1258 lines
118 KiB
Plaintext
1258 lines
118 KiB
Plaintext
|
{
|
|||
|
|
"cells": [
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"# LightGBM 回归训练示例 - 使用因子字符串表达式\n",
|
|||
|
|
"\n",
|
|||
|
|
"使用字符串表达式定义因子，训练 LightGBM 回归模型预测未来5日收益率。\n",
|
|||
|
|
"\n",
|
|||
|
|
"**Label**: return_5 = (ts_delay(close, -5) / close) - 1 # 未来5日收益率"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"## 1. 导入依赖"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:34.025295Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:33.223817Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" StockFilterConfig,\n",
|
|||
|
|
" StockPoolManager,\n",
|
|||
|
|
" Trainer,\n",
|
|||
|
|
" Winsorizer,\n",
|
|||
|
|
" NullFiller,\n",
|
|||
|
|
")\n",
|
|||
|
|
"from src.training.config import TrainingConfig"
|
|||
|
|
],
|
|||
|
|
"outputs": [],
|
|||
|
|
"execution_count": 1
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"## 2. 定义辅助函数"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:34.040804Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:34.036138Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 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 + [\"return_5\"] # 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"
|
|||
|
|
],
|
|||
|
|
"outputs": [],
|
|||
|
|
"execution_count": 2
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"## 3. 配置参数\n",
|
|||
|
|
"\n",
|
|||
|
|
"### 3.1 因子定义"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:34.050475Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:34.045956Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"FACTOR_DEFINITIONS = {\n",
|
|||
|
|
" # 1. 价格动量因子\n",
|
|||
|
|
" \"ma5\": \"ts_mean(close, 5)\",\n",
|
|||
|
|
" \"ma10\": \"ts_mean(close, 10)\",\n",
|
|||
|
|
" \"ma20\": \"ts_mean(close, 20)\",\n",
|
|||
|
|
" \"ma_ratio\": \"ts_mean(close, 5) / ts_mean(close, 20) - 1\",\n",
|
|||
|
|
" # 2. 波动率因子\n",
|
|||
|
|
" \"volatility_5\": \"ts_std(close, 5)\",\n",
|
|||
|
|
" \"volatility_20\": \"ts_std(close, 20)\",\n",
|
|||
|
|
" \"vol_ratio\": \"ts_std(close, 5) / (ts_std(close, 20) + 1e-8)\",\n",
|
|||
|
|
" # 3. 收益率动量因子\n",
|
|||
|
|
" \"return_10\": \"(close / ts_delay(close, 10)) - 1\",\n",
|
|||
|
|
" \"return_20\": \"(close / ts_delay(close, 20)) - 1\",\n",
|
|||
|
|
" # 4. 收益率变化因子\n",
|
|||
|
|
" \"return_diff\": \"(close / ts_delay(close, 5)) - 1 - ((close / ts_delay(close, 10)) - 1)\",\n",
|
|||
|
|
" # 5. 成交量因子\n",
|
|||
|
|
" \"vol_ma5\": \"ts_mean(vol, 5)\",\n",
|
|||
|
|
" \"vol_ma20\": \"ts_mean(vol, 20)\",\n",
|
|||
|
|
" \"vol_ratio\": \"ts_mean(vol, 5) / (ts_mean(vol, 20) + 1e-8)\",\n",
|
|||
|
|
" # 6. 市值因子（截面排名）\n",
|
|||
|
|
" \"market_cap_rank\": \"cs_rank(total_mv)\",\n",
|
|||
|
|
" # 7. 价格位置因子\n",
|
|||
|
|
