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/experiment/regression.py

@@ -15,13 +15,15 @@ from src.training import (
     NullFiller,
     Winsorizer,
     StandardScaler,
+    CrossSectionalStandardScaler,
 )
 from src.training.core.trainer_v2 import Trainer
 from src.training.components.filters import STFilter
 from src.experiment.common import (
     SELECTED_FACTORS,
     FACTOR_DEFINITIONS,
-    get_label_factor,
+    LABEL_NAME,
+    LABEL_FACTOR,
     TRAIN_START,
     TRAIN_END,
     VAL_START,
@@ -44,58 +46,93 @@ TRAINING_TYPE = "regression"
 # %% md
 # ## 2. 训练特定配置
 # %%
-# Label 配置
-LABEL_NAME = "future_return_5"
-LABEL_FACTOR = get_label_factor(LABEL_NAME)
+# Label 配置（从 common.py 统一导入）
+# LABEL_NAME 和 LABEL_FACTOR 已在 common.py 中绑定，只需从 common 导入
 
 # 排除的因子列表
 EXCLUDED_FACTORS = [
+    "GTJA_alpha062",
+    "GTJA_alpha060",
+    "GTJA_alpha058",
+    "GTJA_alpha056",
+    "GTJA_alpha053",
+    "GTJA_alpha040",
+    "GTJA_alpha043",
+    "GTJA_alpha027",
+    "CP",
+    "max_ret_20",
+    "debt_to_equity",
+    "close_vwap_deviation",
+    "EP",
+    "BP",
+    "EP_rank",
+    "GTJA_alpha044",
+    "GTJA_alpha036",
     "GTJA_alpha010",
     "GTJA_alpha005",
-    "GTJA_alpha036",
-    "GTJA_alpha027",
-    "GTJA_alpha044",
+    "GTJA_alpha001",
+    "GTJA_alpha002",
+    "GTJA_alpha007",
+    "GTJA_alpha016",
     "GTJA_alpha073",
-    "GTJA_alpha104",
-    "GTJA_alpha103",
-    "GTJA_alpha105",
-    "GTJA_alpha092",
-    "GTJA_alpha087",
-    "GTJA_alpha085",
-    "GTJA_alpha062",
-    "GTJA_alpha124",
     "GTJA_alpha133",
     "GTJA_alpha131",
     "GTJA_alpha117",
+    "GTJA_alpha124",
+    "GTJA_alpha120",
+    "GTJA_alpha119",
+    "GTJA_alpha103",
+    "GTJA_alpha099",
+    "GTJA_alpha105",
+    "GTJA_alpha104",
+    "GTJA_alpha090",
+    "GTJA_alpha085",
+    "GTJA_alpha083",
+    "GTJA_alpha084",
+    "GTJA_alpha087",
+    "GTJA_alpha092",
+    "GTJA_alpha074",
+    "GTJA_alpha089",
+    "GTJA_alpha173",
     "GTJA_alpha157",
+    "GTJA_alpha139",
     "GTJA_alpha162",
+    "GTJA_alpha163",
     "GTJA_alpha177",
-    "GTJA_alpha180",
+    "price_to_avg_cost",
+    "cost_skewness",
     "GTJA_alpha191",
+    "GTJA_alpha180",
+    "history_position",
+    "bottom_profit",
+    "smart_money_accumulation",
 ]
 
 # 模型参数配置
 MODEL_PARAMS = {
-    # 基础设置
-    "objective": "regression_l1",
+    # ==================== 基础设置 ====================
+    "objective": "huber",  # 【修改】相比纯 L1(MAE)，huber 对异常值鲁棒且在极小误差处平滑，更适合收益率预测
     "metric": "mae",
-    # 树结构约束
-    "max_depth": 5,
-    "num_leaves": 24,
-    "min_data_in_leaf": 100,
-    # 学习参数
-    "learning_rate": 0.01,
-    "n_estimators": 1500,
-    # 随机采样
-    "subsample": 0.8,
+    # ==================== 树结构约束 ====================
+    "max_depth": 5,  # 【修改】适当加深，允许捕捉一定的高阶交叉
+    "num_leaves": 31,  # 【修改】限制为 31（2的5次方-1），确保树是不对称生长的，防止过拟合
+    "min_data_in_leaf": 512,  # 【大幅增加】从256加到1000。训练集有97万条，极大地限制叶子节点样本量能有效抵抗股市噪音
+    # ==================== 学习参数 ====================
+    "learning_rate": 0.02,  # 【修改】稍微调大一点，帮助模型跳出初始的局部最优（避免十几轮就早停）
+    "n_estimators": 2000,
+    # ==================== 随机采样与降维 ====================
+    "subsample": 0.85,
     "subsample_freq": 1,
-    "colsample_bytree": 0.8,
-    # 正则化
-    "reg_alpha": 0.5,
-    "reg_lambda": 1.0,
-    # 杂项
+    "colsample_bytree": 0.4,  # 【大幅降低】从0.8降到0.4。强制打压 GTJA_alpha127 的霸权，逼迫模型去学习其他因子的信息
+    "extra_trees": True,  # 【新增且极度推荐】极度随机树模式。在分裂点选择时增加随机性，是量化比赛中防过拟合的神器
+    # ==================== 正则化 ====================
+    "reg_alpha": 1.0,  # 【修改】L1正则增加，强行把一些无用特征的权重压到0
+    "reg_lambda": 5.0,  # 【修改】L2正则大幅增加（从1到5），惩罚过大的叶子节点输出权重
+    "max_bin": 127,  # 【新增】默认255，降低到127相当于对连续特征做了一次粗颗粒度的分箱，也是极好的正则化手段
+    # ==================== 杂项 ====================
     "verbose": -1,
     "random_state": 42,
+    "n_jobs": -1,
 }
 
 # 日期范围配置
@@ -143,6 +180,7 @@ def main():
             (NullFiller, {"strategy": "mean"}),
             (Winsorizer, {"lower": 0.01, "upper": 0.99}),
             (StandardScaler, {}),
+            # (CrossSectionalStandardScaler, {}),
         ],
         filters=[STFilter(data_router=engine.router)],
         stock_pool_filter_func=stock_pool_filter,