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 +1,168 @@
+"""
+情绪因子。
+
+将 Qwen 输出的情绪分数转换为量化因子值。
+"""
+
+import numpy as np
+import pandas as pd
+
+from factors.base import BaseFactor
+
+
+class NewsSentimentFactor(BaseFactor):
+    """
+    新闻情绪因子。
+
+    将多条新闻的情绪分数按时间加权聚合到每个交易日。
+
+    参数:
+        window: 滚动窗口（交易日）
+        decay: 指数衰减系数（越大衰减越快），0 表示等权
+        sentiment_df: 情绪分析结果 DataFrame
+                      (date, sentiment_score, confidence, title, content)
+    """
+
+    category = "sentiment"
+
+    def __init__(self, window: int = 5, decay: float = 0.3, sentiment_df: pd.DataFrame | None = None):
+        self.window = window
+        self.decay = decay
+        self.sentiment_df = sentiment_df
+        self.name = f"news_sent_{window}"
+
+    def calculate(self, df: pd.DataFrame) -> pd.Series:
+        if self.sentiment_df is None or self.sentiment_df.empty:
+            return pd.Series(float("nan"), index=df.index, name=self.name)
+
+        return _aggregate_sentiment(
+            df, self.sentiment_df, self.window, self.decay
+        )
+
+    def get_required_columns(self) -> list[str]:
+        return []
+
+
+class SentimentMomentumFactor(BaseFactor):
+    """
+    情绪动量因子。
+
+    当前情绪 - N 日前情绪，衡量情绪变化方向。
+    """
+
+    category = "sentiment"
+
+    def __init__(self, period: int = 5, sentiment_df: pd.DataFrame | None = None):
+        self.period = period
+        self.sentiment_df = sentiment_df
+        self.name = f"sent_delta_{period}"
+
+    def calculate(self, df: pd.DataFrame) -> pd.Series:
+        base = NewsSentimentFactor(window=1, sentiment_df=self.sentiment_df).calculate(df)
+        return base.diff(self.period)
+
+    def get_required_columns(self) -> list[str]:
+        return []
+
+
+class SentimentConfidenceFactor(BaseFactor):
+    """
+    情绪置信度因子。
+
+    新闻情绪分析的置信度越高，因子绝对值越大（方向同 sentiment_score）。
+    sentiment_score × confidence → 高置信利好=正值大，高置信利空=负值大。
+    """
+
+    category = "sentiment"
+
+    def __init__(self, window: int = 5, sentiment_df: pd.DataFrame | None = None):
+        self.window = window
+        self.sentiment_df = sentiment_df
+        self.name = f"news_conf_{window}"
+
+    def calculate(self, df: pd.DataFrame) -> pd.Series:
+        if self.sentiment_df is None or self.sentiment_df.empty:
+            return pd.Series(float("nan"), index=df.index, name=self.name)
+
+        sdf = self.sentiment_df.copy()
+        # 设置加权分数
+        if "confidence" in sdf.columns and "sentiment_score" in sdf.columns:
+            sdf["weighted_score"] = sdf["sentiment_score"] * sdf["confidence"]
+        else:
+            return pd.Series(float("nan"), index=df.index, name=self.name)
+
+        return _aggregate_sentiment(df, sdf, self.window, decay=0.3, score_col="weighted_score")
+
+    def get_required_columns(self) -> list[str]:
+        return []
+
+
+# ── 情绪聚合工具函数 ──────────────────────────────────────
+
+def _aggregate_sentiment(
+    daily_df: pd.DataFrame,
+    sentiment_df: pd.DataFrame,
+    window: int,
+    decay: float,
+    score_col: str = "sentiment_score",
+) -> pd.Series:
+    """
+    将情绪分数按时间加权聚合到交易日。
+
+    逻辑：
+    1. 对每个交易日 t，找到 [t - window + 1, t] 范围内的所有新闻
+    2. 按 time_decay = exp(-decay * days_from_t) 加权
+    3. 按 confidence（如有）加权
+    4. 返回加权平均情绪分数
+
+    参数:
+        daily_df: 日线 DataFrame（提供 index 和日期对齐）
+        sentiment_df: 情绪 DataFrame（date 列 + score_col）
+        window: 窗口大小
+        decay: 衰减系数
+        score_col: 情绪分数列名
+    """
+    if sentiment_df.empty:
+        return pd.Series(float("nan"), index=daily_df.index, name=score_col)
+
+    # 统一日期格式
+    sdf = sentiment_df.copy()
+    sdf["date"] = pd.to_datetime(sdf["date"], format="%Y%m%d", errors="coerce")
+    sdf = sdf.dropna(subset=["date"])
+    sdf = sdf.sort_values("date")
+
+    daily_idx = pd.to_datetime(daily_df.index, format="%Y%m%d", errors="coerce")
+    if daily_idx.isna().all():
+        daily_idx = pd.to_datetime(daily_df.index)
+
+    result = pd.Series(float("nan"), index=daily_df.index)
+
+    # 对 news 日期建立搜索索引
+    news_dates = sdf["date"].values
+
+    for i, dt in enumerate(daily_idx):
+        if pd.isna(dt):
+            continue
+        # 窗口起始
+        window_start = dt - pd.Timedelta(days=window * 2)  # 宽窗覆盖非交易日
+
+        mask = (news_dates >= window_start) & (news_dates <= dt)
+        candidates = sdf[mask]
+
+        if candidates.empty:
+            continue
+
+        # 时间衰减权重
+        days_diff = (dt - candidates["date"]).dt.days
+        time_weights = np.exp(-decay * days_diff)
+
+        # 置信度权重（如有）
+        conf_weights = candidates.get("confidence", pd.Series(1.0, index=candidates.index)).fillna(0.5)
+        scores = candidates[score_col].fillna(0.0)
+
+        total_weight = (time_weights * conf_weights).sum()
+        if total_weight > 0:
+            result.iloc[i] = (scores * time_weights * conf_weights).sum() / total_weight
+
+    result.name = score_col
+    return result.astype("float64")