" \"high_low_ratio\": \"(close - ts_min(low, 20)) / (ts_max(high, 20) - ts_min(low, 20) + 1e-8)\",\n",
|
|||
|
|
" \"n_income\": \"cs_rank(n_income)\",\n",
|
|||
|
|
"}\n",
|
|||
|
|
"\n",
|
|||
|
|
"# Label 因子定义（不参与训练，用于计算目标）\n",
|
|||
|
|
"LABEL_FACTOR = {\n",
|
|||
|
|
" \"return_5\": \"(ts_delay(close, -5) / close) - 1\", # 未来5日收益率\n",
|
|||
|
|
"}"
|
|||
|
|
],
|
|||
|
|
"outputs": [],
|
|||
|
|
"execution_count": 3
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 3.2 训练参数配置"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:34.069686Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:34.065755Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"# 日期范围配置\n",
|
|||
|
|
"TRAIN_START = \"20200101\"\n",
|
|||
|
|
"TRAIN_END = \"20241231\"\n",
|
|||
|
|
"TEST_START = \"20250101\"\n",
|
|||
|
|
"TEST_END = \"20251231\"\n",
|
|||
|
|
"\n",
|
|||
|
|
"# 模型参数配置\n",
|
|||
|
|
"MODEL_PARAMS = {\n",
|
|||
|
|
" \"objective\": \"regression\",\n",
|
|||
|
|
" \"metric\": \"mae\", # 改为 MAE，对异常值更稳健\n",
|
|||
|
|
" # 树结构控制（防过拟合核心）\n",
|
|||
|
|
" \"num_leaves\": 20, # 从31降为20，降低模型复杂度\n",
|
|||
|
|
" \"max_depth\": 4, # 显式限制深度，防止过度拟合噪声\n",
|
|||
|
|
" \"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，增加稀疏性\n",
|
|||
|
|
" \"reg_lambda\": 1.0, # L2正则，平滑权重\n",
|
|||
|
|
" # 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",
|
|||
|
|
"# 股票池筛选配置\n",
|
|||
|
|
"STOCK_FILTER_CONFIG = {\n",
|
|||
|
|
" \"exclude_cyb\": True, # 排除创业板\n",
|
|||
|
|
" \"exclude_kcb\": True, # 排除科创板\n",
|
|||
|
|
" \"exclude_bj\": True, # 排除北交所\n",
|
|||
|
|
" \"exclude_st\": True, # 排除ST股票\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"
|
|||
|
|
],
|
|||
|
|
"outputs": [],
|
|||
|
|
"execution_count": 4
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"## 4. 训练流程\n",
|
|||
|
|
"\n",
|
|||
|
|
"### 4.1 初始化组件"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:39.199834Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:34.082579Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"target_col = \"return_5\"\n",
|
|||
|
|
"\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",
|
|||
|
|
"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",
|
|||
|
|
"# 7. 创建数据划分器\n",
|
|||
|
|
"splitter = DateSplitter(\n",
|
|||
|
|
" train_start=TRAIN_START,\n",
|
|||
|
|
" train_end=TRAIN_END,\n",
|
|||
|
|
" test_start=TEST_START,\n",
|
|||
|
|
" test_end=TEST_END,\n",
|
|||
|
|
")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# 8. 创建股票池管理器\n",
|
|||
|
|
"pool_manager = StockPoolManager(\n",
|
|||
|
|
" filter_config=StockFilterConfig(**STOCK_FILTER_CONFIG),\n",
|
|||
|
|
" selector_config=None, # 暂时不启用市值选择\n",
|
|||
|
|
" data_router=engine.router,\n",
|
|||
|
|
")\n",
|
|||
|
|
"\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",
