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 +1,126 @@
+"""
+LightGBM 模型封装。
+"""
+
+import numpy as np
+import pandas as pd
+import lightgbm as lgb
+
+from models.base import BaseModel
+from sklearn.model_selection import TimeSeriesSplit
+
+_DEFAULT_PARAMS = {
+    "objective": "regression",
+    "metric": "rmse",
+    "boosting_type": "gbdt",
+    "num_leaves": 15,
+    "learning_rate": 0.03,
+    "feature_fraction": 0.7,
+    "bagging_fraction": 0.7,
+    "bagging_freq": 5,
+    "verbose": -1,
+    "n_estimators": 1000,
+    "random_state": 42,
+    "min_data_in_leaf": 20,
+}
+
+
+class LightGBMModel(BaseModel):
+    """LightGBM 回归模型。"""
+
+    name = "lightgbm"
+
+    def __init__(
+        self,
+        params: dict | None = None,
+        early_stopping: int = 50,
+        eval_ratio: float = 0.2,
+        random_seed: int = 42,
+    ):
+        self.params = params or _DEFAULT_PARAMS.copy()
+        self.params["random_state"] = random_seed
+        self.early_stopping = early_stopping
+        self.eval_ratio = eval_ratio
+        self._model: lgb.Booster | None = None
+        self._feature_names: list[str] = []
+
+    def fit(self, X: pd.DataFrame, y: pd.Series) -> "LightGBMModel":
+        self._feature_names = list(X.columns)
+
+        n = len(X)
+        val_size = int(n * self.eval_ratio)
+
+        callbacks = []
+        eval_set = None
+        X_train, y_train = X, y
+
+        # 验证集足够大时才启用早停（至少 50 条）
+        if val_size >= 50:
+            split_idx = n - val_size
+            X_train, X_val = X.iloc[:split_idx], X.iloc[split_idx:]
+            y_train, y_val = y.iloc[:split_idx], y.iloc[split_idx:]
+            eval_set = [(X_val, y_val)]
+            callbacks = [
+                lgb.early_stopping(stopping_rounds=self.early_stopping, verbose=False),
+                lgb.log_evaluation(0),
+            ]
+
+        self._model = lgb.LGBMRegressor(**self.params)
+        self._model.fit(
+            X_train, y_train,
+            eval_set=eval_set,
+            callbacks=callbacks if callbacks else None,
+        )
+        return self
+
+    def predict(self, X: pd.DataFrame) -> pd.Series:
+        if self._model is None:
+            raise RuntimeError("模型尚未训练")
+        preds = self._model.predict(X[self._feature_names])
+        return pd.Series(preds, index=X.index, name="pred")
+
+    def get_feature_importance(self, importance_type: str = "gain") -> pd.DataFrame:
+        """特征重要性。importance_type: 'gain' | 'split'"""
+        if self._model is None:
+            return pd.DataFrame()
+        imp = self._model.booster_.feature_importance(importance_type=importance_type)
+        names = self._model.booster_.feature_name()
+        df = pd.DataFrame({"feature": names, "importance": imp})
+        df["importance_pct"] = df["importance"] / df["importance"].sum() * 100
+        return df.sort_values("importance", ascending=False)
+
+    def cv_evaluate(
+        self, X: pd.DataFrame, y: pd.Series, n_folds: int = 5
+    ) -> pd.DataFrame:
+        """
+        时间序列交叉验证评估（不 shuffle）。
+
+        返回每折的 IC (相关系数) 和 MSE。
+        """
+        tscv = TimeSeriesSplit(n_splits=n_folds)
+        results = []
+        for fold, (train_idx, test_idx) in enumerate(tscv.split(X)):
+            X_train, X_test = X.iloc[train_idx], X.iloc[test_idx]
+            y_train, y_test = y.iloc[train_idx], y.iloc[test_idx]
+
+            model = LightGBMModel(
+                params=self.params,
+                early_stopping=self.early_stopping,
+                eval_ratio=0.0,  # 不使用内部验证，直接全量训练
+            )
+            model.fit(X_train, y_train)
+            preds = model.predict(X_test)
+            ic = preds.corr(y_test)
+            mse = ((preds - y_test) ** 2).mean()
+            results.append({"fold": fold, "ic": round(ic, 4), "mse": round(mse, 4)})
+
+        df = pd.DataFrame(results)
+        df.loc["mean"] = df.mean()
+        return df
+
+    @property
+    def n_estimators_used(self) -> int | None:
+        """实际使用的树数量（早停后可能 < n_estimators）。"""
+        if self._model is None:
+            return None
+        return self._model.booster_.current_iteration()