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>
This commit is contained in:
jackyu66git
@@ -0,0 +1,185 @@
|
||||
"""Walk-forward 重放：用滑动窗口逐步重算缠论，检验买卖点在实时环境下是否稳定。
|
||||
|
||||
要回答三个问题：
|
||||
1. 幻影率——实时曾报出、但在完整历史上并不存在的信号占多少？
|
||||
2. 撤销率——报出后又被结构演化抹掉的信号占多少？
|
||||
3. 真实滞后——信号第一次可被观测到的时刻，比 sure_time 晚多少？
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import pickle
|
||||
import sys
|
||||
from concurrent.futures import ProcessPoolExecutor
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
|
||||
|
||||
from chanlun.core.ChanEnum import Chan_BSP_DIR
|
||||
|
||||
# 子进程共享的只读数据，避免每次任务重复 pickle 整个 DataFrame
|
||||
_G: dict = {}
|
||||
|
||||
BspKey = tuple[str, int, str] # (类型, 方向, 分型时间)
|
||||
|
||||
|
||||
def _init_worker(df: pd.DataFrame, tf: str, zs_source: str) -> None:
|
||||
_G["df"] = df
|
||||
_G["tf"] = tf
|
||||
_G["zs_source"] = zs_source
|
||||
|
||||
|
||||
def _bsp_keys_for_window(args: tuple[int, int]) -> tuple[int, list[BspKey]]:
|
||||
"""在 df[start:end] 这个窗口上重算缠论，返回该时点可观测到的买卖点集合。"""
|
||||
from chanlun import TF_DF # 延迟导入，避免父进程重复加载
|
||||
|
||||
start, end = args
|
||||
df = _G["df"].iloc[start:end].reset_index(drop=True)
|
||||
try:
|
||||
chan = TF_DF(df, 1, _G["tf"])
|
||||
if _G["zs_source"] == "pure":
|
||||
bi_zs_list = chan.cal_bi_zs_list_pure(chan.bi_list)
|
||||
else:
|
||||
bi_zs_list = chan.cal_bi_zs(chan.seg_list)
|
||||
bsp_list = chan.find_all_bsp(chan.bi_list, bi_zs_list) if bi_zs_list else []
|
||||
except Exception:
|
||||
return end - 1, []
|
||||
|
||||
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 bsp_list
|
||||
if b.is_sure and b.sure_time is not None
|
||||
]
|
||||
return end - 1, keys
|
||||
|
||||
|
||||
@dataclass
|
||||
class ReplayResult:
|
||||
observations: dict[int, set[BspKey]] # 每个重算时点 -> 当时可见的买卖点集合
|
||||
checkpoints: list[int]
|
||||
window: int
|
||||
step: int
|
||||
|
||||
|
||||
def replay(
|
||||
df: pd.DataFrame,
|
||||
tf: str,
|
||||
window: int = 3000,
|
||||
step: int = 6,
|
||||
workers: int | None = None,
|
||||
cache_key: str | None = None,
|
||||
zs_source: str = "seg",
|
||||
) -> ReplayResult:
|
||||
"""滑动窗口重放。窗口右端每 step 根前进一次，每次完整重算一遍缠论。
|
||||
|
||||
重放很贵（分钟级），cache_key 非空时把结果落盘复用。
|
||||
"""
|
||||
n = len(df)
|
||||
if n <= window:
|
||||
raise ValueError(f"数据长度 {n} 不足以支撑窗口 {window}")
|
||||
|
||||
cache_path = None
|
||||
if cache_key:
|
||||
cache_dir = Path(__file__).resolve().parents[1] / ".cache"
|
||||
cache_dir.mkdir(parents=True, exist_ok=True)
|
||||
cache_path = cache_dir / f"replay__{cache_key}__{zs_source}__w{window}_s{step}_n{n}.pkl"
|
||||
if cache_path.exists():
|
||||
with cache_path.open("rb") as fh:
|
||||
obs = pickle.load(fh)
|
||||
print(f" [cache] 命中重放缓存 {cache_path.name}")
|
||||
return ReplayResult(observations=obs, checkpoints=sorted(obs), window=window, step=step)
|
||||
|
||||
tasks = [(end - window, end) for end in range(window, n + 1, step)]
|
||||
workers = workers or max(1, (os.cpu_count() or 4) - 1)
|
||||
|
||||
observations: dict[int, set[BspKey]] = {}
|
||||
with ProcessPoolExecutor(
|
||||
