refactor(experiment): 提取共用配置到 common 模块

- 将因子定义、日期配置、股票池筛选等提取到 common.py
- 重构 learn_to_rank 和 regression 脚本，统一使用公共配置
- 简化代码结构，消除重复定义

src/experiment/regression.ipynb

@@ -15,7 +15,6 @@
    "source": [
     "import os\n",
     "from datetime import datetime\n",
-    "from typing import List\n",
     "\n",
     "import polars as pl\n",
     "\n",
@@ -25,7 +24,6 @@
     "    LightGBMModel,\n",
     "    STFilter,\n",
     "    StandardScaler,\n",
-    "    # StockFilterConfig,  # 已删除，使用 StockPoolManager + filter_func 替代\n",
     "    StockPoolManager,\n",
     "    Trainer,\n",
     "    Winsorizer,\n",
@@ -33,87 +31,27 @@
     "    check_data_quality,\n",
     ")\n",
     "from src.training.config import TrainingConfig\n",
-    "\n"
-   ]
-  },
-  {
-   "metadata": {},
-   "cell_type": "markdown",
-   "source": "## 2. 定义辅助函数"
-  },
-  {
-   "metadata": {},
-   "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
-   "source": [
-    "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 DSL 表达式注册）\"\"\"\n",
-    "    print(\"=\" * 80)\n",
-    "    print(\"注册因子\")\n",
-    "    print(\"=\" * 80)\n",
     "\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 selected_factors:\n",
-    "        engine.add_factor(name)\n",
-    "        print(f\"  - {name}\")\n",
-    "\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",
-    "    # 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",
-    "    return feature_cols\n",
-    "\n",
-    "\n",
-    "def prepare_data(\n",
-    "    engine: FactorEngine,\n",
-    "    feature_cols: List[str],\n",
-    "    start_date: str,\n",
-    "    end_date: str,\n",
-    ") -> pl.DataFrame:\n",
-    "    print(\"\\n\" + \"=\" * 80)\n",
-    "    print(\"准备数据\")\n",
-    "    print(\"=\" * 80)\n",
-    "\n",
-    "    # 计算因子（全市场数据）\n",
-    "    print(f\"\\n计算因子: {start_date} - {end_date}\")\n",
-    "    factor_names = feature_cols + [LABEL_NAME]  # 包含 label\n",
-    "\n",
-    "    data = engine.compute(\n",
-    "        factor_names=factor_names,\n",
-    "        start_date=start_date,\n",
-    "        end_date=end_date,\n",
-    "    )\n",
-    "\n",
-    "    print(f\"数据形状: {data.shape}\")\n",
-    "    print(f\"数据列: {data.columns}\")\n",
-    "    print(f\"\\n前5行预览:\")\n",
-    "    print(data.head())\n",
-    "\n",
-    "    return data\n",
+    "# 从 common 模块导入共用配置和函数\n",
+    "from src.experiment.common import (\n",
+    "    SELECTED_FACTORS,\n",
+    "    FACTOR_DEFINITIONS,\n",
+    "    get_label_factor,\n",
+    "    register_factors,\n",
+    "    prepare_data,\n",
+    "    TRAIN_START,\n",
+    "    TRAIN_END,\n",
+    "    VAL_START,\n",
+    "    VAL_END,\n",
+    "    TEST_START,\n",
+    "    TEST_END,\n",
+    "    stock_pool_filter,\n",
+    "    STOCK_FILTER_REQUIRED_COLUMNS,\n",
+    "    OUTPUT_DIR,\n",
+    "    SAVE_PREDICTIONS,\n",
+    "    PERSIST_MODEL,\n",
+    "    TOP_N,\n",
+    ")\n",
     "\n"
    ]
   },
@@ -121,9 +59,9 @@
    "metadata": {},
    "cell_type": "markdown",
    "source": [
-    "## 3. 配置参数\n",
+    "## 2. 配置参数\n",
     "#\n",
