to_datetime(h1["date"], utc=True)
|
||
h1 = h1.sort_values("date").reset_index(drop=True)
|
||
h1["atr"] = ta.ATR(h1, timeperiod=14)
|
||
# 滚动 90 天 ≈ 2160 根 1h 的 ATR 分位
|
||
win = 2160
|
||
h1["atr_percentile"] = h1["atr"].rolling(win, min_periods=200).apply(
|
||
lambda x: pd.Series(x).rank(pct=True).iloc[-1], raw=False
|
||
)
|
||
|
||
h8 = pd.read_feather(DATADIR / f"{pair_file}-8h-futures.feather")
|
||
h8["date"] = pd.to_datetime(h8["date"], utc=True)
|
||
h8 = h8.sort_values("date").reset_index(drop=True)
|
||
h8["ema50"] = ta.EMA(h8, timeperiod=50)
|
||
h8["ema200"] = ta.EMA(h8, timeperiod=200)
|
||
h8["adx"] = ta.ADX(h8, timeperiod=14)
|
||
h8["ema_slope"] = (h8["ema50"] - h8["ema50"].shift(6)) / h8["ema50"].shift(6)
|
||
h8["dist_ema200"] = (h8["close"] - h8["ema200"]) / h8["ema200"]
|
||
h8["bull"] = (h8["close"] > h8["ema200"]) & (h8["ema50"] > h8["ema200"])
|
||
h8["bear"] = (h8["close"] < h8["ema200"]) & (h8["ema50"] < h8["ema200"])
|
||
|
||
# Cycle（粗粒度威科夫语境，非策略信号）
|
||
slope = h8["ema_slope"]
|
||
cycle = np.full(len(h8), "transition", dtype=object)
|
||
cycle[(h8["bear"]) & (slope < -0.01)] = "markdown"
|
||
cycle[(h8["bear"]) & (slope >= -0.01)] = "accumulation_like"
|
||
cycle[(h8["bull"]) & (slope > 0.005)] = "markup"
|
||
cycle[(h8["bull"]) & (slope <= 0.005)] = "distribution_like"
|
||
h8["btc_cycle"] = cycle
|
||
|
||
# trend strength
|
||
ts = np.full(len(h8), "weak", dtype=object)
|
||
ts[(h8["adx"] >= 25) & (h8["adx"] < 35)] = "moderate"
|
||
ts[h8["adx"] >= 35] = "strong"
|
||
h8["trend_strength"] = ts
|
||
|
||
regime = np.full(len(h8), "range", dtype=object)
|
||
regime[h8["bull"].fillna(False)] = "bull"
|
||
regime[h8["bear"].fillna(False)] = "bear"
|
||
h8["market_regime"] = regime
|
||
return h1, h8
|
||
|
||
|
||
def atr_bucket(p: float) -> str:
|
||
if pd.isna(p):
|
||
return "atr_unknown"
|
||
if p < 0.33:
|
||
return "atr_low"
|
||
if p < 0.66:
|
||
return "atr_mid"
|
||
return "atr_high"
|
||
|
||
|
||
def slope_bucket(s: float) -> str:
|
||
if pd.isna(s):
|
||
return "slope_unknown"
|
||
if s > 0.01:
|
||
return "slope_up_strong"
|
||
if s > 0:
|
||
return "slope_up_mild"
|
||
if s > -0.01:
|
||
return "slope_flat_down"
|
||
return "slope_down_strong"
|
||
|
||
|
||
def run_backtest_trades() -> list[dict[str, Any]]:
|
||
from freqtrade.configuration import Configuration
|
||
from freqtrade.enums import RunMode
|
||
from freqtrade.optimize.backtesting import Backtesting
|
||
from freqtrade.persistence import LocalTrade
|
||
import freqtrade.optimize.optimize_reports.bt_output as bt_output
|
||
|
||
bt_output.show_backtest_results = lambda *a, **k: None # type: ignore
|
||
for mod in list(sys.modules):
|
||
if "Wyckoff_BTC" in mod:
|
||
