feat: 量化引擎加固 — 新增测试 + 数据/因子/回测层优化
- 新增 finance/tests/ 6 个测试套件（agents/backtest/dao_upsert/factors/features/fundamental_lookahead） - 数据层: data_manager / dao 优化，新增 upsert 逻辑 - 因子层: 基本面因子抽象定位 _mapping、ROE/PE/PB 重构 - 回测层: vectorbt/engine 大改动（251 行），report 增强 - ML 层: features/backtest_integration 特征工程与回测优化 - CLI: agent_cli 重构 - config/settings 扩充配置项
This commit is contained in:
Simon
@@ -0,0 +1,100 @@
|
||||
"""
|
||||
财务数据 → 日线映射（负责消除披露时点前视偏差）。
|
||||
|
||||
A 股季报的披露日远晚于报告期末：
|
||||
- 一季报 / 年报 最迟约 4/30
|
||||
- 中报 最迟约 8/31
|
||||
- 三季报 最迟约 10/31
|
||||
|
||||
若直接把报告期 end_date 当日就"看到"本期财务结果，会引入前视偏差。
|
||||
本模块统一在 end_date 上叠加一个保守的披露滞后：
|
||||
1) 财务帧中若带 ann_date（实际披露日），则优先用 ann_date 作为可用日；
|
||||
2) 否则按报告期月份推断法定披露时点，作为保守可用日。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def _disclosure_available_date(end_date_ts: pd.Timestamp) -> pd.Timestamp:
|
||||
"""根据报告期末推断法定披露可用日（无 ann_date 时的保守近似）。
|
||||
|
||||
一季度(0331)→4/30；中报(0630)→8/31；三季报(0930)→10/31；年报(1231)→次年4/30。
|
||||
"""
|
||||
if end_date_ts.month == 3 and end_date_ts.day == 31:
|
||||
return pd.Timestamp(year=end_date_ts.year, month=4, day=30)
|
||||
if end_date_ts.month == 6 and end_date_ts.day == 30:
|
||||
return pd.Timestamp(year=end_date_ts.year, month=8, day=31)
|
||||
if end_date_ts.month == 9 and end_date_ts.day == 30:
|
||||
return pd.Timestamp(year=end_date_ts.year, month=10, day=31)
|
||||
# 年报 12/31 → 次年 4/30
|
||||
return pd.Timestamp(year=end_date_ts.year + 1, month=4, day=30)
|
||||
|
||||
|
||||
def _eff_available_dates(fina_df: pd.DataFrame) -> pd.DataFrame:
|
||||
"""计算每期财务的"可用日"（取最小滞后：有 ann_date 用它，否则法定截止）。"""
|
||||
fina = fina_df.copy()
|
||||
# 数值型 ann_date（YYYYMMDD）→ datetime；缺失用报告期末推断
|
||||
if "ann_date" in fina.columns:
|
||||
ann = pd.to_datetime(fina["ann_date"].astype(str), format="%Y%m%d", errors="coerce")
|
||||
else:
|
||||
ann = pd.Series(pd.NaT, index=fina.index)
|
||||
|
||||
end = pd.to_datetime(
|
||||
fina["end_date"].astype(str), format="%Y%m%d", errors="coerce")
|
||||
|
||||
avail = ann.fillna(pd.Series(
|
||||
[_disclosure_available_date(x) if not pd.isna(x) else pd.NaT for x in end],
|
||||
index=end.index,
|
||||
))
|
||||
# 极少数 ann_date 早于报告期末（脏数据）时兜底用期末
|
||||
avail = avail.where(avail >= end, end)
|
||||
fina["_avail"] = avail
|
||||
return fina
|
||||
|
||||
|
||||
def effective_available_dates(fina_df: pd.DataFrame) -> pd.DataFrame:
|
||||
"""
|
||||
(公开) 返回带 _avail（披露可用日）的财务帧，供同比/环比等因子复用。
|
||||
要求 fina_df 至少含 'end_date'；可选 'ann_date'。
|
||||
"""
|
||||
return _eff_available_dates(fina_df)
|
||||
|
||||
|
||||
def map_fundamental_to_daily(
|
||||
daily_df: pd.DataFrame,
|
||||
fina_df: pd.DataFrame,
|
||||
column: str,
|
||||
) -> pd.Series:
|
||||
"""
|
||||
将季度财务数据按披露可用日映射到日线索引（前值填充）。
|
||||
|
||||
- 优先按 ann_date（实际披露日）对齐；
|
||||
- 无 ann_date 时按报告期末的法定披露截止日保守对齐；
|
||||
- 从而避免"财报在披露日之前就被回测看到"的前视偏差。
|
||||
"""
|
||||
if column not in fina_df.columns or "end_date" not in fina_df.columns:
|
||||
return pd.Series(float("nan"), index=daily_df.index)
|
||||
|
||||
cols = ["end_date", column] + (["ann_date"] if "ann_date" in fina_df.columns else [])
|
||||
fina = fina_df[cols].dropna(subset=["end_date", column]).copy()
|
||||
if fina.empty:
|
||||
return pd.Series(float("nan"), index=daily_df.index)
|
||||
|
