simonandClaude Opus 4.7
271a9343a5
7 Sprints 全部完成: Sprint 0: 基础设施 (DataManager + MariaDB) Sprint 1: 因子引擎 (34因子/12分类) Sprint 2: VectorBT 回测 (5策略+截面) Sprint 3: Optuna 优化 (+Walk-Forward) Sprint 4: ML 模型 (LightGBM+CatBoost) Sprint 5: Qwen 情绪因子 (三源新闻+日期对齐) Sprint 6: Agent 系统 (4Agent+日报.md/.html) 生产加固 (15项): Tushare双源fallback, SSH自动恢复, pool_pre_ping, save_daily先删后插, load_dotenv绝对路径, 日报5d/20d修复, RiskAgent改上证指数, 昨日对比+数据截止, mac_report utf8mb4, CLAUDE-*.md 9条已知Bug, demo全参数化, djapi数据源归一化, indexDatas API修正 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
105 lines
3.3 KiB
Python
105 lines
3.3 KiB
Python
"""
|
||
ROE 因子。
|
||
"""
|
||
|
||
import pandas as pd
|
||
|
||
from factors.base import BaseFactor
|
||
|
||
|
||
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。"""
|
||
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")
|
||
|
||
|
||
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)
|
||
|
||
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")
|
||
|
||
# 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:
|
||
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
|
||
roe_delta[mask] = delta
|
||
|
||
return roe_delta.astype("float64")
|