docs(AGENTS): 新增AI行为准则规范

- 添加代码存放位置规则，强制代码存放于 src/ 或 tests/ 目录
- 添加 Tests 目录代码运行规则，强制使用 pytest 运行测试代码
- 更新 learn_to_rank 实验代码：调整因子列表和处理器配置
- 修复 schema_cache 表结构缓存逻辑

src/experiment/regression.ipynb

@@ -30,6 +30,7 @@
     "    Trainer,\n",
     "    Winsorizer,\n",
     "    NullFiller,\n",
+    "    check_data_quality,\n",
     ")\n",
     "from src.training.config import TrainingConfig\n",
     "\n"
@@ -46,13 +47,13 @@
    "outputs": [],
    "execution_count": null,
    "source": [
-    "def create_factors_with_metadata(\n",
+    "def register_factors(\n",
     "    engine: FactorEngine,\n",
     "    selected_factors: List[str],\n",
     "    factor_definitions: dict,\n",
     "    label_factor: dict,\n",
     ") -> List[str]:\n",
-    "    \"\"\"注册因子（SELECTED_FACTORS 从 metadata 查询，FACTOR_DEFINITIONS 用表达式注册）\"\"\"\n",
+    "    \"\"\"注册因子（selected_factors 从 metadata 查询，factor_definitions 用 DSL 表达式注册）\"\"\"\n",
     "    print(\"=\" * 80)\n",
     "    print(\"注册因子\")\n",
     "    print(\"=\" * 80)\n",
@@ -327,9 +328,6 @@
     "    \"random_state\": 42,\n",
     "}\n",
     "\n",
-    "# 数据处理器配置（新 API：需要传入 feature_cols）\n",
-    "# 注意：processor 现在需要显式指定要处理的特征列\n",
-    "\n",
     "\n",
     "# 股票池筛选函数\n",
     "# 使用新的 StockPoolManager API：传入自定义筛选函数和所需列/因子\n",
@@ -409,7 +407,7 @@
     "\n",
     "# 2. 使用 metadata 定义因子\n",
     "print(\"\\n[2] 定义因子（从 metadata 注册）\")\n",
-    "feature_cols = create_factors_with_metadata(\n",
+    "feature_cols = register_factors(\n",
     "    engine, SELECTED_FACTORS, FACTOR_DEFINITIONS, LABEL_FACTOR\n",
     ")\n",
     "target_col = LABEL_NAME\n",
@@ -434,7 +432,7 @@
     "# 5. 创建模型\n",
     "model = LightGBMModel(params=MODEL_PARAMS)\n",
     "\n",
-    "# 6. 创建数据处理器（新 API：需要传入 feature_cols）\n",
+    "# 6. 创建数据处理器（使用函数返回的完整特征列表）\n",
     "processors = [\n",
     "    NullFiller(feature_cols=feature_cols, strategy=\"mean\"),\n",
     "    Winsorizer(feature_cols=feature_cols, lower=0.01, upper=0.99),\n",
@@ -560,8 +558,32 @@
    "outputs": [],
    "execution_count": null,
    "source": [
-    "# 步骤 3: 训练集数据处理\n",
-    "print(\"\\n[步骤 3/6] 训练集数据处理\")\n",
+    "# 步骤 3: 数据质量检查（必须在预处理之前）\n",
+    "print(\"\\n[步骤 3/7] 数据质量检查\")\n",
+    "print(\"-\" * 60)\n",
+    "print(\"  [说明] 此检查在 fillna 等处理之前执行，用于发现数据问题\")\n",
+    "\n",
+    "print(\"\\n  检查训练集...\")\n",
+    "check_data_quality(train_data, feature_cols, raise_on_error=True)\n",
+    "\n",
+    "if \"val_data\" in locals() and val_data is not None:\n",
+    "    print(\"\\n  检查验证集...\")\n",
+    "    check_data_quality(val_data, feature_cols, raise_on_error=True)\n",
+    "\n",
+    "print(\"\\n  检查测试集...\")\n",
+    "check_data_quality(test_data, feature_cols, raise_on_error=True)\n",
+    "\n",
+    "print(\"  [成功] 数据质量检查通过，未发现异常\")\n"
+   ]
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "# 步骤 4: 训练集数据处理\n",
+    "print(\"\\n[步骤 4/7] 训练集数据处理\")\n",
     "print(\"-\" * 60)\n",
     "fitted_processors = []\n",
     "if processors:\n",
@@ -595,7 +617,7 @@
    "execution_count": null,
    "source": [
     "# 步骤 4: 训练模型\n",
-    "print(\"\\n[步骤 4/6] 训练模型\")\n",
+    "print(\"\\n[步骤 5/7] 训练模型\")\n",
     "print(\"-\" * 60)\n",
     "print(f\"  模型类型: LightGBM\")\n",
     "print(f\"  训练样本数: {len(train_data)}\")\n",
@@ -624,7 +646,7 @@
    "execution_count": null,
    "source": [
     "# 步骤 5: 测试集数据处理\n",
-    "print(\"\\n[步骤 5/6] 测试集数据处理\")\n",
+    "print(\"\\n[步骤 6/7] 测试集数据处理\")\n",
     "print(\"-\" * 60)\n",
     "if processors and test_data is not train_data:\n",
     "    for i, processor in enumerate(fitted_processors, 1):\n",
@@ -647,7 +669,7 @@
    "execution_count": null,
    "source": [
     "# 步骤 6: 生成预测\n",
-    "print(\"\\n[步骤 6/6] 生成预测\")\n",
+    "print(\"\\n[步骤 7/7] 生成预测\")\n",
     "print(\"-\" * 60)\n",
     "X_test = test_data.select(feature_cols)\n",
     "print(f\"  测试样本数: {len(X_test)}\")\n",