2026-03-06 20:57:27 +08:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. 导入依赖"
]
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:04.748286Z",
"start_time": "2026-03-09T14:21:04.170825Z"
2026-03-06 20:57:27 +08:00
}
},
"source": [
"import os\n",
"from datetime import datetime\n",
"from typing import List\n",
"\n",
"import polars as pl\n",
"\n",
"from src.factors import FactorEngine\n",
"from src.training import (\n",
" DateSplitter,\n",
" LightGBMModel,\n",
" STFilter,\n",
" StandardScaler,\n",
2026-03-09 22:33:41 +08:00
" # StockFilterConfig, # 已删除，使用 StockPoolManager + filter_func 替代\n",
2026-03-06 20:57:27 +08:00
" StockPoolManager,\n",
" Trainer,\n",
" Winsorizer,\n",
" NullFiller,\n",
")\n",
"from src.training.config import TrainingConfig"
],
"outputs": [],
2026-03-09 22:33:41 +08:00
"execution_count": 1
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. 定义辅助函数"
]
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:04.761117Z",
"start_time": "2026-03-09T14:21:04.756245Z"
2026-03-06 20:57:27 +08:00
}
},
"cell_type": "code",
"source": [
"def create_factors_with_strings(engine: FactorEngine, factor_definitions: dict, label_factor: dict) -> List[str]:\n",
" print(\"=\" * 80)\n",
" print(\"使用字符串表达式定义因子\")\n",
" print(\"=\" * 80)\n",
"\n",
" # 注册所有特征因子\n",
" print(\"\\n注册特征因子:\")\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\n",
" print(\"\\n注册 Label 因子:\")\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",
"\n",
" print(f\"\\n特征因子数: {len(feature_cols)}\")\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",
2026-03-09 22:33:41 +08:00
" engine: FactorEngine,\n",
" feature_cols: List[str],\n",
" start_date: str,\n",
" end_date: str,\n",
2026-03-06 20:57:27 +08:00
") -> 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",
2026-03-08 14:12:03 +08:00
" factor_names = feature_cols + [LABEL_NAME] # 包含 label\n",
2026-03-06 20:57:27 +08:00
"\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"
],
"outputs": [],
2026-03-09 22:33:41 +08:00
"execution_count": 2
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. 配置参数\n",
"\n",
"### 3.1 因子定义"
]
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:04.770022Z",
"start_time": "2026-03-09T14:21:04.766036Z"
2026-03-06 20:57:27 +08:00
}
},
"cell_type": "code",
"source": [
"# 特征因子定义字典：新增因子只需在此处添加一行\n",
2026-03-08 14:12:03 +08:00
"LABEL_NAME = 'future_return_5'\n",
"\n",
2026-03-06 20:57:27 +08:00
"FACTOR_DEFINITIONS = {\n",
2026-03-09 22:33:41 +08:00
" # 1. 趋势因子\n",
2026-03-08 23:14:18 +08:00
" \"ma_5\": \"ts_mean(close, 5)\",\n",
" \"ma_20\": \"ts_mean(close, 20)\",\n",
2026-03-09 22:33:41 +08:00
" \"ma_ratio_5_20\": \"ts_mean(close, 5) / (ts_mean(close, 20) + 1e-8) - 1\",\n",
" \"bias_10\": \"close / (ts_mean(close, 10) + 1e-8) - 1\",\n",
" \"bbi_ratio\": \"(ts_mean(close, 3) + ts_mean(close, 6) + ts_mean(close, 12) + ts_mean(close, 24)) / (4 * close + 1e-8)\",\n",
"\n",
" # 2. 动量与反转\n",
" \"return_5\": \"(close / ts_delay(close, 5)) - 1\",\n",
2026-03-06 20:57:27 +08:00
" \"return_20\": \"(close / ts_delay(close, 20)) - 1\",\n",
2026-03-09 22:33:41 +08:00
" \"momentum_accel\": \"(close / ts_delay(close, 5)) - (close / ts_delay(close, 20))\",\n",
" \"volatility_ratio\": \"ts_std(close, 5) / (ts_std(close, 20) + 1e-8)\",\n",
" \"reversal_1\": \"close / ts_delay(close, 1) - 1\",\n",
"\n",
" # 3. 量能与微观结构\n",
" \"volume_ratio\": \"ts_mean(vol, 5) / (ts_mean(vol, 20) + 1e-8)\",\n",
" \"turnover_rate_mean_5\": \"ts_mean(turnover_rate, 5)\",\n",
" # \"vol_price_corr\": \"ts_corr(close, vol, 10)\",\n",
" \"turnover_deviation\": \"(turnover_rate - ts_mean(turnover_rate, 10)) / (ts_std(turnover_rate, 10) + 1e-8)\",\n",
"\n",
" # 4. 财务动量与质量\n",
" \"net_profit_growth\": \"(n_income / ts_delay(n_income, 4)) - 1\",\n",
" \"revenue_growth\": \"(revenue / ts_delay(revenue, 4)) - 1\",\n",
" \"roe\": \"n_income / (total_hldr_eqy_exc_min_int + 1e-8)\",\n",
" \"roe_delta\": \"roe - ts_delay(roe, 4)\",\n",
" \"debt_to_equity\": \"total_liab / (total_hldr_eqy_exc_min_int + 1e-8)\",\n",
" \"current_ratio\": \"total_cur_assets / (total_cur_liab + 1e-8)\",\n",
"\n",
" # 5. 财务估值与排名\n",
" \"EP_rank\": \"cs_rank(n_income / (total_mv * 10000 + 1e-8))\",\n",
" \"BP_rank\": \"cs_rank(total_hldr_eqy_exc_min_int / (total_mv * 10000 + 1e-8))\",\n",
" \"market_cap_rank\": \"cs_rank(total_mv)\",\n",
" \"cashflow_act_rank\": \"cs_rank(n_cashflow_act)\",\n",
" \"ebitda_rank\": \"cs_rank(ebitda)\"\n",
2026-03-06 20:57:27 +08:00
"}\n",
"\n",
"# Label 因子定义（不参与训练，用于计算目标）\n",
"LABEL_FACTOR = {\n",
2026-03-09 22:33:41 +08:00
" LABEL_NAME: \"(ts_delay(close, -5) / ts_delay(open, -1)) - 1\", # 未来5日收益率\n",
2026-03-06 20:57:27 +08:00
"}"
],
"outputs": [],
2026-03-09 22:33:41 +08:00
"execution_count": 3
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 3.2 训练参数配置"
]
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:04.778317Z",
"start_time": "2026-03-09T14:21:04.773776Z"
2026-03-06 20:57:27 +08:00
}
},
"source": [
2026-03-08 01:09:47 +08:00
"# 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: 仅用于最终评估，完全独立于训练过程\n",
2026-03-06 20:57:27 +08:00
"TRAIN_START = \"20200101\"\n",
2026-03-08 01:09:47 +08:00
"TRAIN_END = \"20231231\"\n",
"VAL_START = \"20240101\"\n",
"VAL_END = \"20241231\"\n",
2026-03-06 20:57:27 +08:00
"TEST_START = \"20250101\"\n",
2026-03-09 22:33:41 +08:00
"TEST_END = \"20261231\"\n",
2026-03-06 20:57:27 +08:00
"\n",
"# 模型参数配置\n",
"MODEL_PARAMS = {\n",
" \"objective\": \"regression\",\n",
" \"metric\": \"mae\", # 改为 MAE，
" # 树结构控制（防过拟合核心）\n",
" \"num_leaves\": 20, # 从31降为20，
2026-03-09 22:33:41 +08:00
" \"max_depth\": 5, # 显式限制深度，防止过度拟合噪声\n",
2026-03-06 20:57:27 +08:00
" \"min_child_samples\": 50, # 叶子最小样本数，防止学习极端样本\n",
" \"min_child_weight\": 0.001,\n",
" # 学习参数\n",
" \"learning_rate\": 0.01, # 降低学习率，配合更多树\n",
" \"n_estimators\": 1000, # 增加树数量，配合早停\n",
" # 采样策略（关键防过拟合）\n",
" \"subsample\": 0.8, # 每棵树随机采样80%数据（行采样）\n",
" \"subsample_freq\": 5, # 每5轮迭代进行一次 subsample\n",
" \"colsample_bytree\": 0.8, # 每棵树随机选择80%特征（列采样）\n",
" # 正则化\n",
" \"reg_alpha\": 0.1, # L1正则，
" \"reg_lambda\": 1.0, # L2正则，
" # 数值稳定性\n",
" \"verbose\": -1,\n",
" \"random_state\": 42,\n",
"}\n",
"\n",
