Simon
73d191b43a
- 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
99 lines
3.4 KiB
Python
99 lines
3.4 KiB
Python
"""
|
||
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):
|
||
"""
|
||
ROE 因子。
|
||
|
||
从财务数据提取 ROE 并映射到日线。
|
||
|
||
需要 df 中包含 'roe' 列（由 FactorEngine 合并财务数据后传入），
|
||
或将 financial_df 直接传入构造函数。
|
||
"""
|
||
|
||
category = "fundamental"
|
||
|
||
def __init__(self, financial_df: pd.DataFrame | None = None):
|
||
"""
|
||
参数:
|
||
financial_df: 财务数据 DataFrame，columns 含 'end_date', 'roe'。
|
||
None 时需在 df 参数中直接提供 roe 列。
|
||
"""
|
||
self._financial_df = financial_df
|
||
self.name = "roe"
|
||
|
||
def calculate(self, df: pd.DataFrame) -> pd.Series:
|
||
if "roe" in df.columns:
|
||
return df["roe"].copy()
|
||
|
||
if self._financial_df is None or self._financial_df.empty:
|
||
return pd.Series(float("nan"), index=df.index)
|
||
|
||
return self._map_financial_to_daily(
|
||
df, self._financial_df, "roe"
|
||
)
|
||
|
||
@staticmethod
|
||
def _map_financial_to_daily(
|
||
daily_df: pd.DataFrame,
|
||
fina_df: pd.DataFrame,
|
||
column: str,
|
||
) -> pd.Series:
|
||
"""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):
|
||
"""ROE 同比变化（当前 ROE - 去年同期 ROE）。"""
|
||
|
||
category = "fundamental"
|
||
|
||
def __init__(self, financial_df: pd.DataFrame | None = None):
|
||
self._financial_df = financial_df
|
||
self.name = "roe_delta"
|
||
|
||
def calculate(self, df: pd.DataFrame) -> pd.Series:
|
||
if self._financial_df is None or self._financial_df.empty:
|
||
return pd.Series(float("nan"), index=df.index)
|
||
|
||
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")
|
||
|
||
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():
|
||
avail_dt = row["_avail"]
|
||
if pd.isna(avail_dt):
|
||
continue
|
||
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")
|