feat(factors): 新增筹码集中度相关因子并优化训练框架

- 添加 19 个筹码分布和胜率相关因子(包括chip_dispersion、winner_rate等系列)
- LightGBM模型添加早停和训练指标记录功能
- 统一Label配置到common.py模块
- 新增list_factors.py因子列表脚本

src/training/components/models/lightgbm.py

@@ -48,6 +48,7 @@ class LightGBMModel(BaseModel):
         self.params = dict(params) if params is not None else {}
         self.model = None
         self.feature_names_: Optional[list] = None
+        self.evals_result_: Optional[dict] = None
 
     def fit(
         self,
@@ -90,14 +91,23 @@ class LightGBMModel(BaseModel):
             y_val_np = y_val.to_numpy()
             valid_sets = lgb.Dataset(X_val_np, label=y_val_np, reference=train_data)
 
-        # 从 params 中提取 num_boost_round，默认 100
-        num_boost_round = self.params.pop("n_estimators", 100)
+        # 从 params 中提取训练控制参数
+        params_copy = dict(self.params)
+        num_boost_round = params_copy.pop("n_estimators", 100)
+        early_stopping_round = params_copy.pop("early_stopping_round", 50)
+
+        self.evals_result_ = {}
+        callbacks = [
+            lgb.early_stopping(stopping_rounds=early_stopping_round),
+            lgb.record_evaluation(self.evals_result_),
+        ]
 
         self.model = lgb.train(
-            self.params,
+            params_copy,
             train_data,
             num_boost_round=num_boost_round,
             valid_sets=[valid_sets] if valid_sets else None,
+            callbacks=callbacks,
         )
 
         return self
@@ -121,6 +131,34 @@ class LightGBMModel(BaseModel):
         result = self.model.predict(X_np)
         return np.asarray(result)
 
+    def get_evals_result(self) -> Optional[dict]:
+        """获取训练评估结果
+
+        Returns:
+            评估结果字典，如果模型尚未训练返回 None
+        """
+        return self.evals_result_
+
+    def get_best_iteration(self) -> Optional[int]:
+        """获取最佳迭代轮数（考虑早停）
+
+        Returns:
+            最佳迭代轮数，如果模型未训练返回 None
+        """
+        if self.model is None:
+            return None
+        return self.model.best_iteration
+
+    def get_best_score(self) -> Optional[dict]:
+        """获取最佳评分
+
+        Returns:
+            最佳评分字典，如果模型未训练返回 None
+        """
+        if self.model is None:
+            return None
+        return self.model.best_score
+
     def feature_importance(self) -> Optional[pd.Series]:
         """返回特征重要性