-    "### 3.1 因子定义"
+    "### 2.1 标签定义"
    ]
   },
   {
@@ -132,177 +70,11 @@
    "outputs": [],
    "execution_count": null,
    "source": [
-    "# 特征因子定义字典：新增因子只需在此处添加一行\n",
+    "# Label 名称（回归任务使用连续收益率）\n",
     "LABEL_NAME = \"future_return_5\"\n",
     "\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",
-    "    \"ma_ratio_5_20\": \"ts_mean(close, 5) / (ts_mean(close, 20) + 1e-8) - 1\",  # 均线发散度\n",
-    "    \"bias_10\": \"close / (ts_mean(close, 10) + 1e-8) - 1\",  # 10日乖离率\n",
-    "    \"high_low_ratio\": \"(close - ts_min(low, 20)) / (ts_max(high, 20) - ts_min(low, 20) + 1e-8)\",  # 威廉指标变形\n",
-    "    \"bbi_ratio\": \"(ts_mean(close, 3) + ts_mean(close, 6) + ts_mean(close, 12) + ts_mean(close, 24)) / (4 * close + 1e-8)\",  # 多空指标比率\n",
-    "    \"return_5\": \"(close / (ts_delay(close, 5) + 1e-8)) - 1\",  # 5日动量\n",
-    "    \"return_20\": \"(close / (ts_delay(close, 20) + 1e-8)) - 1\",  # 20日动量\n",
-    "    # [高阶] Kaufman 趋势效率 (极高价值) - 衡量趋势流畅度，剔除无序震荡\n",
-    "    \"kaufman_ER_20\": \"abs(close - ts_delay(close, 20)) / (ts_sum(abs(close - ts_delay(close, 1)), 20) + 1e-8)\",\n",
-    "    # [高阶] 动量加速度 - 寻找二阶导数大于0，正在加速爆发的股票\n",
-    "    \"mom_acceleration_10_20\": \"(close / (ts_delay(close, 10) + 1e-8) - 1) - (ts_delay(close, 10) / (ts_delay(close, 20) + 1e-8) - 1)\",\n",
-    "    # [高阶] 高点距离衰减 - 衡量套牢盘压力\n",
-    "    \"drawdown_from_high_60\": \"close / (ts_max(high, 60) + 1e-8) - 1\",\n",
-    "    # [高阶] 趋势一致性 - 过去20天内收红的天数比例\n",
-    "    \"up_days_ratio_20\": \"ts_sum(close > ts_delay(close, 1), 20) / 20\",\n",
-    "    # ================= 2. 波动率、风险调整与高阶矩 (Volatility & Risk-Adjusted Returns) =================\n",
-    "    \"volatility_5\": \"ts_std(close, 5)\",\n",
-    "    \"volatility_20\": \"ts_std(close, 20)\",\n",
-    "    \"volatility_ratio\": \"ts_std(close, 5) / (ts_std(close, 20) + 1e-8)\",  # 波动率期限结构\n",
-    "    \"std_return_20\": \"ts_std((close / (ts_delay(close, 1) + 1e-8)) - 1, 20)\",  # 真实收益率波动率\n",
-    "    # [高阶] 夏普趋势比率 - 惩罚暴涨暴跌，奖励稳健爬坡\n",
-    "    \"sharpe_ratio_20\": \"ts_mean(close / (ts_delay(close, 1) + 1e-8) - 1, 20) / (ts_std(close / (ts_delay(close, 1) + 1e-8) - 1, 20) + 1e-8)\",\n",
-    "    # [高阶] 尾部崩盘风险 - 过去一个月最大单日跌幅\n",
-    "    \"min_ret_20\": \"ts_min(close / (ts_delay(close, 1) + 1e-8) - 1, 20)\",\n",
-    "    # [高阶] 波动率挤压比 - 寻找盘整到极致面临变盘的股票 (布林带收口)\n",
-    "    \"volatility_squeeze_5_60\": \"ts_std(close, 5) / (ts_std(close, 60) + 1e-8)\",\n",
-    "    # ================= 3. 日内微观结构与异象 (Intraday Microstructure & Anomalies) =================\n",
-    "    # [高阶] 隔夜与日内背离 - 差值越小说明主力越喜欢在盘中吸筹\n",
-    "    \"overnight_intraday_diff\": \"(open / (ts_delay(close, 1) + 1e-8) - 1) - (close / (open + 1e-8) - 1)\",\n",
-    "    # [高阶] 上影线抛压极值 - 冲高回落被套牢的概率\n",
-    "    \"upper_shadow_ratio\": \"(high - ((open + close + abs(open - close)) / 2)) / (high - low + 1e-8)\",\n",
-    "    # [高阶] 资金沉淀率 - 衡量主力日内高抛低吸洗盘的剧烈程度\n",
-    "    \"capital_retention_20\": \"ts_sum(abs(close - open), 20) / (ts_sum(high - low, 20) + 1e-8)\",\n",
-    "    # [高阶] MAX 彩票效应 - 反转因子，剔除近期有过妖股连板特征的标的\n",
