204 lines
9.2 KiB
Python
204 lines
9.2 KiB
Python
"""得分口径对比器（score_lab，纯只读）——三套排序口径对未来收益，用数据收口权重之争。
|
||
|
||
背景（2026-08-17 用户拍板）：选层撤掉主题限额之后，排序完全由总分决定，
|
||
"哪种加权更合理"不再靠感觉定。本工具对每个历史档位日，用三套口径各生成
|
||
一份主榜前 N 名单，对齐之后 5、10、20 个交易日的真实收益，输出逐日明细与汇总。
|
||
|
||
三套口径：
|
||
A 现行词典序 t_factor_akg_score 降序（先档后分已编码在分值里，强弱档按当日中位切）
|
||
B 绝对档界 同样先档后分，但强弱传导改为绝对判据：传导分 >= strong_min 记强档，
|
||
0 < 传导分 < strong_min 记弱档（组内分沿用 A 里已编码的那份，只重排档）
|
||
C 连续加权 不分档：w1·z(log1p 传导) + w2·z(upside) + w3·z(−热度)，仅主榜票参赛
|
||
基准：主榜（gate=2）全体等权——选层不做任何排序时的底线，跑不赢它的口径直接出局。
|
||
|
||
读数怎么看：mean 是名单等权买入持有 k 个交易日的平均收益，hit 是上涨占比，
|
||
excess 是相对基准的超额。样本告知：传导史 2026-07 起、每天只多一个样本点，
|
||
头一两个月只看方向、不下死结论。
|
||
|
||
跑法【桥机 factorevaluation · ~/akg-factor-bridge】：
|
||
docker compose exec -T akg-factor-bridge python score_lab.py
|
||
docker compose exec -T akg-factor-bridge python score_lab.py --top 30 --horizons 5,10,20 \
|
||
--strong-min 1.0 --weights 0.5,0.3,0.2
|
||
产出：data/score_lab/对比_<起>_<止>.csv（逐日×口径×期限一行）+ 终端汇总表。
|
||
纯只读：因子表与行情表全部 SELECT，不写任何库；产物只落容器内 data/ 目录。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import os
|
||
|
||
import numpy as np
|
||
import pandas as pd
|
||
|
||
import common
|
||
import db
|
||
import factors
|
||
|
||
|
||
def _factor_map(table: str, ds: str) -> pd.Series:
|
||
df = db.read_mysql("factor", f"SELECT stock_code, factor_value FROM {table} "
|
||
f"WHERE trade_date=%s", (ds,))
|
||
if df.empty:
|
||
return pd.Series(dtype=float)
|
||
return df.set_index("stock_code")["factor_value"].astype(float)
|
||
|
||
|
||
def _score_dates(start=None, end=None) -> list[str]:
|
||
df = db.read_mysql("factor", "SELECT DISTINCT trade_date FROM t_factor_akg_score "
|
||
"ORDER BY trade_date")
|
||
out = [pd.Timestamp(x).date().isoformat() for x in df["trade_date"]]
|
||
if start:
|
||
out = [d for d in out if d >= start]
|
||
if end:
|
||
out = [d for d in out if d <= end]
|
||
return out
|
||
|
||
|
||
def _price_panel(start: str, end_plus: str):
|
||
"""(交易日历, {(date, code): close})。行情取到 end 之后一段，好算前瞻收益。"""
|
||
px = factors._read_gp_price(start, end_plus) # noqa: SLF001 —— 同仓自用, 口径不分叉
|
||
if px.empty:
|
||
raise SystemExit("gp_day_data 在该区间没有行情——先确认行情库连通。")
|
||
px = px.dropna(subset=["close"])
|
||
px["k"] = px["ts_code"].map(lambda s: common.to_prefix(str(s).strip().upper()))
|
||
px["d"] = px["trade_date"].map(lambda x: pd.Timestamp(x).date().isoformat())
|
||
cal = sorted(px["d"].unique())
|
||
close = {(r.d, r.k): float(r.close) for r in px.itertuples()}
|
||
return cal, close
|
||
|
||
|
||
def _tier_from_score(sc: float) -> float:
|
||
"""A 口径分值里编码的档位（200+档×20+组内分, 组内分夹 ±9.9）。"""
|
||
return float(max(0, min(2, int((sc - 190.0) // 20))))
|
||
|
||
|
||
def _rank_a(score: pd.Series) -> list[str]:
|
||
main = score[score >= 150.0].sort_values(ascending=False)
|
||
return list(main.index)
|
||
|
||
|
||
def _rank_b(score: pd.Series, trans: pd.Series, strong_min: float) -> list[str]:
|
||
"""绝对档界：组内分沿用 A（从分值反解），档位按传导分绝对阈值重记。"""
|
||
main = score[score >= 150.0]
|
||
if main.empty:
|
||
return []
|
||
rows = []
|
||
for k, sc in main.items():
|
||
inner = float(sc) - (200.0 + _tier_from_score(float(sc)) * 20.0)
|
||
st = float(trans.get(k) or 0.0)
|
||
tier = 2.0 if st >= strong_min else (1.0 if st > 0 else 0.0)
|
||
rows.append((k, 200.0 + tier * 20.0 + inner))
|
||
rows.sort(key=lambda x: -x[1])
|
||
return [k for k, _ in rows]
|
||
|
||
|
||
def _rank_c(score: pd.Series, trans: pd.Series, upside: pd.Series, heat: pd.Series,
|
||
w: tuple) -> list[str]:
|
||
"""连续加权：仅主榜票参赛；缺失处置同 build_score（传导缺=0，热度缺=中位数）。"""
|
||
main = score[score >= 150.0]
|
||
if main.empty:
|
||
return []
|
||
idx = main.index
|
||
t = np.log1p(pd.Series({k: float(trans.get(k) or 0.0) for k in idx}))
|
||
u = pd.Series({k: upside.get(k) for k in idx}, dtype=float)
|
||
h = pd.Series({k: heat.get(k) for k in idx}, dtype=float)
|
||
h = h.fillna(h.median())
|
||
u = u.fillna(0.0)
|
||
z = factors._robust_z # noqa: SLF001 —— 与生产打分同一把尺子
|
||
comp = w[0] * z(t) + w[1] * z(u) + w[2] * (-z(h))
|
||
return list(comp.sort_values(ascending=False).index)
|
||
|
||
|
||
def _fwd(cal: list, close: dict, d: str, codes: list, k: int):
|
||
"""名单在 d 买入、持有 k 个交易日的逐票收益（两头都要有价，缺价的票跳过）。"""
|
||
try:
|
||
i = cal.index(d)
|
||
except ValueError:
|
||
return []
|
||
if i + k >= len(cal):
|
||
return []
|
||
dt = cal[i + k]
|
||
out = []
|
||
for c in codes:
|
||
p0, p1 = close.get((d, c)), close.get((dt, c))
|
||
if p0 and p1 and p0 > 0:
|
||
out.append(p1 / p0 - 1.0)
|
||
return out
|
||
|
||
|
||
def main() -> int:
|
||
ap = argparse.ArgumentParser(description="得分口径对比器（只读）")
|
||
ap.add_argument("--top", type=int, default=30, help="每套口径取主榜前几只（默认 30）")
|
||
ap.add_argument("--horizons", default="5,10,20", help="前瞻交易日数，逗号分隔")
|
||
ap.add_argument("--strong-min", type=float, default=1.0,
|
||
help="B 口径的强传导绝对阈值（传导分 = 源数×(1−已动比例)）")
|
||
ap.add_argument("--weights", default="0.5,0.3,0.2",
|
||
help="C 口径权重 传导,upside,−热度")
|
||
ap.add_argument("--start")
|
||
ap.add_argument("--end")
|
||
a = ap.parse_args()
|
||
horizons = sorted({int(x) for x in a.horizons.split(",") if x.strip()})
|
||