|
|||
|
|
" filters=[st_filter],\n",
|
|||
|
|
" 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",
|
|||
|
|
" - ma5: ts_mean(close, 5)\n",
|
|||
|
|
" - ma10: ts_mean(close, 10)\n",
|
|||
|
|
" - ma20: ts_mean(close, 20)\n",
|
|||
|
|
" - ma_ratio: ts_mean(close, 5) / ts_mean(close, 20) - 1\n",
|
|||
|
|
" - volatility_5: ts_std(close, 5)\n",
|
|||
|
|
" - volatility_20: ts_std(close, 20)\n",
|
|||
|
|
" - vol_ratio: ts_mean(vol, 5) / (ts_mean(vol, 20) + 1e-8)\n",
|
|||
|
|
" - return_10: (close / ts_delay(close, 10)) - 1\n",
|
|||
|
|
" - return_20: (close / ts_delay(close, 20)) - 1\n",
|
|||
|
|
" - return_diff: (close / ts_delay(close, 5)) - 1 - ((close / ts_delay(close, 10)) - 1)\n",
|
|||
|
|
" - vol_ma5: ts_mean(vol, 5)\n",
|
|||
|
|
" - vol_ma20: ts_mean(vol, 20)\n",
|
|||
|
|
" - market_cap_rank: cs_rank(total_mv)\n",
|
|||
|
|
" - high_low_ratio: (close - ts_min(low, 20)) / (ts_max(high, 20) - ts_min(low, 20) + 1e-8)\n",
|
|||
|
|
" - n_income: cs_rank(n_income)\n",
|
|||
|
|
"\n",
|
|||
|
|
"注册 Label 因子:\n",
|
|||
|
|
" - return_5: (ts_delay(close, -5) / close) - 1\n",
|
|||
|
|
"\n",
|
|||
|
|
"特征因子数: 15\n",
|
|||
|
|
"Label: return_5\n",
|
|||
|
|
"已注册因子总数: 16\n",
|
|||
|
|
"\n",
|
|||
|
|
"[3] 准备数据\n",
|
|||
|
|
"\n",
|
|||
|
|
"================================================================================\n",
|
|||
|
|
"准备数据\n",
|
|||
|
|
"================================================================================\n",
|
|||
|
|
"\n",
|
|||
|
|
"计算因子: 20200101 - 20251231\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"name": "stderr",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"D:\\PyProject\\ProStock\\src\\data\\financial_loader.py:123: 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: (7044952, 24)\n",
|
|||
|
|
"数据列: ['ts_code', 'trade_date', 'high', 'vol', 'close', 'low', 'total_mv', 'f_ann_date', 'n_income', 'ma5', 'ma10', 'ma20', 'ma_ratio', 'volatility_5', 'volatility_20', 'vol_ratio', 'return_10', 'return_20', 'return_diff', 'vol_ma5', 'vol_ma20', 'market_cap_rank', 'high_low_ratio', 'return_5']\n",
|
|||
|
|
"\n",
|
|||
|
|
"前5行预览:\n",
|
|||
|
|
"shape: (5, 24)\n",
|
|||
|
|
"┌───────────┬────────────┬─────────┬───────────┬───┬──────────┬────────────┬───────────┬───────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_date ┆ high ┆ vol ┆ … ┆ vol_ma20 ┆ market_cap ┆ high_low_ ┆ return_5 │\n",
|
|||
|
|
"│ --- ┆ --- ┆ --- ┆ --- ┆ ┆ --- ┆ _rank ┆ ratio ┆ --- │\n",
|
|||
|
|
"│ str ┆ str ┆ f64 ┆ f64 ┆ ┆ f64 ┆ --- ┆ --- ┆ f64 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n",
|
|||
|
|