-    "    \"max_ret_20\": \"ts_max(close / (ts_delay(close, 1) + 1e-8) - 1, 20)\",\n",
-    "    # ================= 4. 量能、流动性与量价背离 (Volume, Liquidity & Divergence) =================\n",
-    "    \"volume_ratio_5_20\": \"ts_mean(vol, 5) / (ts_mean(vol, 20) + 1e-8)\",  # 相对放量比\n",
-    "    \"turnover_rate_mean_5\": \"ts_mean(turnover_rate, 5)\",  # 活跃度\n",
-    "    \"turnover_deviation\": \"(turnover_rate - ts_mean(turnover_rate, 10)) / (ts_std(turnover_rate, 10) + 1e-8)\",  # 换手率偏离度\n",
-    "    # [高阶] Amihud 非流动性异象 (绝对核心) - 衡量砸盘/拉升的摩擦成本\n",
-    "    \"amihud_illiq_20\": \"ts_mean(abs(close / (ts_delay(close, 1) + 1e-8) - 1) / (amount + 1e-8), 20)\",\n",
-    "    # [高阶] 换手率惩罚因子 - 换手率忽高忽低说明游资接力，行情极不稳定\n",
-    "    \"turnover_cv_20\": \"ts_std(turnover_rate, 20) / (ts_mean(turnover_rate, 20) + 1e-8)\",\n",
-    "    # [高阶] 纯粹量价相关性 - 检验是否是\"放量上涨，缩量下跌\"的良性多头\n",
-    "    \"pv_corr_20\": \"ts_corr(close / (ts_delay(close, 1) + 1e-8) - 1, vol, 20)\",\n",
-    "    # [高阶] 收盘价与均价背离 - 专门抓尾盘突袭拉升骗线的股票\n",
-    "    \"close_vwap_deviation\": \"close / (amount / (vol * 100 + 1e-8) + 1e-8) - 1\",\n",
-    "    # ================= 5. 基本面财务特征 (Fundamental Quality & Structure) =================\n",
-    "    \"roe\": \"n_income / (total_hldr_eqy_exc_min_int + 1e-8)\",  # 净资产收益率\n",
-    "    \"roa\": \"n_income / (total_assets + 1e-8)\",  # 总资产收益率\n",
-    "    \"profit_margin\": \"n_income / (revenue + 1e-8)\",  # 销售净利率\n",
-    "    \"debt_to_equity\": \"total_liab / (total_hldr_eqy_exc_min_int + 1e-8)\",  # 杠杆率\n",
-    "    \"current_ratio\": \"total_cur_assets / (total_cur_liab + 1e-8)\",  # 短期偿债安全垫\n",
-    "    # [高阶] 利润同比增速 (日频延后252天等于去年同期)\n",
-    "    \"net_profit_yoy\": \"(n_income / (ts_delay(n_income, 252) + 1e-8)) - 1\",\n",
-    "    # [高阶] 营收同比增速\n",
-    "    \"revenue_yoy\": \"(revenue / (ts_delay(revenue, 252) + 1e-8)) - 1\",\n",
-    "    # [高阶] 资产负债表扩张斜率 - 剔除单纯靠举债扩张的公司\n",
-    "    \"healthy_expansion_velocity\": \"(total_assets / (ts_delay(total_assets, 252) + 1e-8) - 1) - (total_liab / (ts_delay(total_liab, 252) + 1e-8) - 1)\",\n",
-    "    # ================= 6. 基本面估值与截面动量共振 (Valuation & Cross-Sectional Ranking) =================\n",
-    "    # 估值水平绝对值 (Tushare 市值单位需要 * 10000 转换为元)\n",
-    "    \"EP\": \"n_income / (total_mv * 10000 + 1e-8)\",  # 盈利收益率 (1/PE)\n",
-    "    \"BP\": \"total_hldr_eqy_exc_min_int / (total_mv * 10000 + 1e-8)\",  # 账面市值比 (1/PB)\n",
-    "    \"CP\": \"n_cashflow_act / (total_mv * 10000 + 1e-8)\",  # 经营现金流收益率 (1/PCF)\n",
-    "    # 全市场截面排名因子\n",
-    "    \"market_cap_rank\": \"cs_rank(total_mv)\",  # 规模因子 (Size)\n",
-    "    \"turnover_rank\": \"cs_rank(turnover_rate)\",\n",
-    "    \"return_5_rank\": \"cs_rank((close / (ts_delay(close, 5) + 1e-8)) - 1)\",\n",
-    "    \"EP_rank\": \"cs_rank(n_income / (total_mv + 1e-8))\",  # 谁最便宜\n",
-    "    # [高阶] 戴维斯双击动量 - 估值相对上一年是否在扩张\n",
-    "    \"pe_expansion_trend\": \"(total_mv / (n_income + 1e-8)) / (ts_delay(total_mv, 60) / (ts_delay(n_income, 60) + 1e-8) + 1e-8) - 1\",\n",