||||
fina = _eff_available_dates(fina)
|
||||
fina = fina.sort_values("_avail")
|
||||
|
||||
dates = pd.to_datetime(daily_df.index, format="%Y%m%d", errors="coerce")
|
||||
result = pd.Series(float("nan"), index=daily_df.index)
|
||||
avail_dates = fina["_avail"].values
|
||||
|
||||
for i, avail_dt in enumerate(avail_dates):
|
||||
if pd.isna(avail_dt):
|
||||
continue
|
||||
mask = dates >= avail_dt
|
||||
if i + 1 < len(avail_dates) and not pd.isna(avail_dates[i + 1]):
|
||||
mask &= dates < avail_dates[i + 1]
|
||||
result[mask] = fina[column].iloc[i]
|
||||
|
||||
return result.astype("float64")
|
||||
@@ -7,6 +7,7 @@ PE / PB 估值因子。
|
||||
import pandas as pd
|
||||
|
||||
from factors.base import BaseFactor
|
||||
from factors.fundamental._mapping import map_fundamental_to_daily
|
||||
|
||||
|
||||
class PEFactor(BaseFactor):
|
||||
@@ -31,7 +32,7 @@ class PEFactor(BaseFactor):
|
||||
if self._financial_df is None or self._financial_df.empty:
|
||||
return pd.Series(float("nan"), index=df.index)
|
||||
|
||||
eps_series = _map_to_daily(df, self._financial_df, "eps")
|
||||
eps_series = map_fundamental_to_daily(df, self._financial_df, "eps")
|
||||
close = df["close"]
|
||||
return close / eps_series.replace(0, float("nan"))
|
||||
|
||||
@@ -56,7 +57,7 @@ class PBFactor(BaseFactor):
|
||||
if self._financial_df is None or self._financial_df.empty:
|
||||
return pd.Series(float("nan"), index=df.index)
|
||||
|
||||
bvps_series = _map_to_daily(df, self._financial_df, "bvps")
|
||||
bvps_series = map_fundamental_to_daily(df, self._financial_df, "bvps")
|
||||
return df["close"] / bvps_series.replace(0, float("nan"))
|
||||
|
||||
def get_required_columns(self) -> list[str]:
|
||||
@@ -80,34 +81,8 @@ class EPFactor(BaseFactor):
|
||||
if self._financial_df is None or self._financial_df.empty:
|
||||
return pd.Series(float("nan"), index=df.index)
|
||||
|
||||
eps_series = _map_to_daily(df, self._financial_df, "eps")
|
||||
eps_series = map_fundamental_to_daily(df, self._financial_df, "eps")
|
||||
return eps_series / df["close"].replace(0, float("nan")) * 100
|
||||
|
||||
def get_required_columns(self) -> list[str]:
|
||||
return ["close"]
|
||||
|
||||
|
||||
def _map_to_daily(
|
||||
daily_df: pd.DataFrame,
|
||||
fina_df: pd.DataFrame,
|
||||
column: str,
|
||||
) -> pd.Series:
|
||||
"""将季度财务数据填充到日线索引（前值填充）。"""
|
||||
fina = fina_df[["end_date", column]].dropna().copy()
|
||||
fina["end_date"] = fina["end_date"].astype(str)
|
||||
fina = fina.sort_values("end_date")
|
||||
|
||||
result = pd.Series(float("nan"), index=daily_df.index)
|
||||
if fina.empty:
|
||||
return result
|
||||
|
||||
dates = pd.to_datetime(daily_df.index, format="%Y%m%d", errors="coerce")
|
||||
fina_dates = pd.to_datetime(fina["end_date"], format="%Y%m%d", errors="coerce")
|
||||
|
||||
for i, fina_date in enumerate(fina_dates):
|
||||
mask = dates >= fina_date
|
||||
if i + 1 < len(fina_dates):
|
||||
mask &= dates < fina_dates.iloc[i + 1]
|
||||
result[mask] = fina[column].iloc[i]
|
||||
|
||||
return result.astype("float64")
|
||||
|
||||
@@ -5,6 +5,7 @@ ROE 因子。
|
||||
import pandas as pd
|
||||
|
||||
from factors.base import BaseFactor
|
||||
from factors.fundamental._mapping import map_fundamental_to_daily, effective_available_dates