"╞═══════════╪════════════╪═════════╪═══════════╪═══╪══════════╪════════════╪═══════════╪═══════════╡\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200102 ┆ 1850.42 ┆ 1.5302e6 ┆ … ┆ null ┆ 0.993583 ┆ null ┆ -0.004746 │\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200103 ┆ 1889.72 ┆ 1.1162e6 ┆ … ┆ null ┆ 0.993585 ┆ null ┆ -0.02852 │\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200106 ┆ 1893.0 ┆ 862083.5 ┆ … ┆ null ┆ 0.993588 ┆ null ┆ -0.004685 │\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200107 ┆ 1886.45 ┆ 728607.56 ┆ … ┆ null ┆ 0.993588 ┆ null ┆ -0.022743 │\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200108 ┆ 1861.34 ┆ 847824.12 ┆ … ┆ null ┆ 0.993586 ┆ null ┆ -0.008401 │\n",
|
|||
|
|
"└───────────┴────────────┴─────────┴───────────┴───┴──────────┴────────────┴───────────┴───────────┘\n",
|
|||
|
|
"\n",
|
|||
|
|
"[配置] 训练期: 20200101 - 20241231\n",
|
|||
|
|
"[配置] 测试期: 20250101 - 20251231\n",
|
|||
|
|
"[配置] 特征数: 15\n",
|
|||
|
|
"[配置] 目标变量: return_5\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 5
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 4.2 执行训练"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:45.542301Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:39.210579Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 执行每日独立筛选股票池...\n",
|
|||
|
|
" 筛选前数据规模: (7044952, 24)\n",
|
|||
|
|
" 筛选后数据规模: (4532198, 24)\n",
|
|||
|
|
" 筛选前股票数: 5678\n",
|
|||
|
|
" 筛选后股票数: 3359\n",
|
|||
|
|
" 删除记录数: 2512754\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 6
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:46.133946Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:45.552454Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"source": [
|
|||
|
|
"# 步骤 2: 划分训练/测试集\n",
|
|||
|
|
"print(\"\\n[步骤 2/6] 划分训练集和测试集\")\n",
|
|||
|
|
"print(\"-\" * 60)\n",
|
|||
|
|
"if splitter:\n",
|
|||
|
|
" train_data, test_data = splitter.split(filtered_data)\n",
|
|||
|
|
" print(f\" 训练集数据规模: {train_data.shape}\")\n",
|
|||
|
|
" 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",
|
|||
|
|
" 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",
|
|||
|
|
" 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",
|
|||
|
|
" 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",
|
|||
|
|
"[步骤 2/6] 划分训练集和测试集\n",
|
|||
|
|
"------------------------------------------------------------\n",
|
|||
|
|
" 训练集数据规模: (3760991, 24)\n",
|
|||
|
|
" 测试集数据规模: (771207, 24)\n",
|
|||
|
|
" 训练集股票数: 3321\n",
|
|||
|
|
" 测试集股票数: 3215\n",
|
|||
|
|
" 训练集日期范围: 20200102 - 20241231\n",
|
|||
|
|
" 测试集日期范围: 20250102 - 20251231\n",
|
|||
|
|
"\n",
|
|||
|
|
" 训练集前5行预览:\n",
|
|||
|
|
"shape: (5, 24)\n",
|
|||
|
|
"┌───────────┬────────────┬─────────┬───────────┬───┬──────────┬────────────┬───────────┬───────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_date ┆ high ┆ vol ┆ … ┆ vol_ma20 ┆ market_cap ┆ high_low_ ┆ return_5 │\n",