"# 数据处理器配置\n",
"PROCESSOR_CONFIGS = [\n",
" {\"name\": \"winsorizer\", \"params\": {\"lower\": 0.01, \"upper\": 0.99}},\n",
" {\"name\": \"cs_standard_scaler\", \"params\": {}},\n",
"]\n",
"\n",
2026-03-09 22:33:41 +08:00
"\n",
"# 股票池筛选函数\n",
"# 使用新的 StockPoolManager API：
"# 筛选函数接收单日 DataFrame，
"#\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（ ）
"# 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(\"300\") & # 排除创业板\n",
" ~df[\"ts_code\"].str.starts_with(\"688\") & # 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，
" # 按市值升序排序，
" 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：
" 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",
2026-03-06 20:57:27 +08:00
"\n",
"# 输出配置（相对于本文件所在目录）\n",
"OUTPUT_DIR = \"output\"\n",
"SAVE_PREDICTIONS = True\n",
2026-03-08 11:46:30 +08:00
"PERSIST_MODEL = False\n",
"\n",
"# Top N 配置：每日推荐股票数量\n",
2026-03-08 20:58:35 +08:00
"TOP_N = 5 # 可调整为 10, 20 等"
2026-03-06 20:57:27 +08:00
],
"outputs": [],
2026-03-09 22:33:41 +08:00
"execution_count": 4
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. 训练流程\n",
"\n",
"### 4.1 初始化组件"
]
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:11.178131Z",
"start_time": "2026-03-09T14:21:04.783890Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"source": [
"print(\"\\n\" + \"=\" * 80)\n",
"print(\"LightGBM 回归模型训练\")\n",
"print(\"=\" * 80)\n",
"\n",
"# 1. 创建 FactorEngine\n",
"print(\"\\n[1] 创建 FactorEngine\")\n",
"engine = FactorEngine()\n",
"\n",
"# 2. 使用字符串表达式定义因子\n",
"print(\"\\n[2] 定义因子（字符串表达式）\")\n",
"feature_cols = create_factors_with_strings(engine, FACTOR_DEFINITIONS, LABEL_FACTOR)\n",
2026-03-08 14:12:03 +08:00
"target_col = LABEL_NAME\n",
2026-03-06 20:57:27 +08:00
"\n",
"# 3. 准备数据（使用模块级别的日期配置）\n",
"print(\"\\n[3] 准备数据\")\n",
"\n",
"data = prepare_data(\n",
" engine=engine,\n",
" feature_cols=feature_cols,\n",
" start_date=TRAIN_START,\n",
" end_date=TEST_END,\n",
")\n",
"\n",
"# 4. 打印配置信息\n",
"print(f\"\\n[配置] 训练期: {TRAIN_START} - {TRAIN_END}\")\n",
2026-03-08 01:09:47 +08:00
"print(f\"[配置] 验证期: {VAL_START} - {VAL_END}\")\n",
2026-03-06 20:57:27 +08:00
"print(f\"[配置] 测试期: {TEST_START} - {TEST_END}\")\n",
"print(f\"[配置] 特征数: {len(feature_cols)}\")\n",
"print(f\"[配置] 目标变量: {target_col}\")\n",
"\n",
"# 5. 创建模型\n",
"model = LightGBMModel(params=MODEL_PARAMS)\n",
"\n",
"# 6. 创建数据处理器\n",
"processors = [\n",
" NullFiller(strategy=\"mean\"),\n",
" Winsorizer(**PROCESSOR_CONFIGS[0][\"params\"]),\n",
" StandardScaler(exclude_cols=[\"ts_code\", \"trade_date\", target_col]),\n",
"]\n",
"\n",
2026-03-08 01:09:47 +08:00
"# 7. 创建数据划分器（正确的 train/val/test 三分法）\n",
"# Train: 训练模型参数 | Val: 验证/早停 | Test: 最终评估\n",
2026-03-06 20:57:27 +08:00
"splitter = DateSplitter(\n",
" train_start=TRAIN_START,\n",
" train_end=TRAIN_END,\n",
2026-03-08 01:09:47 +08:00
" val_start=VAL_START,\n",
" val_end=VAL_END,\n",
2026-03-06 20:57:27 +08:00
" test_start=TEST_START,\n",
" test_end=TEST_END,\n",
")\n",
"\n",
"# 8. 创建股票池管理器\n",
2026-03-09 22:33:41 +08:00
"# 使用新的 API：
2026-03-06 20:57:27 +08:00
"pool_manager = StockPoolManager(\n",
2026-03-09 22:33:41 +08:00
" filter_func=stock_pool_filter,\n",
" required_columns=STOCK_FILTER_REQUIRED_COLUMNS, # 筛选所需的额外列\n",
" # required_factors=STOCK_FILTER_REQUIRED_FACTORS, # 可选：筛选所需的因子\n",
2026-03-06 20:57:27 +08:00
" data_router=engine.router,\n",
")\n",
2026-03-09 22:33:41 +08:00
"print(\"[股票池筛选] 使用自定义函数进行股票池筛选\")\n",
"print(f\"[股票池筛选] 所需基础列: {STOCK_FILTER_REQUIRED_COLUMNS}\")\n",
"print(\"[股票池筛选] 筛选逻辑: 排除创业板/科创板/北交所后，
"# print(f\"[股票池筛选] 所需因子: {list(STOCK_FILTER_REQUIRED_FACTORS.keys())}\")\n",
2026-03-06 20:57:27 +08:00
"\n",
"# 9. 创建 ST 股票过滤器\n",
"st_filter = STFilter(\n",
" data_router=engine.router,\n",
")\n",
"\n",
"# 10. 创建训练器\n",
"trainer = Trainer(\n",
" model=model,\n",
" pool_manager=pool_manager,\n",
" processors=processors,\n",
2026-03-09 22:33:41 +08:00
" filters=[st_filter], # 使用STFilter过滤ST股票\n",
2026-03-06 20:57:27 +08:00
" splitter=splitter,\n",
" target_col=target_col,\n",
" feature_cols=feature_cols,\n",
" persist_model=PERSIST_MODEL,\n",
")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"================================================================================\n",
"LightGBM 回归模型训练\n",
"================================================================================\n",
"\n",
"[1] 创建 FactorEngine\n",
"\n",
"[2] 定义因子（字符串表达式）\n",
"================================================================================\n",
"使用字符串表达式定义因子\n",
"================================================================================\n",
"\n",
"注册特征因子:\n",
2026-03-08 23:14:18 +08:00
" - 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\n",
" - bias_10: close / (ts_mean(close, 10) + 1e-8) - 1\n",
" - bbi_ratio: (ts_mean(close, 3) + ts_mean(close, 6) + ts_mean(close, 12) + ts_mean(close, 24)) / (4 * close + 1e-8)\n",
" - return_5: (close / ts_delay(close, 5)) - 1\n",
2026-03-06 20:57:27 +08:00
" - return_20: (close / ts_delay(close, 20)) - 1\n",
2026-03-09 22:33:41 +08:00
" - momentum_accel: (close / ts_delay(close, 5)) - (close / ts_delay(close, 20))\n",
2026-03-08 23:14:18 +08:00
" - volatility_ratio: ts_std(close, 5) / (ts_std(close, 20) + 1e-8)\n",
2026-03-09 22:33:41 +08:00
" - reversal_1: close / ts_delay(close, 1) - 1\n",
" - volume_ratio: ts_mean(vol, 5) / (ts_mean(vol, 20) + 1e-8)\n",
2026-03-08 14:12:03 +08:00
" - turnover_rate_mean_5: ts_mean(turnover_rate, 5)\n",
2026-03-08 23:14:18 +08:00
" - turnover_deviation: (turnover_rate - ts_mean(turnover_rate, 10)) / (ts_std(turnover_rate, 10) + 1e-8)\n",
2026-03-09 22:33:41 +08:00
" - net_profit_growth: (n_income / ts_delay(n_income, 4)) - 1\n",
" - revenue_growth: (revenue / ts_delay(revenue, 4)) - 1\n",
" - roe: n_income / (total_hldr_eqy_exc_min_int + 1e-8)\n",
" - roe_delta: roe - ts_delay(roe, 4)\n",
" - debt_to_equity: total_liab / (total_hldr_eqy_exc_min_int + 1e-8)\n",
" - current_ratio: total_cur_assets / (total_cur_liab + 1e-8)\n",
" - EP_rank: cs_rank(n_income / (total_mv * 10000 + 1e-8))\n",
" - BP_rank: cs_rank(total_hldr_eqy_exc_min_int / (total_mv * 10000 + 1e-8))\n",
2026-03-08 23:14:18 +08:00
" - market_cap_rank: cs_rank(total_mv)\n",