|
||||
|
||||
|
||||
class ROEFactor(BaseFactor):
|
||||
@@ -45,28 +46,8 @@ class ROEFactor(BaseFactor):
|
||||
fina_df: pd.DataFrame,
|
||||
column: str,
|
||||
) -> pd.Series:
|
||||
"""将财务数据（季度）映射到日线索引。"""
|
||||
fina = fina_df[["end_date", column]].dropna().copy()
|
||||
fina["end_date"] = fina["end_date"].astype(str)
|
||||
fina = fina.sort_values("end_date")
|
||||
|
||||
result = pd.Series(float("nan"), index=daily_df.index)
|
||||
|
||||
if fina.empty:
|
||||
return result
|
||||
|
||||
dates = pd.to_datetime(daily_df.index, format="%Y%m%d", errors="coerce")
|
||||
fina_dates = pd.to_datetime(fina["end_date"], format="%Y%m%d", errors="coerce")
|
||||
|
||||
for i, fina_date in enumerate(fina_dates):
|
||||
mask = dates >= fina_date
|
||||
if i + 1 < len(fina_dates):
|
||||
mask &= dates < fina_dates.iloc[i + 1]
|
||||
else:
|
||||
pass # 最新一期覆盖所有后续日期
|
||||
result[mask] = fina[column].iloc[i]
|
||||
|
||||
return result.astype("float64")
|
||||
"""将财务数据（季度）映射到日线索引，按披露可用日消除前视。"""
|
||||
return map_fundamental_to_daily(daily_df, fina_df, column)
|
||||
|
||||
|
||||
class ROETTMDeltaFactor(BaseFactor):
|
||||
@@ -82,23 +63,36 @@ class ROETTMDeltaFactor(BaseFactor):
|
||||
if self._financial_df is None or self._financial_df.empty:
|
||||
return pd.Series(float("nan"), index=df.index)
|
||||
|
||||
fina = self._financial_df[["end_date", "roe"]].dropna().copy()
|
||||
fina["end_date"] = fina["end_date"].astype(str)
|
||||
fina["year"] = fina["end_date"].str[:4].astype(int)
|
||||
fina = fina.sort_values("end_date")
|
||||
if "roe" not in self._financial_df.columns or "end_date" not in self._financial_df.columns:
|
||||
return pd.Series(float("nan"), index=df.index)
|
||||
|
||||
# 基于财务帧计算披露可用日（含 ann_date 优先/法定滞后兜底）
|
||||
fina = effective_available_dates(self._financial_df)
|
||||
fina = fina[["_avail", "end_date", "roe"]].dropna(subset=["_avail", "roe"]).copy()
|
||||
if fina.empty:
|
||||
return pd.Series(float("nan"), index=df.index)
|
||||
|
||||
# 报告期月份（A 股季末：03/06/09/12）
|
||||
end_dt = pd.to_datetime(fina["end_date"].astype(str), format="%Y%m%d", errors="coerce")
|
||||
fina["report_month"] = end_dt.dt.month
|
||||
fina["report_year"] = end_dt.dt.year
|
||||
# 本年取数映射：{ (year, month): roe }
|
||||
cur_map = dict(zip(zip(fina["report_year"], fina["report_month"]), fina["roe"]))
|
||||
# 按披露可用日排序，逐期覆盖区间
|
||||
fina = fina.sort_values("_avail")
|
||||
|
||||
# 按年分组计算 YoY 差值
|
||||
roe_delta = pd.Series(float("nan"), index=df.index)
|
||||
dates = pd.to_datetime(df.index, format="%Y%m%d", errors="coerce")
|
||||
|
||||
for _, row in fina.iterrows():
|
||||
this_year = row["year"]
|
||||
prev_row = fina[fina["year"] == this_year - 1]
|
||||
if prev_row.empty:
|
||||
avail_dt = row["_avail"]
|
||||
if pd.isna(avail_dt):
|
||||
continue
|
||||
delta = row["roe"] - prev_row["roe"].iloc[-1]
|
||||
f_date = pd.to_datetime(row["end_date"], format="%Y%m%d")
|
||||
mask = dates >= f_date
|
||||
prev_roe = cur_map.get((row["report_year"] - 1, row["report_month"]))
|
||||
if prev_roe is None:
|
||||
continue
|
||||
delta = row["roe"] - prev_roe
|
||||
mask = dates >= avail_dt
|
||||
roe_delta[mask] = delta
|
||||
|
||||
return roe_delta.astype("float64")
|
||||
|
||||
Reference in New Issue
Block a user