max_workers=workers, initializer=_init_worker, initargs=(df, tf, zs_source)
|
||||
) as pool:
|
||||
for i, (bar_idx, keys) in enumerate(pool.map(_bsp_keys_for_window, tasks, chunksize=8)):
|
||||
observations[bar_idx] = set(keys)
|
||||
if (i + 1) % 500 == 0:
|
||||
print(f" ...{i + 1}/{len(tasks)} 窗口", flush=True)
|
||||
|
||||
if cache_path is not None:
|
||||
with cache_path.open("wb") as fh:
|
||||
pickle.dump(observations, fh)
|
||||
|
||||
return ReplayResult(observations=observations, checkpoints=sorted(observations), window=window, step=step)
|
||||
|
||||
|
||||
def analyze_stability(
|
||||
result: ReplayResult,
|
||||
final_keys: set[BspKey],
|
||||
df: pd.DataFrame,
|
||||
window: int,
|
||||
maturity_bars: int = 300,
|
||||
edge_buffer: int = 500,
|
||||
) -> pd.DataFrame:
|
||||
"""把重放结果整理成每个信号的生命周期：首次出现、最后可见、是否被撤销。
|
||||
|
||||
两处偏差必须剔除，否则统计会失真：
|
||||
- 左截断：分型早于第一个窗口起点的信号，其 first_seen 是假的，标记 truncated。
|
||||
- 右截断：临近重放末尾才出现的信号还没经历足够演化，谈不上"没被撤销"，标记 immature。
|
||||
"""
|
||||
checkpoints = result.checkpoints
|
||||
times = df["date"].dt.strftime("%Y-%m-%d %H:%M:%S").to_numpy()
|
||||
idx_of = {t: i for i, t in enumerate(times)}
|
||||
|
||||
first_seen: dict[BspKey, int] = {}
|
||||
last_seen: dict[BspKey, int] = {}
|
||||
seen_count: dict[BspKey, int] = {}
|
||||
for bar_idx in checkpoints:
|
||||
for key in result.observations[bar_idx]:
|
||||
first_seen.setdefault(key, bar_idx)
|
||||
last_seen[key] = bar_idx
|
||||
seen_count[key] = seen_count.get(key, 0) + 1
|
||||
|
||||
last_cp = checkpoints[-1]
|
||||
rows = []
|
||||
for key, first in first_seen.items():
|
||||
bsp_type, direction, fx_time = key
|
||||
fx_idx = idx_of.get(fx_time)
|
||||
|
||||
# 窗口是滑动的，信号的分型一旦滑出窗口左端就必然不可见。
|
||||
# 只在「信号仍被窗口覆盖」的检查点上评价持续性，否则会把正常的滑出误判成撤销。
|
||||
# 另需 edge_buffer：贴着窗口左端时缠论缺少前置K线构造包含关系，信号会因边界效应消失。
|
||||
if fx_idx is None:
|
||||
in_scope = [cp for cp in checkpoints if cp >= first]
|
||||
else:
|
||||
in_scope = [
|
||||
cp for cp in checkpoints
|
||||
if cp >= first and (cp - window) < (fx_idx - edge_buffer)
|
||||
]
|
||||
scope_end = in_scope[-1] if in_scope else first
|
||||
visible_in_scope = sum(1 for cp in in_scope if key in result.observations[cp])
|
||||
|
||||
rows.append(
|
||||
{
|
||||
"bsp_type": bsp_type,
|
||||
"direction": direction,
|
||||
"fx_time": fx_time,
|
||||
"fx_idx": fx_idx,
|
||||
"first_seen_idx": first,
|
||||
"first_seen_time": times[first],
|
||||
"last_seen_idx": last_seen[key],
|
||||
"observed_lag": (first - fx_idx) if fx_idx is not None else None,
|
||||
"scope_checkpoints": len(in_scope),
|
||||
"persist_ratio": visible_in_scope / len(in_scope) if in_scope else 0.0,
|
||||
"in_final": key in final_keys,
|
||||
# 在「仍被窗口覆盖」的最后一个检查点上是否还活着
|
||||
"alive_at_scope_end": key in result.observations.get(scope_end, set()),
|
||||
# 分型发生在首个窗口完全覆盖之后，first_seen 才是真实的
|
||||
"truncated": fx_idx is None or fx_idx < window,
|
||||
# 覆盖范围太短则谈不上"没被撤销"
|
||||
"immature": len(in_scope) < maturity_bars // max(result.step, 1),
|
||||
}
|
||||
)
|
||||
return pd.DataFrame(rows).sort_values("first_seen_idx").reset_index(drop=True)
|
||||
Reference in New Issue
Block a user