2026-03-09 22:33:41 +08:00
" - cashflow_act_rank: cs_rank(n_cashflow_act)\n",
" - ebitda_rank: cs_rank(ebitda)\n",
2026-03-06 20:57:27 +08:00
"\n",
"注册 Label 因子:\n",
2026-03-09 22:33:41 +08:00
" - future_return_5: (ts_delay(close, -5) / ts_delay(open, -1)) - 1\n",
2026-03-06 20:57:27 +08:00
"\n",
2026-03-09 22:33:41 +08:00
"特征因子数: 24\n",
2026-03-08 14:12:03 +08:00
"Label: future_return_5\n",
2026-03-09 22:33:41 +08:00
"已注册因子总数: 25\n",
2026-03-06 20:57:27 +08:00
"\n",
"[3] 准备数据\n",
"\n",
"================================================================================\n",
"准备数据\n",
"================================================================================\n",
"\n",
2026-03-09 22:33:41 +08:00
"计算因子: 20200101 - 20261231\n",
"[FinancialLoader] 加载 financial_fina_indicator 失败: Binder Error: Referenced column \"f_ann_date\" not found in FROM clause!\n",
"Candidate bindings: \"ann_date\", \"end_date\", \"ocf_to_debt\", \"arturn_days\", \"nca_to_assets\"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"D:\\PyProject\\ProStock\\src\\data\\financial_loader.py:148: UserWarning: Sortedness of columns cannot be checked when 'by' groups provided\n",
" merged = df_price.join_asof(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"数据形状: (7255513, 41)\n",
"数据列: ['ts_code', 'trade_date', 'turnover_rate', 'open', 'vol', 'close', 'total_mv', 'f_ann_date', 'revenue', 'n_income', 'total_hldr_eqy_exc_min_int', 'total_cur_assets', 'total_liab', 'total_cur_liab', 'roe', 'ebitda', 'n_cashflow_act', 'ma_5', 'ma_20', 'ma_ratio_5_20', 'bias_10', 'bbi_ratio', 'return_5', 'return_20', 'momentum_accel', 'volatility_ratio', 'reversal_1', 'volume_ratio', 'turnover_rate_mean_5', 'turnover_deviation', 'net_profit_growth', 'revenue_growth', 'roe_delta', 'debt_to_equity', 'current_ratio', 'EP_rank', 'BP_rank', 'market_cap_rank', 'cashflow_act_rank', 'ebitda_rank', 'future_return_5']\n",
2026-03-06 20:57:27 +08:00
"\n",
"前5行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (5, 41)\n",
"┌───────────┬────────────┬───────────┬─────────┬───┬───────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_date ┆ turnover_ ┆ open ┆ … ┆ market_ca ┆ cashflow_ ┆ ebitda_ra ┆ future_re │\n",
"│ --- ┆ --- ┆ rate ┆ --- ┆ ┆ p_rank ┆ act_rank ┆ nk ┆ turn_5 │\n",
"│ str ┆ str ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪════════════╪═══════════╪═════════╪═══╪═══════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 000001.SZ ┆ 20200102 ┆ 0.7885 ┆ 1817.67 ┆ … ┆ 0.993583 ┆ 0.997594 ┆ null ┆ -0.008857 │\n",
"│ 000001.SZ ┆ 20200103 ┆ 0.5752 ┆ 1849.33 ┆ … ┆ 0.993585 ┆ 0.997594 ┆ null ┆ -0.01881 │\n",
"│ 000001.SZ ┆ 20200106 ┆ 0.4442 ┆ 1856.97 ┆ … ┆ 0.993588 ┆ 0.997596 ┆ null ┆ -0.008171 │\n",
"│ 000001.SZ ┆ 20200107 ┆ 0.3755 ┆ 1870.07 ┆ … ┆ 0.993588 ┆ 0.997596 ┆ null ┆ -0.014117 │\n",
"│ 000001.SZ ┆ 20200108 ┆ 0.4369 ┆ 1855.88 ┆ … ┆ 0.993586 ┆ 0.997595 ┆ null ┆ -0.017252 │\n",
"└───────────┴────────────┴───────────┴─────────┴───┴───────────┴───────────┴───────────┴───────────┘\n",
2026-03-06 20:57:27 +08:00
"\n",
2026-03-08 01:09:47 +08:00
"[配置] 训练期: 20200101 - 20231231\n",
"[配置] 验证期: 20240101 - 20241231\n",
2026-03-09 22:33:41 +08:00
"[配置] 测试期: 20250101 - 20261231\n",
"[配置] 特征数: 24\n",
"[配置] 目标变量: future_return_5\n",
"[股票池筛选] 使用自定义函数进行股票池筛选\n",
"[股票池筛选] 所需基础列: ['total_mv']\n",
"[股票池筛选] 筛选逻辑: 排除创业板/科创板/北交所后，
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 5
2026-03-06 20:57:27 +08:00
},
{
"metadata": {},
2026-03-09 22:33:41 +08:00
"cell_type": "markdown",
"source": "### 4.2 执行训练"
2026-03-06 20:57:27 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:13.936037Z",
"start_time": "2026-03-09T14:21:11.188410Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"source": [
"print(\"\\n\" + \"=\" * 80)\n",
"print(\"开始训练\")\n",
"print(\"=\" * 80)\n",
"\n",
"# 步骤 1: 股票池筛选\n",
"print(\"\\n[步骤 1/6] 股票池筛选\")\n",
"print(\"-\" * 60)\n",
"if pool_manager:\n",
" print(\" 执行每日独立筛选股票池...\")\n",
" filtered_data = pool_manager.filter_and_select_daily(data)\n",
" print(f\" 筛选前数据规模: {data.shape}\")\n",
" print(f\" 筛选后数据规模: {filtered_data.shape}\")\n",
" print(f\" 筛选前股票数: {data['ts_code'].n_unique()}\")\n",
" print(f\" 筛选后股票数: {filtered_data['ts_code'].n_unique()}\")\n",
" print(f\" 删除记录数: {len(data) - len(filtered_data)}\")\n",
"else:\n",
" filtered_data = data\n",
" print(\" 未配置股票池管理器，跳过筛选\")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"================================================================================\n",
"开始训练\n",
"================================================================================\n",
"\n",
"[步骤 1/6] 股票池筛选\n",
"------------------------------------------------------------\n",
2026-03-09 22:33:41 +08:00
" 执行每日独立筛选股票池...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\liaozhaorun\\AppData\\Local\\Temp\\ipykernel_29904\\547547317.py:75: DeprecationWarning: `is_in` with a collection of the same datatype is ambiguous and deprecated.\n",
"Please use `implode` to return to previous behavior.\n",
"\n",
"See https://github.com/pola-rs/polars/issues/22149 for more information.\n",
" return df[\"ts_code\"].is_in(small_cap_codes)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
" 筛选前数据规模: (7255513, 41)\n",
" 筛选后数据规模: (1494000, 41)\n",
" 筛选前股票数: 5694\n",
" 筛选后股票数: 2252\n",
" 删除记录数: 5761513\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 6
2026-03-06 20:57:27 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:13.998861Z",
"start_time": "2026-03-09T14:21:13.946130Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"source": [
2026-03-08 01:09:47 +08:00
"# 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",
2026-03-06 20:57:27 +08:00
"print(\"-\" * 60)\n",
"if splitter:\n",
2026-03-08 01:09:47 +08:00
" # 正确的三分法： ， ，
" train_data, val_data, test_data = splitter.split(filtered_data)\n",
2026-03-06 20:57:27 +08:00
" print(f\" 训练集数据规模: {train_data.shape}\")\n",
2026-03-08 01:09:47 +08:00
" print(f\" 验证集数据规模: {val_data.shape}\")\n",
2026-03-06 20:57:27 +08:00
" print(f\" 测试集数据规模: {test_data.shape}\")\n",
" print(f\" 训练集股票数: {train_data['ts_code'].n_unique()}\")\n",
2026-03-08 01:09:47 +08:00
" print(f\" 验证集股票数: {val_data['ts_code'].n_unique()}\")\n",
