test(debug): 添加因子回测一致性问题的调试测试套件

- 分析GTJA_alpha032等因子在不同LOOKBACK_DAYS下的差异来源
- 验证cs_rank嵌套和截面股票数量对结果的影响
- 测试ts_rank NaN处理和除法除零修复

src/experiment/common.py

@@ -5,7 +5,7 @@
 """
 
 from datetime import datetime
-from typing import List, Optional
+from typing import Dict, List, Optional
 
 import polars as pl
 
@@ -182,14 +182,14 @@ SELECTED_FACTORS = [
     "GTJA_alpha110",
     "GTJA_alpha111",
     "GTJA_alpha112",
-    "GTJA_alpha113",
+    # "GTJA_alpha113",
     "GTJA_alpha114",
     "GTJA_alpha115",
     "GTJA_alpha117",
     "GTJA_alpha118",
     "GTJA_alpha119",
     "GTJA_alpha120",
-    "GTJA_alpha121",
+    # "GTJA_alpha121",
     "GTJA_alpha122",
     "GTJA_alpha123",
     "GTJA_alpha124",
@@ -205,13 +205,13 @@ SELECTED_FACTORS = [
     "GTJA_alpha134",
     "GTJA_alpha135",
     "GTJA_alpha136",
-    "GTJA_alpha138",
+    # "GTJA_alpha138",
     "GTJA_alpha139",
-    "GTJA_alpha140",
+    # "GTJA_alpha140",
     "GTJA_alpha141",
     "GTJA_alpha142",
     "GTJA_alpha145",
-    "GTJA_alpha146",
+    # "GTJA_alpha146",
     "GTJA_alpha148",
     "GTJA_alpha150",
     "GTJA_alpha151",
@@ -253,50 +253,50 @@ SELECTED_FACTORS = [
 ]
 
 # 因子定义字典（完整因子库，用于存放尚未注册到metadata的因子）
-FACTOR_DEFINITIONS = {}
+FACTOR_DEFINITIONS = {"cs_rank_circ_mv": "cs_rank(circ_mv)"}
 
 # 需要排除的因子列表（这些因子不会被计算和使用）
 # 用于临时屏蔽效果不好的因子，无需从 SELECTED_FACTORS 中删除
-EXCLUDED_FACTORS: List[str] = [
-    # "GTJA_alpha005",
-    # "GTJA_alpha028",
-    # "GTJA_alpha023",
-    # "GTJA_alpha002",
-    # "GTJA_alpha010",
-    # "GTJA_alpha011",
-    # "GTJA_alpha044",
-    # "GTJA_alpha036",
-    # "GTJA_alpha027",
-    # "GTJA_alpha109",
-    # "GTJA_alpha104",
-    # "GTJA_alpha103",
-    # "GTJA_alpha085",
-    # "GTJA_alpha111",
-    # "GTJA_alpha092",
-    # "GTJA_alpha067",
-    # "GTJA_alpha060",
-    # "GTJA_alpha062",
-    # "GTJA_alpha063",
-    # "GTJA_alpha079",
-    # "GTJA_alpha073",
-    # "GTJA_alpha087",
-    # "GTJA_alpha117",
-    # "GTJA_alpha113",
-    # "GTJA_alpha138",
-    # "GTJA_alpha121",
-    # "GTJA_alpha124",
-    # "GTJA_alpha133",
-    # "GTJA_alpha131",
-    # "GTJA_alpha118",
-    # "GTJA_alpha164",
-    # "GTJA_alpha162",
-    # "GTJA_alpha157",
-    # "GTJA_alpha171",
-    # "GTJA_alpha177",
-    # "GTJA_alpha180",
-    # "GTJA_alpha188",
-    # "GTJA_alpha191",
-]
+# EXCLUDED_FACTORS: List[str] = [
+#     # "GTJA_alpha005",
+#     # "GTJA_alpha028",
+#     # "GTJA_alpha023",
+#     # "GTJA_alpha002",
+#     # "GTJA_alpha010",
+#     # "GTJA_alpha011",
+#     # "GTJA_alpha044",
+#     # "GTJA_alpha036",
+#     # "GTJA_alpha027",
+#     # "GTJA_alpha109",
+#     # "GTJA_alpha104",
+#     # "GTJA_alpha103",
+#     # "GTJA_alpha085",
+#     # "GTJA_alpha111",
+#     # "GTJA_alpha092",
+#     # "GTJA_alpha067",
+#     # "GTJA_alpha060",
+#     # "GTJA_alpha062",
+#     # "GTJA_alpha063",
+#     # "GTJA_alpha079",
+#     # "GTJA_alpha073",
+#     # "GTJA_alpha087",
+#     # "GTJA_alpha117",
+#     # "GTJA_alpha113",
+#     # "GTJA_alpha138",
+#     # "GTJA_alpha121",
+#     # "GTJA_alpha124",
+#     # "GTJA_alpha133",
+#     # "GTJA_alpha131",
+#     # "GTJA_alpha118",
+#     # "GTJA_alpha164",
+#     # "GTJA_alpha162",
+#     # "GTJA_alpha157",
+#     # "GTJA_alpha171",
+#     # "GTJA_alpha177",
+#     # "GTJA_alpha180",
+#     # "GTJA_alpha188",
+#     # "GTJA_alpha191",
+# ]
 
 
 def get_label_factor(label_name: str) -> dict:
@@ -471,17 +471,18 @@ def stock_pool_filter(df: pl.DataFrame) -> pl.Series:
         & ~df["ts_code"].str.starts_with("4")  # 排除北交所
     )
 
-    # 在已筛选的股票中，选取市值最小的500只
+    # 在已筛选的股票中，选取流通市值最小的500只
     valid_df = df.filter(code_filter)
-    n = min(500, len(valid_df))
-    small_cap_codes = valid_df.sort("total_mv").head(n)["ts_code"]
+    n = min(1000, len(valid_df))
+    small_cap_codes = valid_df.sort("circ_mv").head(n)["ts_code"]
 
     # 返回布尔 Series：是否在被选中的股票中
     return df["ts_code"].is_in(small_cap_codes)
 
 
 # 定义筛选所需的基础列
-STOCK_FILTER_REQUIRED_COLUMNS = ["total_mv"]
+STOCK_FILTER_REQUIRED_COLUMNS = ["circ_mv"]
+
 
 # =============================================================================
 # 输出配置
@@ -490,7 +491,7 @@ OUTPUT_DIR = "output"
 SAVE_PREDICTIONS = True
 
 # 模型保存配置
-SAVE_MODEL = True  # 是否保存模型
+SAVE_MODEL = False  # 是否保存模型
 MODEL_SAVE_DIR = "models"  # 模型保存目录
 
 # Top N 配置：每日推荐股票数量