|
|||
|
|
"│ --- ┆ --- ┆ --- ┆ --- ┆ ┆ --- ┆ _rank ┆ ratio ┆ --- │\n",
|
|||
|
|
"│ str ┆ str ┆ f64 ┆ f64 ┆ ┆ f64 ┆ --- ┆ --- ┆ f64 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n",
|
|||
|
|
"╞═══════════╪════════════╪═════════╪═══════════╪═══╪══════════╪════════════╪═══════════╪═══════════╡\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200102 ┆ 1850.42 ┆ 1.5302e6 ┆ … ┆ null ┆ 0.993583 ┆ null ┆ -0.004746 │\n",
|
|||
|
|
"│ 000002.SZ ┆ 20200102 ┆ 4986.64 ┆ 1012130.4 ┆ … ┆ null ┆ 0.99492 ┆ null ┆ -0.011057 │\n",
|
|||
|
|
"│ 000004.SZ ┆ 20200102 ┆ 93.06 ┆ 17853.2 ┆ … ┆ null ┆ 0.057219 ┆ null ┆ -0.000441 │\n",
|
|||
|
|
"│ 000005.SZ ┆ 20200102 ┆ 29.19 ┆ 104134.12 ┆ … ┆ null ┆ 0.28984 ┆ null ┆ 0.022337 │\n",
|
|||
|
|
"│ 000006.SZ ┆ 20200102 ┆ 193.07 ┆ 124751.76 ┆ … ┆ null ┆ 0.631551 ┆ null ┆ 0.012964 │\n",
|
|||
|
|
"└───────────┴────────────┴─────────┴───────────┴───┴──────────┴────────────┴───────────┴───────────┘\n",
|
|||
|
|
"\n",
|
|||
|
|
" 测试集前5行预览:\n",
|
|||
|
|
"shape: (5, 24)\n",
|
|||
|
|
"┌───────────┬────────────┬─────────┬───────────┬───┬───────────┬───────────┬───────────┬───────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_date ┆ high ┆ vol ┆ … ┆ vol_ma20 ┆ market_ca ┆ high_low_ ┆ return_5 │\n",
|
|||
|
|
"│ --- ┆ --- ┆ --- ┆ --- ┆ ┆ --- ┆ p_rank ┆ ratio ┆ --- │\n",
|
|||
|
|
"│ str ┆ str ┆ f64 ┆ f64 ┆ ┆ f64 ┆ --- ┆ --- ┆ f64 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n",
|
|||
|
|
"╞═══════════╪════════════╪═════════╪═══════════╪═══╪═══════════╪═══════════╪═══════════╪═══════════╡\n",
|
|||
|
|
"│ 000001.SZ ┆ 20250102 ┆ 1504.02 ┆ 1.8196e6 ┆ … ┆ 1.2151e6 ┆ 0.991617 ┆ 0.063478 ┆ -0.002622 │\n",
|
|||
|
|
"│ 000002.SZ ┆ 20250102 ┆ 1337.34 ┆ 1.1827e6 ┆ … ┆ 1.2839e6 ┆ 0.970007 ┆ 0.020839 ┆ -0.022509 │\n",
|
|||
|
|
"│ 000004.SZ ┆ 20250102 ┆ 58.48 ┆ 119760.37 ┆ … ┆ 159807.91 ┆ 0.099106 ┆ 0.131858 ┆ -0.064897 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ 8 ┆ ┆ ┆ │\n",
|
|||
|
|
"│ 000006.SZ ┆ 20250102 ┆ 298.84 ┆ 307195.1 ┆ … ┆ 404264.21 ┆ 0.72392 ┆ 0.028423 ┆ -0.048278 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ 1 ┆ ┆ ┆ │\n",
|
|||
|
|
"│ 000007.SZ ┆ 20250102 ┆ 60.22 ┆ 68219.01 ┆ … ┆ 88380.284 ┆ 0.183495 ┆ 0.391829 ┆ 0.015649 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ 5 ┆ ┆ ┆ │\n",
|
|||
|
|
"└───────────┴────────────┴─────────┴───────────┴───┴───────────┴───────────┴───────────┴───────────┘\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 7
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:54:46.983171Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:46.145439Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 处理前记录数: 3760991\n",
|
|||
|
|
" 处理后记录数: 3760991\n",
|
|||
|
|
" [2/3] 应用处理器: Winsorizer\n",