2026-03-06 20:57:27 +08:00
" print(f\" 测试集股票数: {test_data['ts_code'].n_unique()}\")\n",
" print(\n",
" f\" 训练集日期范围: {train_data['trade_date'].min()} - {train_data['trade_date'].max()}\"\n",
" )\n",
" print(\n",
2026-03-08 01:09:47 +08:00
" f\" 验证集日期范围: {val_data['trade_date'].min()} - {val_data['trade_date'].max()}\"\n",
" )\n",
" print(\n",
2026-03-06 20:57:27 +08:00
" f\" 测试集日期范围: {test_data['trade_date'].min()} - {test_data['trade_date'].max()}\"\n",
" )\n",
"\n",
" print(\"\\n 训练集前5行预览:\")\n",
" print(train_data.head())\n",
2026-03-08 01:09:47 +08:00
" print(\"\\n 验证集前5行预览:\")\n",
" print(val_data.head())\n",
2026-03-06 20:57:27 +08:00
" print(\"\\n 测试集前5行预览:\")\n",
" print(test_data.head())\n",
"else:\n",
" 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": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
2026-03-08 01:09:47 +08:00
"[步骤 2/6] 划分训练集、验证集和测试集\n",
2026-03-06 20:57:27 +08:00
"------------------------------------------------------------\n",
2026-03-09 22:33:41 +08:00
" 训练集数据规模: (970000, 41)\n",
" 验证集数据规模: (242000, 41)\n",
" 测试集数据规模: (282000, 41)\n",
" 训练集股票数: 1888\n",
" 验证集股票数: 1377\n",
" 测试集股票数: 1682\n",
2026-03-08 01:09:47 +08:00
" 训练集日期范围: 20200102 - 20231229\n",
" 验证集日期范围: 20240102 - 20241231\n",
2026-03-09 22:33:41 +08:00
" 测试集日期范围: 20250102 - 20260306\n",
2026-03-06 20:57:27 +08:00
"\n",
" 训练集前5行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (5, 41)\n",
"┌───────────┬────────────┬────────────┬───────┬───┬────────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_date ┆ turnover_r ┆ open ┆ … ┆ market_cap ┆ cashflow_ ┆ ebitda_ra ┆ future_re │\n",
"│ --- ┆ --- ┆ ate ┆ --- ┆ ┆ _rank ┆ act_rank ┆ nk ┆ turn_5 │\n",
"│ str ┆ str ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪════════════╪════════════╪═══════╪═══╪════════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 000004.SZ ┆ 20200102 ┆ 2.1613 ┆ 92.05 ┆ … ┆ 0.057219 ┆ 0.284759 ┆ null ┆ 0.000441 │\n",
"│ 000004.SZ ┆ 20200103 ┆ 1.6198 ┆ 90.67 ┆ … ┆ 0.0556 ┆ 0.284416 ┆ null ┆ 0.005875 │\n",
"│ 000004.SZ ┆ 20200106 ┆ 2.4595 ┆ 90.22 ┆ … ┆ 0.049158 ┆ 0.284264 ┆ null ┆ 0.05644 │\n",
"│ 000004.SZ ┆ 20200107 ┆ 2.1104 ┆ 88.59 ┆ … ┆ 0.049158 ┆ 0.283997 ┆ null ┆ 0.049753 │\n",
"│ 000004.SZ ┆ 20200108 ┆ 1.8769 ┆ 89.04 ┆ … ┆ 0.048904 ┆ 0.284073 ┆ null ┆ 0.019922 │\n",
"└───────────┴────────────┴────────────┴───────┴───┴────────────┴───────────┴───────────┴───────────┘\n",
2026-03-08 01:09:47 +08:00
"\n",
" 验证集前5行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (5, 41)\n",
"┌───────────┬────────────┬────────────┬───────┬───┬────────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_date ┆ turnover_r ┆ open ┆ … ┆ market_cap ┆ cashflow_ ┆ ebitda_ra ┆ future_re │\n",
"│ --- ┆ --- ┆ ate ┆ --- ┆ ┆ _rank ┆ act_rank ┆ nk ┆ turn_5 │\n",
"│ str ┆ str ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪════════════╪════════════╪═══════╪═══╪════════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 000004.SZ ┆ 20240102 ┆ 2.2858 ┆ 65.43 ┆ … ┆ 0.07789 ┆ 0.247079 ┆ null ┆ -0.014188 │\n",
"│ 000004.SZ ┆ 20240103 ┆ 2.4017 ┆ 65.55 ┆ … ┆ 0.081629 ┆ 0.247079 ┆ null ┆ 0.002432 │\n",
"│ 000004.SZ ┆ 20240104 ┆ 12.6841 ┆ 65.8 ┆ … ┆ 0.0927 ┆ 0.247079 ┆ null ┆ 0.016919 │\n",
"│ 000004.SZ ┆ 20240105 ┆ 10.2752 ┆ 67.38 ┆ … ┆ 0.087038 ┆ 0.246986 ┆ null ┆ -0.013477 │\n",
"│ 000004.SZ ┆ 20240108 ┆ 6.5832 ┆ 66.04 ┆ … ┆ 0.091165 ┆ 0.246986 ┆ null ┆ -0.024684 │\n",
"└───────────┴────────────┴────────────┴───────┴───┴────────────┴───────────┴───────────┴───────────┘\n",
2026-03-06 20:57:27 +08:00
"\n",
" 测试集前5行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (5, 41)\n",
"┌───────────┬────────────┬────────────┬───────┬───┬────────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_date ┆ turnover_r ┆ open ┆ … ┆ market_cap ┆ cashflow_ ┆ ebitda_ra ┆ future_re │\n",
"│ --- ┆ --- ┆ ate ┆ --- ┆ ┆ _rank ┆ act_rank ┆ nk ┆ turn_5 │\n",
"│ str ┆ str ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪════════════╪════════════╪═══════╪═══╪════════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 000004.SZ ┆ 20250102 ┆ 9.4831 ┆ 55.8 ┆ … ┆ 0.099106 ┆ 0.310371 ┆ null ┆ -0.066193 │\n",
"│ 000004.SZ ┆ 20250103 ┆ 9.8133 ┆ 57.71 ┆ … ┆ 0.083783 ┆ 0.310313 ┆ null ┆ 0.00893 │\n",
"│ 000004.SZ ┆ 20250106 ┆ 6.7156 ┆ 50.39 ┆ … ┆ 0.079717 ┆ 0.310429 ┆ null ┆ -0.0142 │\n",
"│ 000004.SZ ┆ 20250107 ┆ 6.8175 ┆ 51.41 ┆ … ┆ 0.082837 ┆ 0.310254 ┆ null ┆ 0.013031 │\n",
"│ 000004.SZ ┆ 20250108 ┆ 7.9011 ┆ 52.95 ┆ … ┆ 0.088421 ┆ 0.310254 ┆ null ┆ 0.00442 │\n",
"└───────────┴────────────┴────────────┴───────┴───┴────────────┴───────────┴───────────┴───────────┘\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 7
2026-03-06 20:57:27 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:14.315924Z",
"start_time": "2026-03-09T14:21:14.008258Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"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",
"print(\"-\" * 60)\n",
"fitted_processors = []\n",
"if processors:\n",
" for i, processor in enumerate(processors, 1):\n",
" print(\n",
" f\" [{i}/{len(processors)}] 应用处理器: {processor.__class__.__name__}\"\n",
" )\n",
" train_data_before = len(train_data)\n",
" train_data = processor.fit_transform(train_data)\n",
" train_data_after = len(train_data)\n",
" fitted_processors.append(processor)\n",
" print(f\" 处理前记录数: {train_data_before}\")\n",
" print(f\" 处理后记录数: {train_data_after}\")\n",
" if train_data_before != train_data_after:\n",
" print(f\" 删除记录数: {train_data_before - train_data_after}\")\n",
"\n",
"print(\"\\n 训练集处理后前5行预览:\")\n",
"print(train_data.head())\n",
"print(f\"\\n 训练集特征统计:\")\n",
"print(f\" 特征数: {len(feature_cols)}\")\n",
"print(f\" 样本数: {len(train_data)}\")\n",
"print(f\" 缺失值统计:\")\n",
"for col in feature_cols[:5]: # 只显示前5个特征的缺失值\n",
" null_count = train_data[col].null_count()\n",
" if null_count > 0:\n",
" print(\n",
" f\" {col}: {null_count} ({null_count / len(train_data) * 100:.2f}%)\"\n",
" )"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"[步骤 3/6] 训练集数据处理\n",
"------------------------------------------------------------\n",
" [1/3] 应用处理器: NullFiller\n",
2026-03-09 22:33:41 +08:00
