refactor(factors): 简化 add_factor API 并默认启用 metadata

- 合并 add_factor_by_name 到 add_factor，支持三种调用方式
- FactorManager 构造函数改为可选参数，使用默认路径
- FactorEngine 默认启用 metadata，无需手动配置路径

src/experiment/regression.ipynb

@@ -47,29 +47,40 @@
    "execution_count": null,
    "source": [
     "def create_factors_with_metadata(\n",
-    "    engine: FactorEngine, factor_definitions: dict, label_factor: dict\n",
+    "    engine: FactorEngine,\n",
+    "    selected_factors: List[str],\n",
+    "    factor_definitions: dict,\n",
+    "    label_factor: dict,\n",
     ") -> List[str]:\n",
-    "    \"\"\"使用 metadata 注册因子（特征因子通过名称注册，label 因子通过表达式注册）\"\"\"\n",
+    "    \"\"\"注册因子（SELECTED_FACTORS 从 metadata 查询，FACTOR_DEFINITIONS 用表达式注册）\"\"\"\n",
     "    print(\"=\" * 80)\n",
-    "    print(\"使用 metadata 注册因子\")\n",
+    "    print(\"注册因子\")\n",
     "    print(\"=\" * 80)\n",
     "\n",
-    "    # 注册所有特征因子（通过 metadata 名称）\n",
+    "    # 注册 SELECTED_FACTORS 中的因子（已在 metadata 中）\n",
     "    print(\"\\n注册特征因子（从 metadata）:\")\n",
-    "    for name in factor_definitions.keys():\n",
-    "        engine.add_factor_by_name(name)\n",
+    "    for name in selected_factors:\n",
+    "        engine.add_factor(name)\n",
     "        print(f\"  - {name}\")\n",
     "\n",
-    "    # 注册 label 因子（通过表达式，因为 label 不在 metadata 中）\n",
+    "    # 注册 FACTOR_DEFINITIONS 中的因子（通过表达式，尚未在 metadata 中）\n",
+    "    print(\"\\n注册特征因子（表达式）:\")\n",
+    "    for name, expr in factor_definitions.items():\n",
+    "        engine.add_factor(name, expr)\n",
+    "        print(f\"  - {name}: {expr}\")\n",
+    "\n",
+    "    # 注册 label 因子（通过表达式）\n",
     "    print(\"\\n注册 Label 因子（表达式）:\")\n",
     "    for name, expr in label_factor.items():\n",
     "        engine.add_factor(name, expr)\n",
     "        print(f\"  - {name}: {expr}\")\n",
     "\n",
-    "    # 从字典自动获取特征列\n",
-    "    feature_cols = list(factor_definitions.keys())\n",
+    "    # 特征列 = SELECTED_FACTORS + FACTOR_DEFINITIONS 的 keys\n",
+    "    feature_cols = selected_factors + list(factor_definitions.keys())\n",
     "\n",
     "    print(f\"\\n特征因子数: {len(feature_cols)}\")\n",
+    "    print(f\"  - 来自 metadata: {len(selected_factors)}\")\n",
+    "    print(f\"  - 来自表达式: {len(factor_definitions)}\")\n",
     "    print(f\"Label: {list(label_factor.keys())[0]}\")\n",
     "    print(f\"已注册因子总数: {len(engine.list_registered())}\")\n",
     "\n",
@@ -123,7 +134,67 @@
     "# 特征因子定义字典：新增因子只需在此处添加一行\n",
     "LABEL_NAME = \"future_return_5\"\n",
     "\n",
-    "FACTOR_DEFINITIONS = FACTOR_DICT = {\n",
+    "# 当前选择的因子列表（从 FACTOR_DEFINITIONS 中选择要使用的因子）\n",
+    "SELECTED_FACTORS = [\n",
+    "    # ================= 1. 价格、趋势与路径依赖 =================\n",
+    "    \"ma_5\",\n",
+    "    \"ma_20\",\n",
+    "    \"ma_ratio_5_20\",\n",
+    "    \"bias_10\",\n",
+    "    \"high_low_ratio\",\n",
+    "    \"bbi_ratio\",\n",
+    "    \"return_5\",\n",
+    "    \"return_20\",\n",
+    "    \"kaufman_ER_20\",\n",
+    "    \"mom_acceleration_10_20\",\n",
+    "    \"drawdown_from_high_60\",\n",
+    "    \"up_days_ratio_20\",\n",
+    "    # ================= 2. 波动率、风险调整与高阶矩 =================\n",
+    "    \"volatility_5\",\n",
+    "    \"volatility_20\",\n",
+    "    \"volatility_ratio\",\n",
+    "    \"std_return_20\",\n",
+    "    \"sharpe_ratio_20\",\n",
+    "    \"min_ret_20\",\n",
+    "    \"volatility_squeeze_5_60\",\n",
+    "    # ================= 3. 日内微观结构与异象 =================\n",
+    "    \"overnight_intraday_diff\",\n",
+    "    \"upper_shadow_ratio\",\n",
+    "    \"capital_retention_20\",\n",
+    "    \"max_ret_20\",\n",
+    "    # ================= 4. 量能、流动性与量价背离 =================\n",
+    "    \"volume_ratio_5_20\",\n",
+    "    \"turnover_rate_mean_5\",\n",
+    "    \"turnover_deviation\",\n",
+    "    \"amihud_illiq_20\",\n",
+    "    \"turnover_cv_20\",\n",
+    "    \"pv_corr_20\",\n",
+    "    \"close_vwap_deviation\",\n",
+    "    # ================= 5. 基本面财务特征 =================\n",
+    "    \"roe\",\n",
+    "    \"roa\",\n",
+    "    \"profit_margin\",\n",
+    "    \"debt_to_equity\",\n",
+    "    \"current_ratio\",\n",
+    "    \"net_profit_yoy\",\n",
+    "    \"revenue_yoy\",\n",
+    "    \"healthy_expansion_velocity\",\n",
+    "    # ================= 6. 基本面估值与截面动量共振 =================\n",
+    "    \"EP\",\n",
+    "    \"BP\",\n",
+    "    \"CP\",\n",
+    "    \"market_cap_rank\",\n",
+    "    \"turnover_rank\",\n",
+    "    \"return_5_rank\",\n",
+    "    \"EP_rank\",\n",
+    "    \"pe_expansion_trend\",\n",
+    "    \"value_price_divergence\",\n",
+    "    \"active_market_cap\",\n",
+    "    \"ebit_rank\",\n",
+    "]\n",
+    "\n",
+    "# 因子定义字典（完整因子库）\n",
+    "FACTOR_DEFINITIONS = {\n",
     "    # ================= 1. 价格、趋势与路径依赖 (Trend, Momentum & Path Dependency) =================\n",
     "    \"ma_5\": \"ts_mean(close, 5)\",\n",
     "    \"ma_20\": \"ts_mean(close, 20)\",\n",
@@ -338,7 +409,9 @@
     "\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(engine, FACTOR_DEFINITIONS, LABEL_FACTOR)\n",
+    "feature_cols = create_factors_with_metadata(\n",
+    "    engine, SELECTED_FACTORS, FACTOR_DEFINITIONS, LABEL_FACTOR\n",
+    ")\n",
     "target_col = LABEL_NAME\n",
     "\n",
     "# 3. 准备数据（使用模块级别的日期配置）\n",