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 +1,205 @@
+"""Step 19：区间套在不同级别对上的一致性。
+
+15m/1h+4h 只有 57 笔核心样本，无法定论。但区间套是级别无关的结构，
+把整套上移一级（1h 小级别有 2524 天，是 15m 的两倍）既能扩样本，
+又能验证它究竟是普适结构还是只在某一个级别对上凑巧成立。
+
+级别对：
+  5m  / 15m + 1h
+  15m / 1h  + 4h     （step16~17 已测）
+  1h  / 4h  + 1d
+"""
+from __future__ import annotations
+
+import argparse
+import sys
+import warnings
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+
+warnings.filterwarnings("ignore")
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+
+from lib.breakout import run_trades, summarize_trades
+from lib.data import fetch_ohlcv
+from lib.fast_bsp3 import find_fast_bsp3
+from lib.fx_signal import extract_fx_signals, signals_to_frame
+from lib.nested_bsp import attach_htf_context, htf_fx_timeline
+from lib.nested_level import build_htf_zones
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+from chanlun import TF_DF
+
+pd.set_option("display.width", 260)
+
+SYMBOLS = ["BTC/USDT:USDT", "ETH/USDT:USDT", "SOL/USDT:USDT"]
+DEFAULT_PAIRS = "5m:15m:1h,15m:1h:4h,1h:4h:1d"
+SL, TP, MAXB = 1.5, 3.0, 48
+
+
+def E(g):
+    return list(zip(g["entry_idx"].astype(int), g["direction"].astype(int)))
+
+
+# 同一 (品种, 周期) 的 pipeline 在多个级别对之间反复出现，缓存后能省掉大部分耗时
+_engine_cache: dict = {}
+_timeline_cache: dict = {}
+
+
+def _engine(symbol: str, tf: str, min_rows: int):
+    key = (symbol, tf)
+    if key not in _engine_cache:
+        try:
+            df = fetch_ohlcv(symbol, tf, 10**9)
+        except Exception:
+            df = None
+        if df is None or len(df) < min_rows:
+            _engine_cache[key] = None
+        else:
+            _engine_cache[key] = TF_DF(df, 1, tf)
+    return _engine_cache[key]
+
+
+def _timeline(symbol: str, tf: str):
+    key = (symbol, tf)
+    if key not in _timeline_cache:
+        chan = _engine(symbol, tf, 300)
+        if chan is None:
+            _timeline_cache[key] = None
+        else:
+            s = signals_to_frame(extract_fx_signals(chan, chan.dataframe))
+            _timeline_cache[key] = htf_fx_timeline(s, chan.dataframe)
+    return _timeline_cache[key]
+
+
+def build(symbol: str, ltf: str, htf1: str, htf2: str):
+    chan_l = _engine(symbol, ltf, 3000)
+    if chan_l is None:
+        return None, None
+    cdf_l = chan_l.dataframe
+    sig = find_fast_bsp3(cdf_l, build_htf_zones(cdf_l, ltf, chan=chan_l))
+    if sig.empty:
+        return cdf_l, None
+    for tf, pref in ((htf1, "h1"), (htf2, "h2")):
+        tl = _timeline(symbol, tf)
+        if tl is None or tl.empty:
+            continue
+        sig = attach_htf_context(sig, cdf_l, tl, pref)
+    return cdf_l, sig
+
+
+def main() -> None:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--core-only", action="store_true",
+                    help="只输出核心组合（大级别同向 + 浅回抽）")
+    ap.add_argument("--pairs", default=DEFAULT_PAIRS,
+                    help="级别对，格式 小级别:大级别1:大级别2，逗号分隔")
+    ap.add_argument("--symbols", default="BTC,ETH,SOL")
+    args = ap.parse_args()
+
+    global SYMBOLS
+    SYMBOLS = [f"{s.strip()}/USDT:USDT" for s in args.symbols.split(",") if s.strip()]
+    pairs = [tuple(p.split(":")) for p in args.pairs.split(",") if p]
+
+    all_rows, pool = [], []
+    for ltf, h1, h2 in pairs:
+        print(f"\n{'=' * 100}")
+        print(f"级别对：小级别 {ltf}   大级别 {h1} + {h2}")
+        rows = []
+        pair_pool = []
+        for sym in SYMBOLS:
+            cdf, sig = build(sym, ltf, h1, h2)
+            if sig is None or sig.empty or len(sig) < 10:
+                continue
+            tr = run_trades(cdf, E(sig), SL, TP, MAXB)
+            if tr.empty:
+                continue
+            s = summarize_trades(tr, f"{sym.split('/')[0]:>4} 全部")
+            s["滞后"] = f"{sig['lag'].median():.0f}"
