refactor: 精简仓库为 chanlun 核心与 web 分析，移除威科夫与遗留模块

删除根目录旧 Chan 模块、策略、配置、文档及 wyckoff 相关代码；更新缠论 pipeline 与笔中枢计算；补充 research 研究与 web 测试。 Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-27 01:05:12 +08:00
parent 5c10e35b76
commit 7f393b93ed
360 changed files with 140008 additions and 41167 deletions
@@ -0,0 +1,169 @@
+"""Step 4：中枢来源 A/B —— cal_bi_zs(seg_list) vs cal_bi_zs_list_pure(bi_list)。
+
+假设：seg 口径下笔中枢必须等所属线段成形，多叠了一层确认滞后；
+pure 口径直接在扁平笔序列上滚动，应当显著更快出信号。
+用同一套 walk-forward 重放，只切换中枢来源，对比滞后与真实收益。
+"""
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+
+from lib.bsp_eval import baseline_stats, run_pipeline
+from lib.data import fetch_ohlcv
+from lib.walkforward import analyze_stability, replay
+
+pd.set_option("display.width", 240)
+
+from chanlun.core.ChanEnum import Chan_BSP_DIR
+
+HORIZONS = (1, 3, 5, 10, 20, 40)
+
+
+def evaluate(df: pd.DataFrame, tf: str, symbol: str, zs_source: str, window: int, step: int):
+    _, final_bsp = run_pipeline(df, tf, zs_source=zs_source)
+    final_keys = {
+        (str(b.type).replace("Chan_BSP_TYPE.", ""),
+         1 if b.dir == Chan_BSP_DIR.BUY else -1, str(b.end_time))
+        for b in final_bsp if b.is_sure and b.sure_time is not None
+    }
+    result = replay(
+        df, tf, window=window, step=step, zs_source=zs_source,
+        cache_key=f"{symbol.replace('/', '_').replace(':', '-')}_{tf}",
+    )
+    life = analyze_stability(result, final_keys, df, window=window)
+    valid = life[~life["truncated"]].dropna(subset=["fx_idx"]).copy()
+    valid["fx_idx"] = valid["fx_idx"].astype(int)
+    mature = valid[~valid["immature"]]
+    return final_keys, valid, mature
+
+
+def rt_returns(valid: pd.DataFrame, df: pd.DataFrame) -> pd.DataFrame:
+    """以实时首见时刻入场的方向调整收益。"""
+    closes = df["close"].to_numpy(dtype=float)
+    n = len(df)
+    rows = []
+    for _, r in valid.iterrows():
+        i, d = int(r["first_seen_idx"]), int(r["direction"])
+        row = {"bsp_type": r["bsp_type"], "direction": d}
+        for h in HORIZONS:
+            j = i + h
+            row[f"ret_{h}"] = d * (closes[j] - closes[i]) / closes[i] if j < n else np.nan
+        rows.append(row)
+    return pd.DataFrame(rows)
+
+
+def stats_block(fwd: pd.DataFrame, df: pd.DataFrame, mask=None, label="") -> list[dict]:
+    base = baseline_stats(df, HORIZONS).set_index("horizon")
+    g = fwd if mask is None else fwd[mask]
+    out = []
+    for h in HORIZONS:
+        r = g[f"ret_{h}"].dropna().to_numpy()
+        if len(r) == 0:
+            continue
+        dirs = g.loc[g[f"ret_{h}"].notna(), "direction"].to_numpy()
+        sd = r.std(ddof=1) if len(r) > 1 else np.nan
+        out.append({
+            "group": label, "horizon": h, "n": len(r), "mean": r.mean(),
+            "winrate": (r > 0).mean(),
+            "excess": r.mean() - float(np.mean(dirs) * base.loc[h, "base_mean_long"]),
+            "tstat": r.mean() / (sd / np.sqrt(len(r))) if sd else np.nan,
+        })
+    return out
+
+
+def fmt(rows: list[dict]) -> str:
+    d = pd.DataFrame(rows)
+    if d.empty:
+        return "(无数据)"
+    d["mean"] = d["mean"].map(lambda v: f"{v * 100:+.2f}%")
+    d["excess"] = d["excess"].map(lambda v: f"{v * 100:+.2f}%")
