feat(training): 支持 Label 预处理器

- DataPipeline 新增 label_processor_configs 参数
- 分离特征与 label 的预处理流程
- regression.py 添加 label 缩尾处理配置
- 调整学习率并更新排除因子列表

src/experiment/regression.py

@@ -51,61 +51,55 @@ TRAINING_TYPE = "regression"
 
 # 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_alpha001",
-    "GTJA_alpha002",
-    "GTJA_alpha007",
-    "GTJA_alpha016",
-    "GTJA_alpha073",
-    "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",
-    "price_to_avg_cost",
-    "cost_skewness",
-    "GTJA_alpha191",
-    "GTJA_alpha180",
-    "history_position",
-    "bottom_profit",
-    "smart_money_accumulation",
+    'GTJA_alpha036',
+    'GTJA_alpha032',
+    'GTJA_alpha010',
+    'GTJA_alpha005',
+    'CP',
+    'BP',
+    'debt_to_equity',
+    'current_ratio',
+    'GTJA_alpha002',
+    'GTJA_alpha027',
+    'GTJA_alpha064',
+    'GTJA_alpha062',
+    'GTJA_alpha043',
+    'GTJA_alpha044',
+    'GTJA_alpha120',
+    'GTJA_alpha117',
+    'GTJA_alpha103',
+    'GTJA_alpha104',
+    'GTJA_alpha105',
+    'GTJA_alpha073',
+    'GTJA_alpha077',
+    'GTJA_alpha085',
+    'GTJA_alpha090',
+    'GTJA_alpha087',
+    'GTJA_alpha083',
+    'GTJA_alpha092',
+    'GTJA_alpha133',
+    'GTJA_alpha131',
+    'GTJA_alpha126',
+    'GTJA_alpha124',
+    'GTJA_alpha162',
+    'GTJA_alpha164',
+    'GTJA_alpha157',
+    'GTJA_alpha177',
+    'price_to_avg_cost',
+    'cost_skewness',
+    'GTJA_alpha191',
+    'GTJA_alpha180',
+    'history_position',
+    'bottom_profit',
+    'mean_median_dev',
+    'smart_money_accumulation',
+'GTJA_alpha013',
+'GTJA_alpha099',
+'GTJA_alpha107',
+'GTJA_alpha119',
+'GTJA_alpha141',
+'GTJA_alpha130',
+'GTJA_alpha173',
 ]
 
 # 模型参数配置
@@ -118,7 +112,7 @@ MODEL_PARAMS = {
     "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）
+    "learning_rate": 0.01,  # 【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,
@@ -182,6 +176,11 @@ def main():
             (StandardScaler, {}),
             # (CrossSectionalStandardScaler, {}),
         ],
+        label_processor_configs=[
+            # 对 label 进行缩尾处理（去除极端收益率）
+            (Winsorizer, {"lower": 0.05, "upper": 0.95}),
+            # (StandardScaler, {}),
+        ],
         filters=[STFilter(data_router=engine.router)],
         stock_pool_filter_func=stock_pool_filter,
         stock_pool_required_columns=STOCK_FILTER_REQUIRED_COLUMNS,