" 处理前记录数: 970000\n",
" 处理后记录数: 970000\n",
2026-03-06 20:57:27 +08:00
" [2/3] 应用处理器: Winsorizer\n",
2026-03-09 22:33:41 +08:00
" 处理前记录数: 970000\n",
" 处理后记录数: 970000\n",
2026-03-06 20:57:27 +08:00
" [3/3] 应用处理器: StandardScaler\n",
2026-03-09 22:33:41 +08:00
" 处理前记录数: 970000\n",
" 处理后记录数: 970000\n",
2026-03-06 20:57:27 +08:00
"\n",
" 训练集处理后前5行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (5, 41)\n",
"┌───────────┬───────────┬───────────┬──────────┬───┬───────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_dat ┆ turnover_ ┆ open ┆ … ┆ market_ca ┆ cashflow_ ┆ ebitda_ra ┆ future_re │\n",
"│ --- ┆ e ┆ rate ┆ --- ┆ ┆ p_rank ┆ act_rank ┆ nk ┆ turn_5 │\n",
"│ str ┆ --- ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ str ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪═══════════╪═══════════╪══════════╪═══╪═══════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 000004.SZ ┆ 20200102 ┆ -0.158161 ┆ 4.205157 ┆ … ┆ -1.231095 ┆ -0.740158 ┆ null ┆ 0.000441 │\n",
"│ 000004.SZ ┆ 20200103 ┆ -0.308973 ┆ 4.205157 ┆ … ┆ -1.248088 ┆ -0.741819 ┆ null ┆ 0.005875 │\n",
"│ 000004.SZ ┆ 20200106 ┆ -0.07511 ┆ 4.205157 ┆ … ┆ -1.315695 ┆ -0.742554 ┆ null ┆ 0.05644 │\n",
"│ 000004.SZ ┆ 20200107 ┆ -0.172337 ┆ 4.205157 ┆ … ┆ -1.315695 ┆ -0.743846 ┆ null ┆ 0.049753 │\n",
"│ 000004.SZ ┆ 20200108 ┆ -0.237369 ┆ 4.205157 ┆ … ┆ -1.318362 ┆ -0.743479 ┆ null ┆ 0.019922 │\n",
"└───────────┴───────────┴───────────┴──────────┴───┴───────────┴───────────┴───────────┴───────────┘\n",
2026-03-06 20:57:27 +08:00
"\n",
" 训练集特征统计:\n",
2026-03-09 22:33:41 +08:00
" 特征数: 24\n",
" 样本数: 970000\n",
2026-03-06 20:57:27 +08:00
" 缺失值统计:\n",
2026-03-09 22:33:41 +08:00
" ma_5: 4000 (0.41%)\n",
" ma_20: 19000 (1.96%)\n",
" ma_ratio_5_20: 19000 (1.96%)\n",
" bias_10: 9000 (0.93%)\n",
" bbi_ratio: 23000 (2.37%)\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 8
2026-03-06 20:57:27 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:20.028734Z",
"start_time": "2026-03-09T14:21:14.320887Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"source": [
"# 步骤 4: 训练模型\n",
"print(\"\\n[步骤 4/6] 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",
"print(f\" 特征数: {len(feature_cols)}\")\n",
"print(f\" 目标变量: {target_col}\")\n",
"\n",
"X_train = train_data.select(feature_cols)\n",
"y_train = train_data.select(target_col).to_series()\n",
"\n",
"print(f\"\\n 目标变量统计:\")\n",
"print(f\" 均值: {y_train.mean():.6f}\")\n",
"print(f\" 标准差: {y_train.std():.6f}\")\n",
"print(f\" 最小值: {y_train.min():.6f}\")\n",
"print(f\" 最大值: {y_train.max():.6f}\")\n",
"print(f\" 缺失值: {y_train.null_count()}\")\n",
"\n",
"print(\"\\n 开始训练...\")\n",
"model.fit(X_train, y_train)\n",
"print(\" 训练完成！\")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"[步骤 4/6] 训练模型\n",
"------------------------------------------------------------\n",
" 模型类型: LightGBM\n",
2026-03-09 22:33:41 +08:00
" 训练样本数: 970000\n",
" 特征数: 24\n",
2026-03-08 14:12:03 +08:00
" 目标变量: future_return_5\n",
2026-03-06 20:57:27 +08:00
"\n",
" 目标变量统计:\n",
2026-03-09 22:33:41 +08:00
" 均值: 0.004184\n",
" 标准差: 0.058740\n",
" 最小值: -0.152621\n",
" 最大值: 0.216472\n",
2026-03-06 20:57:27 +08:00
" 缺失值: 0\n",
"\n",
" 开始训练...\n",
" 训练完成！\n"
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 9
2026-03-06 20:57:27 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:20.079300Z",
"start_time": "2026-03-09T14:21:20.035212Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"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(\"-\" * 60)\n",
"if processors and test_data is not train_data:\n",
" for i, processor in enumerate(fitted_processors, 1):\n",
" print(\n",
" f\" [{i}/{len(fitted_processors)}] 应用处理器: {processor.__class__.__name__}\"\n",
" )\n",
" test_data_before = len(test_data)\n",
" test_data = processor.transform(test_data)\n",
" test_data_after = len(test_data)\n",
" print(f\" 处理前记录数: {test_data_before}\")\n",
" print(f\" 处理后记录数: {test_data_after}\")\n",
"else:\n",
" print(\" 跳过测试集处理\")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"[步骤 5/6] 测试集数据处理\n",
"------------------------------------------------------------\n",
" [1/3] 应用处理器: NullFiller\n",
2026-03-09 22:33:41 +08:00
" 处理前记录数: 282000\n",
" 处理后记录数: 282000\n",
2026-03-06 20:57:27 +08:00
" [2/3] 应用处理器: Winsorizer\n",
2026-03-09 22:33:41 +08:00
" 处理前记录数: 282000\n",
" 处理后记录数: 282000\n",
2026-03-06 20:57:27 +08:00
" [3/3] 应用处理器: StandardScaler\n",
2026-03-09 22:33:41 +08:00
" 处理前记录数: 282000\n",
" 处理后记录数: 282000\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 10
2026-03-06 20:57:27 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:20.557802Z",
"start_time": "2026-03-09T14:21:20.083857Z"
2026-03-06 20:57:27 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-06 20:57:27 +08:00
"source": [
"# 步骤 6: 生成预测\n",
"print(\"\\n[步骤 6/6] 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",
"print(\" 预测中...\")\n",
"predictions = model.predict(X_test)\n",
"print(f\" 预测完成！\")\n",
"\n",
"print(f\"\\n 预测结果统计:\")\n",
"print(f\" 均值: {predictions.mean():.6f}\")\n",
"print(f\" 标准差: {predictions.std():.6f}\")\n",
"print(f\" 最小值: {predictions.min():.6f}\")\n",
"print(f\" 最大值: {predictions.max():.6f}\")\n",
"\n",
"# 保存结果到 trainer\n",
"trainer.results = test_data.with_columns([pl.Series(\"prediction\", predictions)])"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"[步骤 6/6] 生成预测\n",
"------------------------------------------------------------\n",
2026-03-09 22:33:41 +08:00
" 测试样本数: 282000\n",
2026-03-06 20:57:27 +08:00
" 预测中...\n",
" 预测完成！\n",
"\n",
" 预测结果统计:\n",
2026-03-09 22:33:41 +08:00
" 均值: 0.003423\n",
" 标准差: 0.007422\n",
" 最小值: -0.117124\n",
" 最大值: 0.068818\n"
2026-03-08 01:09:47 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 11
2026-03-08 01:09:47 +08:00
},
{
"metadata": {},
2026-03-09 22:33:41 +08:00
"cell_type": "markdown",
"source": "### 4.3 训练指标曲线"
2026-03-08 01:09:47 +08:00
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:21.403754Z",
"start_time": "2026-03-09T14:21:20.562703Z"
2026-03-08 01:09:47 +08:00
}
},
2026-03-09 22:33:41 +08:00
"cell_type": "code",
2026-03-08 01:09:47 +08:00
"source": [
"print(\"\\n\" + \"=\" * 80)\n",
"print(\"训练指标曲线\")\n",
"print(\"=\" * 80)\n",