-    "    # [高阶] 业绩与价格背离度 - 截面做差：利润排名全市场第一，但近20日价格排名倒数第一，捕捉被错杀的潜伏股\n",
-    "    \"value_price_divergence\": \"cs_rank((n_income - ts_delay(n_income, 252)) / (abs(ts_delay(n_income, 252)) + 1e-8)) - cs_rank(close / (ts_delay(close, 20) + 1e-8))\",\n",
-    "    # [高阶] 流动性溢价调整后市值 - 识别僵尸大盘股和极度活跃的小微盘\n",
-    "    \"active_market_cap\": \"total_mv * ts_mean(turnover_rate, 20)\",\n",
-    "    \"ebit_rank\": \"cs_rank(ebit)\",\n",
-    "}\n",
-    "\n",
-    "# Label 因子定义（不参与训练，用于计算目标）\n",
-    "LABEL_FACTOR = {\n",
-    "    LABEL_NAME: \"(ts_delay(close, -5) / ts_delay(open, -1)) - 1\",  # 未来5日收益率\n",
-    "}"
-   ]
-  },
-  {
-   "metadata": {},
-   "cell_type": "markdown",
-   "source": "### 3.2 训练参数配置"
-  },
-  {
-   "metadata": {},
-   "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
-   "source": [
-    "# 日期范围配置（正确的 train/val/test 三分法）\n",
-    "# Train: 用于训练模型参数\n",
-    "# Val: 用于验证/早停/调参（位于 train 之后，test 之前）\n",
-    "# Test: 仅用于最终评估，完全独立于训练过程\n",
-    "TRAIN_START = \"20200101\"\n",
-    "TRAIN_END = \"20231231\"\n",
-    "VAL_START = \"20240101\"\n",
-    "VAL_END = \"20241231\"\n",
-    "TEST_START = \"20250101\"\n",
-    "TEST_END = \"20261231\"\n",
+    "# 获取 Label 因子定义\n",
+    "LABEL_FACTOR = get_label_factor(LABEL_NAME)\n",
     "\n",
     "# 模型参数配置\n",
     "MODEL_PARAMS = {\n",
@@ -326,60 +98,7 @@
     "    # 数值稳定性\n",
     "    \"verbose\": -1,\n",
     "    \"random_state\": 42,\n",
-    "}\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",
-    "# 筛选函数接收单日 DataFrame，返回布尔 Series\n",
-    "#\n",
-    "# 筛选逻辑（针对单日数据）：\n",
-    "# 1. 先排除创业板、科创板、北交所（ST过滤由STFilter组件处理）\n",
-    "# 2. 然后选取市值最小的500只股票\n",
-    "def stock_pool_filter(df: pl.DataFrame) -> pl.Series:\n",
-    "    \"\"\"股票池筛选函数（单日数据）\n",
-    "\n",
-    "    筛选条件：\n",
-    "    1. 排除创业板（代码以 300 开头）\n",
-    "    2. 排除科创板（代码以 688 开头）\n",
-    "    3. 排除北交所（代码以 8、9 或 4 开头）\n",
-    "    4. 选取当日市值最小的500只股票\n",
-    "    \"\"\"\n",
-    "    # 代码筛选（排除创业板、科创板、北交所）\n",
-    "    code_filter = (\n",
-    "        ~df[\"ts_code\"].str.starts_with(\"30\")  # 排除创业板\n",
-    "        & ~df[\"ts_code\"].str.starts_with(\"68\")  # 排除科创板\n",
-    "        & ~df[\"ts_code\"].str.starts_with(\"8\")  # 排除北交所\n",
-    "        & ~df[\"ts_code\"].str.starts_with(\"9\")  # 排除北交所\n",
-    "        & ~df[\"ts_code\"].str.starts_with(\"4\")  # 排除北交所\n",
-    "    )\n",
-    "\n",
-    "    # 在已筛选的股票中，选取市值最小的500只\n",
-    "    # 按市值升序排序，取前500\n",
-    "    valid_df = df.filter(code_filter)\n",
-    "    n = min(1000, len(valid_df))\n",
-    "    small_cap_codes = valid_df.sort(\"total_mv\").head(n)[\"ts_code\"]\n",
-    "\n",
-    "    # 返回布尔 Series：是否在被选中的股票中\n",
-    "    return df[\"ts_code\"].is_in(small_cap_codes)\n",
-    "\n",
-    "\n",
-    "# 定义筛选所需的基础列\n",
-    "STOCK_FILTER_REQUIRED_COLUMNS = [\"total_mv\"]  # ST过滤由STFilter组件处理\n",
-    "\n",
-    "# 可选：定义筛选所需的因子（如果需要用因子进行筛选）\n",
-    "# STOCK_FILTER_REQUIRED_FACTORS = {\n",
-    "#     \"market_cap_rank\": \"cs_rank(total_mv)\",\n",
-    "# }\n",
-    "\n",
-    "\n",
-    "# 输出配置（相对于本文件所在目录）\n",
-    "OUTPUT_DIR = \"output\"\n",