+    d["winrate"] = d["winrate"].map(lambda v: f"{v * 100:.0f}%")
+    d["tstat"] = d["tstat"].map(lambda v: f"{v:+.2f}")
+    return d.to_string(index=False)
+
+
+def main() -> None:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--symbol", default="BTC/USDT:USDT")
+    ap.add_argument("--tf", default="1h")
+    ap.add_argument("--window", type=int, default=3000)
+    ap.add_argument("--step", type=int, default=4)
+    args = ap.parse_args()
+
+    df = fetch_ohlcv(args.symbol, args.tf, 50000)
+    print(f"[data] {args.symbol} {args.tf} rows={len(df)} "
+          f"{df['date'].iloc[0]} -> {df['date'].iloc[-1]}\n")
+
+    store = {}
+    for src in ("seg", "pure"):
+        print(f"===== 中枢来源: {src} =====")
+        final_keys, valid, mature = evaluate(df, args.tf, args.symbol, src, args.window, args.step)
+        fwd = rt_returns(valid, df)
+        store[src] = (final_keys, valid, mature, fwd)
+        print(f"  全量口径买卖点 = {len(final_keys)}")
+        print(f"  重放有效信号   = {len(valid)}（已成熟 {len(mature)}）")
+        print(f"  实时首见滞后   = 中位数 {valid['observed_lag'].median():.0f} 根 / "
+              f"均值 {valid['observed_lag'].mean():.1f} 根")
+        print(f"  幻影率         = {(~mature['in_final']).mean() * 100:.1f}%")
+        print(f"  存活度         = {mature['persist_ratio'].mean():.3f}\n")
+
+    print("\n########## 滞后对比 ##########")
+    for src in ("seg", "pure"):
+        v = store[src][1]
+        q = v["observed_lag"].quantile([0.25, 0.5, 0.75])
+        print(f"  {src:5s}  P25={q[0.25]:5.0f}  中位数={q[0.5]:5.0f}  P75={q[0.75]:5.0f}  n={len(v)}")
+
+    print("\n########## 分类型滞后中位数 ##########")
+    comp = pd.DataFrame({
+        src: store[src][1].groupby("bsp_type")["observed_lag"].median()
+        for src in ("seg", "pure")
+    })
+    comp["改善(根)"] = comp["seg"] - comp["pure"]
+    print(comp.to_string())
+
+    print("\n########## 分类型信号数量与幻影率 ##########")
+    cnt = pd.DataFrame({
+        f"{src}_n": store[src][1].groupby("bsp_type").size() for src in ("seg", "pure")
+    })
+    ph = pd.DataFrame({
+        f"{src}_幻影": store[src][2].groupby("bsp_type")["in_final"].apply(lambda s: (1 - s.mean()) * 100)
+        for src in ("seg", "pure")
+    })
+    print(pd.concat([cnt, ph], axis=1).round(1).to_string())
+
+    print("\n########## 无未来函数收益：全部信号 ##########")
+    for src in ("seg", "pure"):
+        print(f"--- {src} ---")
+        print(fmt(stats_block(store[src][3], df, None, "ALL")))
+
+    print("\n########## 无未来函数收益：仅做多 ##########")
+    for src in ("seg", "pure"):
+        fwd = store[src][3]
+        print(f"--- {src} ---")
+        print(fmt(stats_block(fwd, df, fwd.direction == 1, "LONG")))
+
+    print("\n########## 无未来函数收益：仅做空 ##########")
+    for src in ("seg", "pure"):
+        fwd = store[src][3]
+        print(f"--- {src} ---")
+        print(fmt(stats_block(fwd, df, fwd.direction == -1, "SHORT")))
+
+    print("\n########## pure 口径分类型（持有 5 / 20 根）##########")
+    fwd = store["pure"][3]
+    rows = []
+    for t in sorted(fwd["bsp_type"].unique()):
+        rows += stats_block(fwd, df, fwd.bsp_type == t, t)
+    d = pd.DataFrame(rows)
+    d = d[d["horizon"].isin([5, 20])]
+    print(fmt(d.to_dict("records")))
+
+
+if __name__ == "__main__":
+    main()