w = tuple(float(x) for x in a.weights.split(","))
|
||
if len(w) != 3:
|
||
raise SystemExit("--weights 需要三个数，如 0.5,0.3,0.2")
|
||
|
||
dates = _score_dates(a.start, a.end)
|
||
if not dates:
|
||
raise SystemExit("t_factor_akg_score 在该区间没有数据。")
|
||
end_plus = (pd.Timestamp(dates[-1]) + pd.Timedelta(days=int(max(horizons) * 2.2 + 14))
|
||
).date().isoformat()
|
||
print(f"档位日 {dates[0]} ~ {dates[-1]} 共 {len(dates)} 天；"
|
||
f"前瞻 {horizons} 交易日；行情取到 {end_plus}")
|
||
cal, close = _price_panel(dates[0], end_plus)
|
||
|
||
rows = []
|
||
for ds in dates:
|
||
score = _factor_map("t_factor_akg_score", ds)
|
||
if score.empty:
|
||
continue
|
||
trans = _factor_map("t_factor_akg_transmission", ds)
|
||
upside = _factor_map("t_factor_akg_upside", ds)
|
||
hd = factors._heat_day_for(ds) # noqa: SLF001
|
||
heat = _factor_map("t_factor_akg_heat", hd) if hd else pd.Series(dtype=float)
|
||
|
||
base_codes = list(score[score >= 150.0].index)
|
||
lists = {"A现行": _rank_a(score)[:a.top],
|
||
"B绝对档界": _rank_b(score, trans, a.strong_min)[:a.top],
|
||
"C连续加权": _rank_c(score, trans, upside, heat, w)[:a.top],
|
||
"基准主榜等权": base_codes}
|
||
for name, codes in lists.items():
|
||
for k in horizons:
|
||
rets = _fwd(cal, close, ds, codes, k)
|
||
if not rets:
|
||
continue
|
||
rows.append({"date": ds, "scheme": name, "horizon": k,
|
||
"n": len(rets), "mean": float(np.mean(rets)),
|
||
"hit": float(np.mean([1.0 if r > 0 else 0.0 for r in rets])),
|
||
"median": float(np.median(rets))})
|
||
|
||
if not rows:
|
||
raise SystemExit("没有任何可评样本——多半是前瞻天数超出了已有行情（等几天再跑）。")
|
||
df = pd.DataFrame(rows)
|
||
os.makedirs("data/score_lab", exist_ok=True)
|
||
out = f"data/score_lab/对比_{dates[0]}_{dates[-1]}.csv"
|
||
df.to_csv(out, index=False, encoding="utf-8-sig")
|
||
|
||
print(f"\n—— 汇总（逐日等权平均；excess = 相对基准主榜等权）——")
|
||
print(f"{'口径':<10}{'期限':>4}{'样本日':>5}{'均值':>9}{'胜率':>7}{'超额':>9}")
|
||
agg = df.groupby(["scheme", "horizon"]).agg(days=("date", "nunique"),
|
||
mean=("mean", "mean"),
|
||
hit=("hit", "mean")).reset_index()
|
||
base = {(r.horizon): r.mean for r in agg[agg["scheme"] == "基准主榜等权"].itertuples()}
|
||
for r in agg.itertuples():
|
||
ex = r.mean - base.get(r.horizon, 0.0)
|
||
print(f"{r.scheme:<10}{r.horizon:>4}{r.days:>5}{r.mean:>9.2%}{r.hit:>7.1%}"
|
||
+ (f"{ex:>9.2%}" if r.scheme != "基准主榜等权" else f"{'—':>9}"))
|
||
n_days = df["date"].nunique()
|
||
print(f"\n已写 {out}（{len(df)} 行）。样本 {n_days} 天"
|
||
+ ("——样本很小, 只看方向、别下死结论。" if n_days < 40 else "。"))
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
raise SystemExit(main())
|