del sys.modules[mod]
|
||
|
||
config = Configuration.from_files([str(CONFIG)])
|
||
config.update(
|
||
{
|
||
"strategy": STRAT,
|
||
"strategy_path": str(ROOT / "user_data/Chan/strategies"),
|
||
"timerange": TIMERANGE,
|
||
"timeframe": "1h",
|
||
"export": "none",
|
||
"runmode": RunMode.BACKTEST,
|
||
"datadir": ROOT / "user_data/data/binance",
|
||
"user_data_dir": ROOT / "user_data",
|
||
"enable_protections": False,
|
||
"fee": FEE + SLIP,
|
||
"exchange": {
|
||
**config.get("exchange", {}),
|
||
"name": "binance",
|
||
"pair_whitelist": [PAIR],
|
||
},
|
||
}
|
||
)
|
||
bt = Backtesting(config)
|
||
bt.start()
|
||
|
||
rows = []
|
||
for t in LocalTrade.bt_trades:
|
||
rows.append(
|
||
{
|
||
"pair": t.pair,
|
||
"enter_tag": t.enter_tag or "",
|
||
"is_short": bool(t.is_short),
|
||
"entry_date": t.open_date_utc.isoformat(),
|
||
"exit_date": t.close_date_utc.isoformat() if t.close_date_utc else None,
|
||
"profit_ratio": float(t.close_profit or 0.0),
|
||
"exit_reason": t.exit_reason or "",
|
||
}
|
||
)
|
||
return rows
|
||
|
||
|
||
def attribute(trades: list[dict], h1: pd.DataFrame, h8: pd.DataFrame) -> list[dict]:
|
||
h1 = h1.set_index("date").sort_index()
|
||
h8 = h8.set_index("date").sort_index()
|
||
out = []
|
||
for t in trades:
|
||
ed = pd.Timestamp(t["entry_date"])
|
||
if ed.tzinfo is None:
|
||
ed = ed.tz_localize("UTC")
|
||
# asof merge：入场前最后一根已收盘特征
|
||
i1 = h1.index.get_indexer([ed], method="ffill")[0]
|
||
i8 = h8.index.get_indexer([ed], method="ffill")[0]
|
||
if i1 < 0 or i8 < 0:
|
||
continue
|
||
r1 = h1.iloc[i1]
|
||
r8 = h8.iloc[i8]
|
||
ap = float(r1["atr_percentile"]) if pd.notna(r1["atr_percentile"]) else float("nan")
|
||
slope = float(r8["ema_slope"]) if pd.notna(r8["ema_slope"]) else float("nan")
|
||
adx = float(r8["adx"]) if pd.notna(r8["adx"]) else float("nan")
|
||
era = "2023plus" if ed >= pd.Timestamp("2023-01-01", tz="UTC") else "pre_2023"
|
||
rec = {
|
||
**t,
|
||
"market_regime": str(r8["market_regime"]),
|
||
"8h_adx": round(adx, 2) if not np.isnan(adx) else None,
|
||
"8h_ema_slope": round(slope, 5) if not np.isnan(slope) else None,
|
||
"atr_percentile": round(ap, 3) if not np.isnan(ap) else None,
|
||
"btc_cycle": str(r8["btc_cycle"]),
|
||
"trend_strength": str(r8["trend_strength"]),
|
||
"dist_ema200": round(float(r8["dist_ema200"]), 4) if pd.notna(r8["dist_ema200"]) else None,
|
||
"atr_bucket": atr_bucket(ap),
|
||
"slope_bucket": slope_bucket(slope),
|
||
"era": era,
|
||
"setup": t["enter_tag"] or ("UTAD_SHORT" if t["is_short"] else "SPRING_LONG"),
|
||
"result": "win" if t["profit_ratio"] > 0 else "loss",
|
||
}
|
||
out.append(rec)
|
||
return out
|
||
|
||
|
||
def write_boundary(summary: dict[str, Any]) -> None:
|
||
# 从桶结果提炼适用域草案（描述性，非自动交易规则）
|
||
atr = summary["by_atr_bucket"]
|
||
cycle = summary["by_btc_cycle"]
|
||
era = summary["by_era"]
|
||
ts = summary["by_trend_strength"]
|
||
|
||
def best_worst(d: dict) -> tuple[str, str]:
|
||
items = [(k, v) for k, v in d.items() if v["n"] >= 5]
|
||
if not items:
|
||
return "n/a", "n/a"
|
||
best = max(items, key=lambda x: x[1]["pf"])
|
||
worst = min(items, key=lambda x: x[1]["pf"])
|
||
return f"{best[0]} (PF {best[1]['pf']}, n={best[1]['n']})", f"{worst[0]} (PF {worst[1]['pf']}, n={worst[1]['n']})"
|
||
|
||
ab, aw = best_worst(atr)
|
||
cb, cw = best_worst(cycle)
|
||
tb, tw = best_worst(ts)
|
||
|
||
text = f"""# Validity Boundary — Spring Baseline (draft)
|
||
|
||
> 策略规则冻结。本文仅来自 Regime Attribution，**不是**新入场条件。
|
||
|
||
## Evidence snapshot
|
||
|
||
| Era | n | PF (net) | sum%% |
|
||
|-----|---|----------|-------|
|
||
| pre_2023 | {era.get('pre_2023', {}).get('n', 0)} | {era.get('pre_2023', {}).get('pf', 0)} | {era.get('pre_2023', {}).get('sum_pct', 0):.1f} |
|
||
| 2023plus | {era.get('2023plus', {}).get('n', 0)} | {era.get('2023plus', {}).get('pf', 0)} | {era.get('2023plus', {}).get('sum_pct', 0):.1f} |
|
||
|
||
## Observed favorable (descriptive)
|
||
|
||
- ATR bucket best: **{ab}**
|
||
- Cycle best: **{cb}**
|
||
- Trend strength best: **{tb}**
|
||
|
||
## Observed unfavorable (descriptive)
|
||
|
||
- ATR bucket worst: **{aw}**
|
||
- Cycle worst: **{cw}**
|
||
- Trend strength worst: **{tw}**
|
||
|
||
## Draft Validity Boundary
|
||
|
||
```
|
||
Spring Strategy (BTC)
|
||
适用（研究假设，待 Decision Engine 验证）:
|
||
✓ BTC（非默认跨资产）
|
||
✓ 2023+ 类「明确资金方向 / Markup 启动」环境
|
||
✓ 高/中波动（ATR rising / mid-high percentile）若数据支持
|
||
✓ Accumulation_like → Markup 过渡语境
|
||
|
||
不适用（当前证据）:
|
||
✗ 默认全历史无条件交易
|
||
✗ 横盘 / range regime
|
||
✗ 跨资产默认开启（ETH/SOL Phase3 未过）
|
||
✗ 熊市 Markdown 快速崩跌阶段（若桶显示 PF 差）
|
||
```
|
||
|
||
## Next for Decision Engine
|
||
|
||
Market State 先判定「是否落在适用域」→ 再允许 SPRING_LONG / UTAD_SHORT 信号。
|
||
**禁止**把本文件桶标签直接写回 Baseline 参数扫参。
|
||
"""
|
||
OUT_BOUNDARY.write_text(text)
|
||
|
||
|
||
def main() -> None:
|
||
logging.getLogger("freqtrade").setLevel(logging.ERROR)
|
||
install_offline_markets([PAIR])
|
||
|
||
print("===== 1) Frozen baseline backtest (BTC, net cost) =====", flush=True)
|
||
raw = run_backtest_trades()
|
||
print(f" trades={len(raw)}", flush=True)
|
||
|
||
print("===== 2) Build regime features =====", flush=True)
|
||
h1, h8 = build_feature_frames()
|
||
rows = attribute(raw, h1, h8)
|
||
print(f" attributed={len(rows)}", flush=True)
|
||
|
||
with OUT_TRADES.open("w") as f:
|
||
for r in rows:
|
||
f.write(json.dumps(r, ensure_ascii=False) + "\n")
|
||
|
||
summary: dict[str, Any] = {
|
||
