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>
2026-06-07 15:59:05 +08:00
commit 271a9343a5
293 changed files with 59598 additions and 0 deletions
@@ -0,0 +1,192 @@
+"""
+FactorEngine — 因子计算引擎。
+
+批量计算因子，处理技术/基本面/情绪因子的不同数据需求。
+"""
+
+import copy
+
+import pandas as pd
+
+from factors.base import BaseFactor
+from factors.fundamental.roe import ROEFactor
+from factors.fundamental.pe_pb import PEFactor, PBFactor, EPFactor
+
+FUNDAMENTAL_FACTOR_TYPES = (ROEFactor, PEFactor, PBFactor, EPFactor)
+
+
+def _is_sentiment(factor: BaseFactor) -> bool:
+    return getattr(factor, "category", "") == "sentiment"
+
+
+class FactorEngine:
+    """因子计算引擎。"""
+
+    def __init__(self, data_manager, sentiment_engine=None):
+        """
+        参数:
+            data_manager: DataManager 实例。
+            sentiment_engine: SentimentEngine 实例（可选，启用情绪因子时需提供）。
+        """
+        self._dm = data_manager
+        self._sentiment_engine = sentiment_engine
+        self._financial_cache: dict[str, pd.DataFrame] = {}
+
+    def _get_financial(self, ts_code: str) -> pd.DataFrame:
+        """获取财务数据（带缓存）。"""
+        if ts_code not in self._financial_cache:
+            df = self._dm.get_financial(ts_code)
+            self._financial_cache[ts_code] = df
+        return self._financial_cache[ts_code]
+
+    def _resolve_factors(
+        self, factors: list[BaseFactor], fina: pd.DataFrame
+    ) -> list[BaseFactor]:
+        """为每个股票 clone 基本面因子并注入财务数据。"""
+        resolved = []
+        for f in factors:
+            if isinstance(f, FUNDAMENTAL_FACTOR_TYPES):
+                f = copy.copy(f)
+                f._financial_df = fina
+            resolved.append(f)
+        return resolved
+
+    def compute(
+        self,
+        ts_code: str,
+        factors: list[BaseFactor],
+    ) -> pd.DataFrame:
+        """
+        对单只股票计算多个因子。
+
+        参数:
+            ts_code: 如 '000001.SZ'
+            factors: 因子实例列表
+
+        返回:
+            DataFrame，index=trade_date，columns=因子名
+        """
+        if not factors:
+            return pd.DataFrame()
+
+        # 分离情绪因子（通过 SentimentEngine 处理）
+        sent_factors = [f for f in factors if _is_sentiment(f)]
+        other_factors = [f for f in factors if not _is_sentiment(f)]
+
+        # 收集所有需要的列
+        required_cols = set()
+        has_fundamental = False
+        for f in other_factors:
+            required_cols.update(f.get_required_columns())
+            if isinstance(f, FUNDAMENTAL_FACTOR_TYPES):
+                has_fundamental = True
+
+        # 获取日线数据
+        daily = self._dm.get_daily(ts_code)
+        if daily.empty:
+            return pd.DataFrame()
+
+        daily = daily.set_index("trade_date").sort_index()
+
+        # 获取财务数据（如有基本面因子）
+        fina = self._dm.get_financial(ts_code) if has_fundamental else pd.DataFrame()
+
+        # 为当前股票解析因子（clone 基本面因子注入财务数据）
+        resolved_factors = self._resolve_factors(other_factors, fina)
+
+        # 逐因子计算
+        results = {}
+        for factor in resolved_factors:
+            try:
+                series = factor.calculate(daily)
+                results[factor.name] = series.astype("float64")
+            except Exception as e:
+                print(f"[WARN] 因子 {factor.name} 计算失败 ({ts_code}): {e}")
+                results[factor.name] = pd.Series(float("nan"), index=daily.index)
+
+        # 情绪因子：通过 SentimentEngine 计算后合并
+        if sent_factors and self._sentiment_engine:
+            try:
+                sent_df = self._sentiment_engine.compute(ts_code)
+                for f in sent_factors:
+                    if f.name in sent_df.columns:
+                        results[f.name] = sent_df[f.name]
+                    else:
+                        results[f.name] = pd.Series(float("nan"), index=daily.index)
+            except Exception as e:
+                print(f"[WARN] 情绪因子计算失败 ({ts_code}): {e}")
+                for f in sent_factors:
+                    results[f.name] = pd.Series(float("nan"), index=daily.index)
+
+        factor_df = pd.DataFrame(results)
+        factor_df.index.name = "trade_date"
+        return factor_df
+
+    def compute_batch(
+        self,
+        ts_codes: list[str],
+        factors: list[BaseFactor],
+    ) -> dict[str, pd.DataFrame]:
+        """
+        批量计算多只股票的因子。
+
+        返回:
+            {ts_code: factor_df}
+        """
+        results = {}
+        total = len(ts_codes)
+        for i, ts_code in enumerate(ts_codes):
+            try:
+                results[ts_code] = self.compute(ts_code, factors)
+            except Exception as e:
+                print(f"[WARN] {ts_code} 因子计算失败: {e}")
+                results[ts_code] = pd.DataFrame()
+            if (i + 1) % 50 == 0:
+                print(f"[FactorEngine] 进度: {i + 1}/{total}")
+        return results
+
+    def compute_universe(
+        self,
+        factors: list[BaseFactor],
+        date: str,
+        ts_codes: list[str] | None = None,
+    ) -> pd.DataFrame:
+        """
+        计算全市场某一天的因子截面。
+
+        参数:
+            factors: 因子列表
+            date: 目标日期 'YYYYMMDD'
+            ts_codes: 股票列表，None 表示全部
+
+        返回:
+            DataFrame，index=ts_code，columns=因子名
+        """
+        if ts_codes is None:
+            stocks = self._dm.get_stock_list()
+            ts_codes = list(stocks.index)
+
+        rows = []
+        for ts_code in ts_codes:
+            daily = self._dm.get_daily(ts_code)
+            if daily.empty:
+                continue
+            daily = daily.set_index("trade_date")
+            if date not in daily.index:
+                continue
+
+            row = {"ts_code": ts_code}
+            fina = self._get_financial(ts_code)
+            resolved = self._resolve_factors(factors, fina)
+            for factor in resolved:
+                try:
+                    series = factor.calculate(daily)
+                    row[factor.name] = series.get(date, float("nan"))
+                except Exception:
+                    row[factor.name] = float("nan")
+            rows.append(row)
+
+        if not rows:
+            return pd.DataFrame()
+        result = pd.DataFrame(rows).set_index("ts_code")
+        return result