+            rows.append(s)
+            m = sig.set_index("entry_idx")
+            tr = tr.copy()
+            tr["symbol"] = sym.split("/")[0]
+            tr["pair"] = f"{ltf}/{h1}"
+            tr["date"] = cdf["date"].to_numpy()[tr["entry_idx"].to_numpy()]
+            tr["h1_agree"] = tr["entry_idx"].map(m["h1_agree"]) if "h1_agree" in m else np.nan
+            tr["depth"] = tr["entry_idx"].map(m["depth"])
+            pair_pool.append(tr)
+        if not pair_pool:
+            print("  样本不足")
+            continue
+        if rows and not args.core_only:
+            print(pd.DataFrame(rows).to_string(index=False))
+
+        pt = pd.concat(pair_pool, ignore_index=True)
+        pool.append(pt)
+        a1 = pt["h1_agree"] == 1
+        dq = pt["depth"].quantile(0.66)
+        core = pt[a1 & (pt["depth"] >= dq)]
+
+        sub = [summarize_trades(pt, f"{ltf} 全部")]
+        if len(pt[a1]) >= 20:
+            sub.append(summarize_trades(pt[a1], f"{ltf} +{h1}同向"))
+        if len(core) >= 15:
+            sub.append(summarize_trades(core, f"{ltf} 核心(同向+浅回抽)"))
+        if len(pt[~a1]) >= 15:
+            sub.append(summarize_trades(pt[~a1], f"{ltf} 反向(对照)"))
+        print(pd.DataFrame(sub).to_string(index=False))
+
+        if len(core) >= 15:
+            r = core["ret"].to_numpy()
+            all_rows.append({
+                "级别对": f"{ltf} / {h1}+{h2}", "核心笔数": len(r),
+                "胜率": f"{(r > 0).mean() * 100:.1f}%",
+                "均收益": f"{r.mean() * 100:+.3f}%",
+                "中位数": f"{np.median(r) * 100:+.3f}%",
+                "PF": f"{r[r > 0].sum() / abs(r[r <= 0].sum()):.2f}",
+                "偏度": f"{pd.Series(r).skew():.2f}",
+                "t值": f"{r.mean() / (r.std(ddof=1) / np.sqrt(len(r))):+.2f}",
+            })
+
+    print(f"\n{'=' * 100}")
+    print("########## 跨级别对：核心组合汇总 ##########")
+    if all_rows:
+        print(pd.DataFrame(all_rows).to_string(index=False))
+
+    if pool:
+        allp = pd.concat(pool, ignore_index=True)
+        a1 = allp["h1_agree"] == 1
+        cores = []
+        for p, g in allp.groupby("pair"):
+            dq = g["depth"].quantile(0.66)
+            cores.append(g[(g["h1_agree"] == 1) & (g["depth"] >= dq)])
+        core_all = pd.concat(cores, ignore_index=True)
+        r = core_all["ret"].to_numpy()
+        print(f"\n  三个级别对合并核心样本 {len(r)} 笔：")
+        print(f"    胜率 {(r > 0).mean() * 100:.1f}%   均收益 {r.mean() * 100:+.3f}%   "
+              f"中位数 {np.median(r) * 100:+.3f}%")
+        print(f"    PF {r[r > 0].sum() / abs(r[r <= 0].sum()):.2f}   "
+              f"偏度 {pd.Series(r).skew():.2f}   "
+              f"t值 {r.mean() / (r.std(ddof=1) / np.sqrt(len(r))):+.2f}")
+        for k in (2, 5, 10):
+            v = r[r <= np.quantile(r, 1 - k / 100)]
+            print(f"    剔除最赚{k:>2}%: PF {v[v > 0].sum() / abs(v[v <= 0].sum()):.2f}  "
+                  f"t {v.mean() / (v.std(ddof=1) / np.sqrt(len(v))):+.2f}  "
+                  f"中位 {np.median(v) * 100:+.3f}%")
+
+        core_all["year"] = pd.to_datetime(core_all["date"]).dt.year
+        print("\n  核心样本分年：")
+        rows = [{"年份": y, "笔数": len(g), "胜率": f"{(g.ret > 0).mean() * 100:.0f}%",
+                 "均收益": f"{g.ret.mean() * 100:+.3f}%",
+                 "PF": f"{g.ret[g.ret > 0].sum() / abs(g.ret[g.ret <= 0].sum()):.2f}"
+                 if (g.ret <= 0).any() else "inf"}
+                for y, g in core_all.groupby("year") if len(g) >= 8]
+        print(pd.DataFrame(rows).to_string(index=False))
+
+        out = Path(__file__).parent / "out" / "step19_level_pairs.csv"
+        out.parent.mkdir(exist_ok=True)
+        allp.to_csv(out, index=False)
+        print(f"\n明细已写入 {out}")
+
+
+if __name__ == "__main__":
+    main()