|
|||
|
|
" 处理前记录数: 3760991\n",
|
|||
|
|
" 处理后记录数: 3760991\n",
|
|||
|
|
" [3/3] 应用处理器: StandardScaler\n",
|
|||
|
|
" 处理前记录数: 3760991\n",
|
|||
|
|
" 处理后记录数: 3760991\n",
|
|||
|
|
"\n",
|
|||
|
|
" 训练集处理后前5行预览:\n",
|
|||
|
|
"shape: (5, 24)\n",
|
|||
|
|
"┌───────────┬────────────┬──────────┬───────────┬───┬──────────┬───────────┬───────────┬───────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_date ┆ high ┆ vol ┆ … ┆ vol_ma20 ┆ market_ca ┆ high_low_ ┆ return_5 │\n",
|
|||
|
|
"│ --- ┆ --- ┆ --- ┆ --- ┆ ┆ --- ┆ p_rank ┆ ratio ┆ --- │\n",
|
|||
|
|
"│ str ┆ str ┆ f64 ┆ f64 ┆ ┆ f64 ┆ --- ┆ --- ┆ f64 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n",
|
|||
|
|
"╞═══════════╪════════════╪══════════╪═══════════╪═══╪══════════╪═══════════╪═══════════╪═══════════╡\n",
|
|||
|
|
"│ 000001.SZ ┆ 20200102 ┆ 7.219126 ┆ 4.505425 ┆ … ┆ null ┆ 1.579213 ┆ null ┆ -0.004746 │\n",
|
|||
|
|
"│ 000002.SZ ┆ 20200102 ┆ 7.219126 ┆ 2.764839 ┆ … ┆ null ┆ 1.579213 ┆ null ┆ -0.011057 │\n",
|
|||
|
|
"│ 000004.SZ ┆ 20200102 ┆ 0.115067 ┆ -0.575482 ┆ … ┆ null ┆ -1.671014 ┆ null ┆ -0.000441 │\n",
|
|||
|
|
"│ 000005.SZ ┆ 20200102 ┆ -0.29753 ┆ -0.285617 ┆ … ┆ null ┆ -0.862878 ┆ null ┆ 0.022337 │\n",
|
|||
|
|
"│ 000006.SZ ┆ 20200102 ┆ 0.761125 ┆ -0.216351 ┆ … ┆ null ┆ 0.324248 ┆ null ┆ 0.012964 │\n",
|
|||
|
|
"└───────────┴────────────┴──────────┴───────────┴───┴──────────┴───────────┴───────────┴───────────┘\n",
|
|||
|
|
"\n",
|
|||
|
|
" 训练集特征统计:\n",
|
|||
|
|
" 特征数: 15\n",
|
|||
|
|
" 样本数: 3760991\n",
|
|||
|
|
" 缺失值统计:\n",
|
|||
|
|
" ma5: 11541 (0.31%)\n",
|
|||
|
|
" ma10: 25950 (0.69%)\n",
|
|||
|
|
" ma20: 54850 (1.46%)\n",
|
|||
|
|
" ma_ratio: 54850 (1.46%)\n",
|
|||
|
|
" volatility_5: 11541 (0.31%)\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 8
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:55:04.341897Z",
|
|||
|
|
"start_time": "2026-03-05T15:54:46.988330Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 训练样本数: 3760991\n",
|
|||
|
|
" 特征数: 15\n",
|
|||
|
|
" 目标变量: return_5\n",
|
|||
|
|
"\n",
|
|||
|
|
" 目标变量统计:\n",
|
|||
|
|
" 均值: 0.001511\n",
|
|||
|
|
" 标准差: 0.062515\n",
|
|||
|
|
" 最小值: -0.165141\n",
|
|||
|
|
" 最大值: 0.225065\n",
|
|||
|
|
" 缺失值: 0\n",
|
|||
|
|
"\n",
|
|||
|
|
" 开始训练...\n",
|
|||
|
|
" 训练完成！\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 9
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:55:04.405805Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:04.349104Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 处理前记录数: 771207\n",
|
|||
|
|
" 处理后记录数: 771207\n",
|
|||
|
|
" [2/3] 应用处理器: Winsorizer\n",
|
|||
|
|
" 处理前记录数: 771207\n",
|
|||
|
|
" 处理后记录数: 771207\n",
|
|||
|
|
" [3/3] 应用处理器: StandardScaler\n",
|
|||
|
|
" 处理前记录数: 771207\n",
|
|||
|
|
