Initial commit: cc-cursor 全链路量化研究平台

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>

finance/factors/fundamental/pe_pb.py

@@ -0,0 +1,113 @@
+"""
+PE / PB 估值因子。
+
+基于日线收盘价 + 财务数据（EPS/每股净资产）计算。
+"""
+
+import pandas as pd
+
+from factors.base import BaseFactor
+
+
+class PEFactor(BaseFactor):
+    """
+    市盈率因子 = close / eps。
+
+    eps 来自财务数据中的 'eps' 列或 TTM EPS。
+    因子值越大表示估值越贵。
+    """
+
+    category = "fundamental"
+
+    def __init__(self, financial_df: pd.DataFrame | None = None):
+        """
+        参数:
+            financial_df: 含 'end_date' 和 'eps' 的 DataFrame。
+        """
+        self._financial_df = financial_df
+        self.name = "pe"
+
+    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)
+
+        eps_series = _map_to_daily(df, self._financial_df, "eps")
+        close = df["close"]
+        return close / eps_series.replace(0, float("nan"))
+
+    def get_required_columns(self) -> list[str]:
+        return ["close"]
+
+
+class PBFactor(BaseFactor):
+    """
+    市净率因子 = close / bvps（每股净资产）。
+
+    因子值越大表示估值越贵。
+    """
+
+    category = "fundamental"
+
+    def __init__(self, financial_df: pd.DataFrame | None = None):
+        self._financial_df = financial_df
+        self.name = "pb"
+
+    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)
+
+        bvps_series = _map_to_daily(df, self._financial_df, "bvps")
+        return df["close"] / bvps_series.replace(0, float("nan"))
+
+    def get_required_columns(self) -> list[str]:
+        return ["close"]
+
+
+class EPFactor(BaseFactor):
+    """
+    盈利收益率因子 = eps / close = 1 / PE。
+
+    值越大表示估值越便宜，适合与动量等因子同向排序。
+    """
+
+    category = "fundamental"
+
+    def __init__(self, financial_df: pd.DataFrame | None = None):
+        self._financial_df = financial_df
+        self.name = "ep"
+
+    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)
+
+        eps_series = _map_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")

finance/factors/fundamental/roe.py

@@ -0,0 +1,104 @@
+"""
+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")