-    "SAVE_PREDICTIONS = True\n",
-    "PERSIST_MODEL = False\n",
-    "\n",
-    "# Top N 配置：每日推荐股票数量\n",
-    "TOP_N = 5  # 可调整为 10, 20 等"
+    "}"
    ]
   },
   {
@@ -420,6 +139,7 @@
     "    feature_cols=feature_cols,\n",
     "    start_date=TRAIN_START,\n",
     "    end_date=TEST_END,\n",
+    "    label_name=LABEL_NAME,\n",
     ")\n",
     "\n",
     "# 4. 打印配置信息\n",
@@ -515,8 +235,6 @@
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "# 步骤 2: 划分训练/验证/测试集（正确的三分法）\n",
     "print(\"\\n[步骤 2/6] 划分训练集、验证集和测试集\")\n",
@@ -550,7 +268,9 @@
     "    train_data = filtered_data\n",
     "    test_data = filtered_data\n",
     "    print(\"  未配置划分器，全部作为训练集\")"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -579,8 +299,6 @@
   {
    "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",
@@ -608,7 +326,9 @@
     "    null_count = train_data[col].null_count()\n",
     "    if null_count > 0:\n",
     "        print(f\"      {col}: {null_count} ({null_count / len(train_data) * 100:.2f}%)\")"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -828,8 +548,6 @@
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "print(\"\\n\" + \"=\" * 80)\n",
     "print(\"训练结果\")\n",
@@ -855,7 +573,9 @@
     "sample_data = results.filter(results[\"trade_date\"] == sample_date).head(10)\n",
     "print(f\"\\n示例日期 {sample_date} 的前10条预测:\")\n",
     "print(sample_data.select([\"ts_code\", \"trade_date\", target_col, \"prediction\"]))"
-   ]
+   ],
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {},
@@ -978,6 +698,61 @@
     "- 可以帮助理解哪些因子最有效"
    ]
   },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "print(\"绘制特征重要性...\")\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(10, 8))\n",
+    "lgb.plot_importance(\n",
+    "    booster,\n",
+    "    max_num_features=20,\n",
+    "    importance_type=\"gain\",\n",
+    "    title=\"Feature Importance (Gain)\",\n",
+    "    ax=ax,\n",
+    ")\n",
+    "ax.set_xlabel(\"Importance (Gain)\")\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "\n",
+    "# 打印重要性排名\n",
+    "importance_gain = pd.Series(\n",
+    "    booster.feature_importance(importance_type=\"gain\"), index=feature_cols\n",
+    ").sort_values(ascending=False)\n",
+    "\n",
+    "print(\"\\n[特征重要性排名 - Gain]\")\n",
+    "print(importance_gain)\n",
+    "\n",
+    "# 识别低重要性特征\n",
+    "zero_importance = importance_gain[importance_gain == 0].index.tolist()\n",
+    "if zero_importance:\n",
+    "    print(f\"\\n[低重要性特征] 以下{len(zero_importance)}个特征重要性为0，可考虑删除:\")\n",
+    "    for feat in zero_importance:\n",
+    "        print(f\"  - {feat}\")\n",
+    "else:\n",
+    "    print(\"\\n所有特征都有一定重要性\")\n"
+   ]
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": [
+    "# 导入可视化库\n",
+    "import matplotlib.pyplot as plt\n",
+    "import lightgbm as lgb\n",
+    "import pandas as pd\n",
+    "\n",
+    "# 从封装的model中取出底层Booster\n",
+    "booster = model.model\n",
+    "print(f\"模型类型: {type(booster)}\")\n",
+    "print(f\"特征数量: {len(feature_cols)}\")"
+   ]
+  },
   {
    "metadata": {},
    "cell_type": "code",