"\n",
"# 重新训练以收集指标（因为之前的训练没有保存评估结果）\n",
"print(\"\\n重新训练模型以收集训练指标...\")\n",
"\n",
"import lightgbm as lgb\n",
"\n",
"# 准备数据（使用 val 做验证，
"X_train_np = X_train.to_numpy()\n",
"y_train_np = y_train.to_numpy()\n",
"X_val_np = val_data.select(feature_cols).to_numpy()\n",
"y_val_np = val_data.select(target_col).to_series().to_numpy()\n",
"\n",
"# 创建数据集\n",
"train_dataset = lgb.Dataset(X_train_np, label=y_train_np)\n",
"val_dataset = lgb.Dataset(X_val_np, label=y_val_np, reference=train_dataset)\n",
"\n",
"# 用于存储评估结果\n",
"evals_result = {}\n",
"\n",
"# 使用与原模型相同的参数重新训练\n",
"# 正确的三分法： ， ，
"# 添加早停：
"booster_with_eval = lgb.train(\n",
" MODEL_PARAMS,\n",
" train_dataset,\n",
" num_boost_round=MODEL_PARAMS.get(\"n_estimators\", 100),\n",
" valid_sets=[train_dataset, val_dataset],\n",
" valid_names=[\"train\", \"val\"],\n",
" callbacks=[\n",
" lgb.record_evaluation(evals_result),\n",
" lgb.early_stopping(stopping_rounds=100, verbose=True),\n",
" ],\n",
")\n",
"\n",
"print(\"训练完成，指标已收集\")\n",
"\n",
"# 获取指标名称\n",
"metric_name = list(evals_result[\"train\"].keys())[0]\n",
"print(f\"\\n评估指标: {metric_name}\")\n",
"\n",
"# 提取训练和验证指标\n",
"train_metric = evals_result[\"train\"][metric_name]\n",
"val_metric = evals_result[\"val\"][metric_name]\n",
"\n",
"# 显示早停信息\n",
"actual_rounds = len(train_metric)\n",
"expected_rounds = MODEL_PARAMS.get(\"n_estimators\", 100)\n",
"print(f\"\\n[早停信息]\")\n",
"print(f\" 配置的最大轮数: {expected_rounds}\")\n",
"print(f\" 实际训练轮数: {actual_rounds}\")\n",
"if actual_rounds < expected_rounds:\n",
" print(f\" 早停状态: 已触发（ ）
"else:\n",
" print(f\" 早停状态: 未触发（达到最大轮数）\")\n",
"\n",
"print(f\"\\n最终指标:\")\n",
"print(f\" 训练 {metric_name}: {train_metric[-1]:.6f}\")\n",
"print(f\" 验证 {metric_name}: {val_metric[-1]:.6f}\")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"================================================================================\n",
"训练指标曲线\n",
"================================================================================\n",
"\n",
"重新训练模型以收集训练指标...\n",
"Training until validation scores don't improve for 100 rounds\n",
"Early stopping, best iteration is:\n",
2026-03-09 22:33:41 +08:00
"[16]\ttrain's l1: 0.042162\tval's l1: 0.0636982\n",
2026-03-08 01:09:47 +08:00
"训练完成，指标已收集\n",
"\n",
"评估指标: l1\n",
"\n",
"[早停信息]\n",
" 配置的最大轮数: 1000\n",
2026-03-09 22:33:41 +08:00
" 实际训练轮数: 116\n",
2026-03-08 01:09:47 +08:00
" 早停状态: 已触发（ ）
"\n",
"最终指标:\n",
2026-03-09 22:33:41 +08:00
" 训练 l1: 0.041670\n",
" 验证 l1: 0.063778\n"
2026-03-08 01:09:47 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 12
2026-03-08 01:09:47 +08:00
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:21.662005Z",
"start_time": "2026-03-09T14:21:21.419111Z"
2026-03-08 01:09:47 +08:00
}
},
"source": [
"# 绘制训练指标曲线\n",
"import matplotlib.pyplot as plt\n",
"\n",
"fig, ax = plt.subplots(figsize=(12, 6))\n",
"\n",
"# 绘制训练集和验证集的指标曲线（ ： ， ）
"iterations = range(1, len(train_metric) + 1)\n",
"ax.plot(iterations, train_metric, label=f\"Train {metric_name}\", linewidth=2, color=\"blue\")\n",
"ax.plot(iterations, val_metric, label=f\"Validation {metric_name}\", linewidth=2, color=\"red\")\n",
"\n",
"ax.set_xlabel(\"Iteration\", fontsize=12)\n",
"ax.set_ylabel(metric_name.upper(), fontsize=12)\n",
"ax.set_title(f\"Training and Validation {metric_name.upper()} Curve\", fontsize=14, fontweight=\"bold\")\n",
"ax.legend(fontsize=10)\n",
"ax.grid(True, alpha=0.3)\n",
"\n",
"# 标记最佳验证指标点（用于早停决策）\n",
"best_iter = val_metric.index(min(val_metric))\n",
"best_metric = min(val_metric)\n",
"ax.axvline(x=best_iter + 1, color=\"green\", linestyle=\"--\", alpha=0.7, label=f\"Best Iteration ({best_iter + 1})\")\n",
"ax.scatter([best_iter + 1], [best_metric], color=\"green\", s=100, zorder=5)\n",
"ax.annotate(\n",
" f\"Best: {best_metric:.6f}\\nIter: {best_iter + 1}\",\n",
" xy=(best_iter + 1, best_metric),\n",
" xytext=(best_iter + 1 + len(iterations) * 0.1, best_metric),\n",
" fontsize=9,\n",
" arrowprops=dict(arrowstyle=\"->\", color=\"green\", alpha=0.7),\n",
")\n",
"\n",
"plt.tight_layout()\n",
"plt.show()\n",
"\n",
"print(f\"\\n[指标分析]\")\n",
"print(f\" 最佳验证 {metric_name}: {best_metric:.6f}\")\n",
"print(f\" 最佳迭代轮数: {best_iter + 1}\")\n",
"print(f\" 早停建议: 如果验证指标连续10轮不下降，
"print(f\"\\n[重要提醒] 验证集仅用于早停/调参，测试集完全独立于训练过程！\")"
],
"outputs": [
{
"data": {
"text/plain": [
"<Figure size 1200x600 with 1 Axes>"
],
2026-03-09 22:33:41 +08:00
"image/png": "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
2026-03-08 01:09:47 +08:00
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"[指标分析]\n",
2026-03-09 22:33:41 +08:00
" 最佳验证 l1: 0.063698\n",
" 最佳迭代轮数: 16\n",
" 早停建议: 如果验证指标连续10轮不下降，
2026-03-08 01:09:47 +08:00
"\n",
"[重要提醒] 验证集仅用于早停/调参，测试集完全独立于训练过程！\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 13
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2026-03-08 01:09:47 +08:00
"### 4.4 查看结果"
2026-03-06 20:57:27 +08:00
]
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:21.684871Z",
"start_time": "2026-03-09T14:21:21.668727Z"
2026-03-06 20:57:27 +08:00
}
},
"source": [
"print(\"\\n\" + \"=\" * 80)\n",
"print(\"训练结果\")\n",
"print(\"=\" * 80)\n",
"\n",
"results = trainer.results\n",
"\n",
"print(f\"\\n结果数据形状: {results.shape}\")\n",
"print(f\"结果列: {results.columns}\")\n",
"print(f\"\\n结果前10行预览:\")\n",
"print(results.head(10))\n",
"print(f\"\\n结果后5行预览:\")\n",
"print(results.tail())\n",
"\n",
"print(f\"\\n每日预测样本数统计:\")\n",
"daily_counts = results.group_by(\"trade_date\").agg(pl.len()).sort(\"trade_date\")\n",
"print(f\" 最小: {daily_counts['len'].min()}\")\n",
"print(f\" 最大: {daily_counts['len'].max()}\")\n",
"print(f\" 平均: {daily_counts['len'].mean():.2f}\")\n",
"\n",
"# 展示某一天的前10个预测结果\n",
"sample_date = results[\"trade_date\"][0]\n",
"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": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"================================================================================\n",
"训练结果\n",
"================================================================================\n",
"\n",
2026-03-09 22:33:41 +08:00
"结果数据形状: (282000, 42)\n",