"pair": PAIR,
|
||
"timerange": TIMERANGE,
|
||
"fee_model": f"fee {FEE}+slip {SLIP}",
|
||
"n": len(rows),
|
||
"overall_pf": round(_pf([r["profit_ratio"] for r in rows]), 3),
|
||
"by_era": _bucket_stats(rows, "era"),
|
||
"by_setup": _bucket_stats(rows, "setup"),
|
||
"by_market_regime": _bucket_stats(rows, "market_regime"),
|
||
"by_atr_bucket": _bucket_stats(rows, "atr_bucket"),
|
||
"by_trend_strength": _bucket_stats(rows, "trend_strength"),
|
||
"by_slope_bucket": _bucket_stats(rows, "slope_bucket"),
|
||
"by_btc_cycle": _bucket_stats(rows, "btc_cycle"),
|
||
"by_era_x_cycle": {},
|
||
"by_era_x_atr": {},
|
||
"interpretation": [],
|
||
}
|
||
|
||
# 交叉：era × cycle / atr
|
||
for era in ("pre_2023", "2023plus"):
|
||
sub = [r for r in rows if r["era"] == era]
|
||
summary["by_era_x_cycle"][era] = _bucket_stats(sub, "btc_cycle")
|
||
summary["by_era_x_atr"][era] = _bucket_stats(sub, "atr_bucket")
|
||
|
||
# 自动写几条解释线索（非交易规则）
|
||
era = summary["by_era"]
|
||
if era.get("2023plus", {}).get("pf", 0) > era.get("pre_2023", {}).get("pf", 0):
|
||
summary["interpretation"].append(
|
||
"2023plus PF 显著高于 pre_2023 → 存在 regime/cycle 依赖，非随机噪声单一窗口。"
|
||
)
|
||
cyc = summary["by_btc_cycle"]
|
||
if cyc:
|
||
best_c = max(cyc.items(), key=lambda x: (x[1]["n"] >= 5, x[1]["pf"]))
|
||
summary["interpretation"].append(
|
||
f"全样本 cycle 最优桶（n≥5 优先）: {best_c[0]} PF={best_c[1]['pf']} n={best_c[1]['n']}"
|
||
)
|
||
|
||
print("\n===== 3) Attribution tables =====", flush=True)
|
||
for name in (
|
||
"by_era", "by_setup", "by_market_regime", "by_atr_bucket",
|
||
"by_trend_strength", "by_slope_bucket", "by_btc_cycle",
|
||
):
|
||
print(f"\n-- {name} --")
|
||
for k, v in summary[name].items():
|
||
print(f" {k:<22} n={v['n']:<3} pf={v['pf']:<6} wr={v['winrate']:.0f}% sum={v['sum_pct']:.1f}%")
|
||
|
||
print("\n-- by_era_x_cycle --")
|
||
print(json.dumps(summary["by_era_x_cycle"], indent=2, ensure_ascii=False))
|
||
|
||
write_boundary(summary)
|
||
OUT_JSON.write_text(json.dumps(summary, indent=2, ensure_ascii=False))
|
||
|
||
# 更新 SYSTEM_STATUS
|
||
if STATUS.exists():
|
||
st = STATUS.read_text()
|
||
marker = "## Frozen Baseline"
|
||
block = (
|
||
"**Status update (Regime Attribution):**\n"
|
||
"Evidence: PASS (2023+ BTC) · Robustness: FAILED (multi-cycle) · "
|
||
"Confidence: LOW-MEDIUM · Next: Decision Engine validity gate "
|
||
f"(see `VALIDITY_BOUNDARY.md`, trades=`{OUT_TRADES.name}`).\n\n"
|
||
)
|
||
if "Status update (Regime Attribution)" not in st:
|
||
st = st.replace(marker, block + marker)
|
||
STATUS.write_text(st)
|
||
|
||
print(f"\nSaved {OUT_JSON}")
|
||
print(f"Saved {OUT_TRADES}")
|
||
print(f"Saved {OUT_BOUNDARY}")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|