"结果列: ['ts_code', 'trade_date', 'turnover_rate', 'open', 'vol', 'close', 'total_mv', 'f_ann_date', 'revenue', 'n_income', 'total_hldr_eqy_exc_min_int', 'total_cur_assets', 'total_liab', 'total_cur_liab', 'roe', 'ebitda', 'n_cashflow_act', 'ma_5', 'ma_20', 'ma_ratio_5_20', 'bias_10', 'bbi_ratio', 'return_5', 'return_20', 'momentum_accel', 'volatility_ratio', 'reversal_1', 'volume_ratio', 'turnover_rate_mean_5', 'turnover_deviation', 'net_profit_growth', 'revenue_growth', 'roe_delta', 'debt_to_equity', 'current_ratio', 'EP_rank', 'BP_rank', 'market_cap_rank', 'cashflow_act_rank', 'ebitda_rank', 'future_return_5', 'prediction']\n",
2026-03-06 20:57:27 +08:00
"\n",
"结果前10行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (10, 42)\n",
"┌───────────┬───────────┬───────────┬──────────┬───┬───────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_dat ┆ turnover_ ┆ open ┆ … ┆ cashflow_ ┆ ebitda_ra ┆ future_re ┆ predictio │\n",
"│ --- ┆ e ┆ rate ┆ --- ┆ ┆ act_rank ┆ nk ┆ turn_5 ┆ n │\n",
"│ str ┆ --- ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ str ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪═══════════╪═══════════╪══════════╪═══╪═══════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 000004.SZ ┆ 20250102 ┆ 1.881022 ┆ 2.213796 ┆ … ┆ -0.616292 ┆ null ┆ -0.066193 ┆ 0.008414 │\n",
"│ 000004.SZ ┆ 20250103 ┆ 1.972985 ┆ 2.34744 ┆ … ┆ -0.616573 ┆ null ┆ 0.00893 ┆ 0.004788 │\n",
"│ 000004.SZ ┆ 20250106 ┆ 1.11025 ┆ 1.835256 ┆ … ┆ -0.616011 ┆ null ┆ -0.0142 ┆ 0.011516 │\n",
"│ 000004.SZ ┆ 20250107 ┆ 1.13863 ┆ 1.906626 ┆ … ┆ -0.616854 ┆ null ┆ 0.013031 ┆ 0.01138 │\n",
"│ 000004.SZ ┆ 20250108 ┆ 1.440421 ┆ 2.01438 ┆ … ┆ -0.616854 ┆ null ┆ 0.00442 ┆ -0.000694 │\n",
"│ 000004.SZ ┆ 20250109 ┆ 1.067777 ┆ 2.10884 ┆ … ┆ -0.617135 ┆ null ┆ 0.024865 ┆ -0.004267 │\n",
"│ 000004.SZ ┆ 20250110 ┆ 1.048783 ┆ 2.080153 ┆ … ┆ -0.616854 ┆ null ┆ 0.073486 ┆ -0.005361 │\n",
"│ 000004.SZ ┆ 20250113 ┆ 0.783364 ┆ 1.832457 ┆ … ┆ -0.615668 ┆ null ┆ -0.04458 ┆ 0.001935 │\n",
"│ 000004.SZ ┆ 20250114 ┆ 0.971525 ┆ 1.87234 ┆ … ┆ -0.613797 ┆ null ┆ -0.152621 ┆ 0.003452 │\n",
"│ 000004.SZ ┆ 20250115 ┆ 1.829191 ┆ 2.168315 ┆ … ┆ -0.613797 ┆ null ┆ -0.152621 ┆ 0.007143 │\n",
"└───────────┴───────────┴───────────┴──────────┴───┴───────────┴───────────┴───────────┴───────────┘\n",
2026-03-06 20:57:27 +08:00
"\n",
"结果后5行预览:\n",
2026-03-09 22:33:41 +08:00
"shape: (5, 42)\n",
"┌───────────┬───────────┬───────────┬──────────┬───┬───────────┬───────────┬───────────┬───────────┐\n",
"│ ts_code ┆ trade_dat ┆ turnover_ ┆ open ┆ … ┆ cashflow_ ┆ ebitda_ra ┆ future_re ┆ predictio │\n",
"│ --- ┆ e ┆ rate ┆ --- ┆ ┆ act_rank ┆ nk ┆ turn_5 ┆ n │\n",
"│ str ┆ --- ┆ --- ┆ f64 ┆ ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ ┆ str ┆ f64 ┆ ┆ ┆ f64 ┆ f64 ┆ f64 ┆ f64 │\n",
"╞═══════════╪═══════════╪═══════════╪══════════╪═══╪═══════════╪═══════════╪═══════════╪═══════════╡\n",
"│ 605588.SH ┆ 20260302 ┆ 0.009947 ┆ 2.541258 ┆ … ┆ 1.00409 ┆ null ┆ null ┆ 0.00702 │\n",
"│ 605588.SH ┆ 20260303 ┆ 0.133214 ┆ 2.553853 ┆ … ┆ 1.372931 ┆ null ┆ null ┆ 0.021044 │\n",
"│ 605588.SH ┆ 20260304 ┆ 0.021087 ┆ 2.167616 ┆ … ┆ 1.004146 ┆ null ┆ null ┆ 0.01389 │\n",
"│ 605588.SH ┆ 20260305 ┆ -0.069317 ┆ 2.15852 ┆ … ┆ 1.003572 ┆ null ┆ null ┆ 0.010792 │\n",
"│ 605588.SH ┆ 20260306 ┆ -0.288642 ┆ 2.173913 ┆ … ┆ 1.002681 ┆ null ┆ null ┆ 0.009205 │\n",
"└───────────┴───────────┴───────────┴──────────┴───┴───────────┴───────────┴───────────┴───────────┘\n",
2026-03-06 20:57:27 +08:00
"\n",
"每日预测样本数统计:\n",
2026-03-09 22:33:41 +08:00
" 最小: 1000\n",
" 最大: 1000\n",
" 平均: 1000.00\n",
2026-03-06 20:57:27 +08:00
"\n",
"示例日期 20250102 的前10条预测:\n",
"shape: (10, 4)\n",
2026-03-08 14:12:03 +08:00
"┌───────────┬────────────┬─────────────────┬────────────┐\n",
"│ ts_code ┆ trade_date ┆ future_return_5 ┆ prediction │\n",
"│ --- ┆ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ f64 ┆ f64 │\n",
"╞═══════════╪════════════╪═════════════════╪════════════╡\n",
2026-03-09 22:33:41 +08:00
"│ 000004.SZ ┆ 20250102 ┆ -0.066193 ┆ 0.008414 │\n",
"│ 000007.SZ ┆ 20250102 ┆ 0.019858 ┆ -0.000127 │\n",
"│ 000010.SZ ┆ 20250102 ┆ 0.076274 ┆ -0.002403 │\n",
"│ 000014.SZ ┆ 20250102 ┆ -0.064651 ┆ -0.002853 │\n",
"│ 000040.SZ ┆ 20250102 ┆ -0.093583 ┆ -0.077776 │\n",
"│ 000042.SZ ┆ 20250102 ┆ -0.035958 ┆ 0.003656 │\n",
"│ 000056.SZ ┆ 20250102 ┆ -0.033205 ┆ 0.018378 │\n",
"│ 000068.SZ ┆ 20250102 ┆ -0.021277 ┆ 0.010857 │\n",
"│ 000153.SZ ┆ 20250102 ┆ -0.018193 ┆ 0.001929 │\n",
"│ 000159.SZ ┆ 20250102 ┆ -0.067833 ┆ 0.003916 │\n",
2026-03-08 14:12:03 +08:00
"└───────────┴────────────┴─────────────────┴────────────┘\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 14
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 4.4 保存结果"
]
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:21.992341Z",
"start_time": "2026-03-09T14:21:21.689211Z"
2026-03-06 20:57:27 +08:00
}
},
"cell_type": "code",
"source": [
"print(\"\\n\" + \"=\" * 80)\n",
"print(\"保存预测结果\")\n",
"print(\"=\" * 80)\n",
"\n",
"# 确保输出目录存在\n",
"os.makedirs(OUTPUT_DIR, exist_ok=True)\n",
"\n",
"# 生成时间戳\n",
"start_dt = datetime.strptime(TEST_START, \"%Y%m%d\")\n",
"end_dt = datetime.strptime(TEST_END, \"%Y%m%d\")\n",
"date_str = f\"{start_dt.strftime('%Y%m%d')}_{end_dt.strftime('%Y%m%d')}\"\n",
"\n",
2026-03-08 11:46:30 +08:00
"# 保存每日 Top N\n",
"print(f\"\\n[1/1] 保存每日 Top {TOP_N} 股票...\")\n",
"topn_output_path = os.path.join(OUTPUT_DIR, f\"regression_output.csv\")\n",
2026-03-06 20:57:27 +08:00
"\n",
2026-03-08 11:46:30 +08:00
"# 按日期分组，取每日 top N\n",
"topn_by_date = []\n",
2026-03-06 20:57:27 +08:00
"unique_dates = results[\"trade_date\"].unique().sort()\n",
"for date in unique_dates:\n",
" day_data = results.filter(results[\"trade_date\"] == date)\n",
2026-03-08 11:46:30 +08:00
" # 按 prediction 降序排序，取前 N\n",
" topn = day_data.sort(\"prediction\", descending=True).head(TOP_N)\n",
" topn_by_date.append(topn)\n",
2026-03-06 20:57:27 +08:00
"\n",
2026-03-08 11:46:30 +08:00
"# 合并所有日期的 top N\n",
"topn_results = pl.concat(topn_by_date)\n",
2026-03-06 20:57:27 +08:00
"\n",
"# 格式化日期并调整列顺序：日期、分数、股票\n",
2026-03-08 11:46:30 +08:00
"topn_to_save = topn_results.select(\n",
2026-03-06 20:57:27 +08:00
" [\n",
" pl.col(\"trade_date\").str.slice(0, 4)\n",
" + \"-\"\n",
" + pl.col(\"trade_date\").str.slice(4, 2)\n",
" + \"-\"\n",
" + pl.col(\"trade_date\").str.slice(6, 2).alias(\"date\"),\n",
" pl.col(\"prediction\").alias(\"score\"),\n",
" pl.col(\"ts_code\"),\n",
" ]\n",
")\n",
2026-03-08 11:46:30 +08:00
"topn_to_save.write_csv(topn_output_path, include_header=True)\n",
"print(f\" 保存路径: {topn_output_path}\")\n",
"print(f\" 保存行数: {len(topn_to_save)}（ × ）
2026-03-06 20:57:27 +08:00
"print(f\"\\n 预览（ ）
2026-03-08 11:46:30 +08:00
"print(topn_to_save.head(15))"
2026-03-06 20:57:27 +08:00
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"================================================================================\n",
"保存预测结果\n",
"================================================================================\n",
"\n",
2026-03-08 20:58:35 +08:00
"[1/1] 保存每日 Top 5 股票...\n",
2026-03-08 11:46:30 +08:00
" 保存路径: output\\regression_output.csv\n",
2026-03-09 22:33:41 +08:00
" 保存行数: 1410（ × ）
2026-03-06 20:57:27 +08:00
"\n",
" 预览（ ）
"shape: (15, 3)\n",
"┌────────────┬──────────┬───────────┐\n",
"│ trade_date ┆ score ┆ ts_code │\n",
"│ --- ┆ --- ┆ --- │\n",
"│ str ┆ f64 ┆ str │\n",
"╞════════════╪══════════╪═══════════╡\n",
2026-03-09 22:33:41 +08:00
"│ 2025-01-02 ┆ 0.030035 ┆ 002427.SZ │\n",
"│ 2025-01-02 ┆ 0.02861 ┆ 002076.SZ │\n",
"│ 2025-01-02 ┆ 0.026407 ┆ 000518.SZ │\n",
"│ 2025-01-02 ┆ 0.026051 ┆ 603838.SH │\n",
"│ 2025-01-02 ┆ 0.025572 ┆ 002199.SZ │\n",
2026-03-06 20:57:27 +08:00
"│ … ┆ … ┆ … │\n",
2026-03-09 22:33:41 +08:00
"│ 2025-01-06 ┆ 0.035263 ┆ 002427.SZ │\n",
"│ 2025-01-06 ┆ 0.032408 ┆ 600962.SH │\n",
"│ 2025-01-06 ┆ 0.03104 ┆ 605298.SH │\n",
"│ 2025-01-06 ┆ 0.030765 ┆ 301006.SZ │\n",
"│ 2025-01-06 ┆ 0.030541 ┆ 002522.SZ │\n",
2026-03-06 20:57:27 +08:00
"└────────────┴──────────┴───────────┘\n"
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 15
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 4.5 特征重要性"
]
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:22.000983Z",
"start_time": "2026-03-09T14:21:21.996749Z"
2026-03-06 20:57:27 +08:00
}
},
"source": [
"importance = model.feature_importance()\n",
"if importance is not None:\n",
" print(\"\\n特征重要性:\")\n",
" print(importance.sort_values(ascending=False))\n",
"\n",
"print(\"\\n\" + \"=\" * 80)\n",
"print(\"训练完成！\")\n",
"print(\"=\" * 80)"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"特征重要性:\n",
2026-03-09 22:33:41 +08:00
"bias_10 883.242468\n",
"bbi_ratio 719.403482\n",
"reversal_1 616.343038\n",
"turnover_deviation 563.883571\n",
"turnover_rate_mean_5 553.710151\n",
"ma_ratio_5_20 493.930772\n",
"return_20 477.078960\n",
"return_5 465.129010\n",
"volume_ratio 438.578614\n",
"roe 386.244247\n",
"EP_rank 324.897361\n",
"ma_20 313.170879\n",
"momentum_accel 273.272078\n",
"net_profit_growth 227.346561\n",
"BP_rank 210.965235\n",
"volatility_ratio 200.314833\n",
"roe_delta 153.102754\n",
"cashflow_act_rank 136.542178\n",
"ma_5 116.355596\n",
"market_cap_rank 89.142452\n",
"debt_to_equity 68.378507\n",
"current_ratio 63.483876\n",
"revenue_growth 0.000000\n",
"ebitda_rank 0.000000\n",
2026-03-06 20:57:27 +08:00
"dtype: float64\n",
"\n",
"================================================================================\n",
"训练完成！\n",
"================================================================================\n"
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 16
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. 可视化分析\n",
"\n",
"使用训练好的模型直接绘图。\n",
"- **特征重要性图**：辅助特征选择\n",
"- **决策树图**：理解决策逻辑"
]
},
{
"cell_type": "code",
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:22.011078Z",
"start_time": "2026-03-09T14:21:22.007446Z"
2026-03-06 20:57:27 +08:00
}
},
"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)}\")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"模型类型: <class 'lightgbm.basic.Booster'>\n",
2026-03-09 22:33:41 +08:00
"特征数量: 24\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 17
2026-03-06 20:57:27 +08:00
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 5.1 绘制特征重要性（辅助特征选择）\n",
"\n",
"**解读**：
"- 重要性高的特征对模型贡献大\n",
"- 重要性为0的特征可以考虑删除\n",
"- 可以帮助理解哪些因子最有效"
]
},
{
"metadata": {
"ExecuteTime": {
2026-03-09 22:33:41 +08:00
"end_time": "2026-03-09T14:21:22.149719Z",
"start_time": "2026-03-09T14:21:22.016953Z"
2026-03-06 20:57:27 +08:00
}
},
"cell_type": "code",
"source": [
"print(\"绘制特征重要性...\")\n",
"\n",
"fig, ax = plt.subplots(figsize=(10, 8))\n",
"lgb.plot_importance(\n",
2026-03-09 22:33:41 +08:00
" booster,\n",
2026-03-06 20:57:27 +08:00
" 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'),\n",
" 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，
" 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\")"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"绘制特征重要性...\n"
]
},
{
"data": {
"text/plain": [
"<Figure size 1000x800 with 1 Axes>"
],
2026-03-09 22:33:41 +08:00
"image/png": "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
2026-03-06 20:57:27 +08:00
},
"metadata": {},
"output_type": "display_data",
"jetTransient": {
"display_id": null
}
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"[特征重要性排名 - Gain]\n",
2026-03-09 22:33:41 +08:00
"bias_10 883.242468\n",
"bbi_ratio 719.403482\n",
"reversal_1 616.343038\n",
"turnover_deviation 563.883571\n",
"turnover_rate_mean_5 553.710151\n",
"ma_ratio_5_20 493.930772\n",
"return_20 477.078960\n",
"return_5 465.129010\n",
"volume_ratio 438.578614\n",
"roe 386.244247\n",
"EP_rank 324.897361\n",
"ma_20 313.170879\n",
"momentum_accel 273.272078\n",
"net_profit_growth 227.346561\n",
"BP_rank 210.965235\n",
"volatility_ratio 200.314833\n",
"roe_delta 153.102754\n",
"cashflow_act_rank 136.542178\n",
"ma_5 116.355596\n",
"market_cap_rank 89.142452\n",
"debt_to_equity 68.378507\n",
"current_ratio 63.483876\n",
"revenue_growth 0.000000\n",
"ebitda_rank 0.000000\n",
2026-03-06 20:57:27 +08:00
"dtype: float64\n",
"\n",
2026-03-09 22:33:41 +08:00
"[低重要性特征] 以下2个特征重要性为0，
" - revenue_growth\n",
" - ebitda_rank\n"
2026-03-06 20:57:27 +08:00
]
}
],
2026-03-09 22:33:41 +08:00
"execution_count": 18
2026-03-06 20:57:27 +08:00
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.0"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