" 处理后记录数: 771207\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 10
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:55:05.493456Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:04.412467Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 测试样本数: 771207\n",
|
|||
|
|
" 预测中...\n",
|
|||
|
|
" 预测完成！\n",
|
|||
|
|
"\n",
|
|||
|
|
" 预测结果统计:\n",
|
|||
|
|
" 均值: 0.000637\n",
|
|||
|
|
" 标准差: 0.006533\n",
|
|||
|
|
" 最小值: -0.125675\n",
|
|||
|
|
" 最大值: 0.148845\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 11
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 4.3 查看结果"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:55:05.517099Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:05.500111Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"结果数据形状: (771207, 25)\n",
|
|||
|
|
"结果列: ['ts_code', 'trade_date', 'high', 'vol', 'close', 'low', 'total_mv', 'f_ann_date', 'n_income', 'ma5', 'ma10', 'ma20', 'ma_ratio', 'volatility_5', 'volatility_20', 'vol_ratio', 'return_10', 'return_20', 'return_diff', 'vol_ma5', 'vol_ma20', 'market_cap_rank', 'high_low_ratio', 'return_5', 'prediction']\n",
|
|||
|
|
"\n",
|
|||
|
|
"结果前10行预览:\n",
|
|||
|
|
"shape: (10, 25)\n",
|
|||
|
|
"┌───────────┬───────────┬───────────┬───────────┬───┬───────────┬───────────┬───────────┬──────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_dat ┆ high ┆ vol ┆ … ┆ market_ca ┆ high_low_ ┆ return_5 ┆ predicti │\n",
|
|||
|
|
"│ --- ┆ e ┆ --- ┆ --- ┆ ┆ p_rank ┆ ratio ┆ --- ┆ on │\n",
|
|||
|
|
"│ str ┆ --- ┆ f64 ┆ f64 ┆ ┆ --- ┆ --- ┆ f64 ┆ --- │\n",
|
|||
|
|
"│ ┆ str ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ ┆ f64 │\n",
|
|||
|
|
"╞═══════════╪═══════════╪═══════════╪═══════════╪═══╪═══════════╪═══════════╪═══════════╪══════════╡\n",
|
|||
|
|
"│ 000001.SZ ┆ 20250102 ┆ 7.219126 ┆ 5.477561 ┆ … ┆ 1.575139 ┆ -1.347097 ┆ -0.002622 ┆ -0.00447 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ ┆ ┆ 3 │\n",
|
|||
|
|
"│ 000002.SZ ┆ 20250102 ┆ 7.219126 ┆ 3.337762 ┆ … ┆ 1.500066 ┆ -1.494802 ┆ -0.022509 ┆ -0.00736 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ ┆ ┆ 9 │\n",
|
|||
|
|
"│ 000004.SZ ┆ 20250102 ┆ -0.108318 ┆ -0.23312 ┆ … ┆ -1.525498 ┆ -1.110228 ┆ -0.064897 ┆ 0.017464 │\n",
|
|||
|
|
"│ 000006.SZ ┆ 20250102 ┆ 1.444393 ┆ 0.396576 ┆ … ┆ 0.645142 ┆ -1.46853 ┆ -0.048278 ┆ -0.00465 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ ┆ ┆ 7 │\n",
|
|||
|
|
"│ 000007.SZ ┆ 20250102 ┆ -0.097078 ┆ -0.406275 ┆ … ┆ -1.232326 ┆ -0.209675 ┆ 0.015649 ┆ -0.00109 │\n",
|
|||
|
|
"│ 000008.SZ ┆ 20250102 ┆ -0.054701 ┆ 3.045596 ┆ … ┆ 0.410216 ┆ -1.48541 ┆ -0.066939 ┆ -0.00931 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ ┆ ┆ 9 │\n",
|
|||
|
|
"│ 000009.SZ ┆ 20250102 ┆ 0.045687 ┆ 0.167823 ┆ … ┆ 1.197186 ┆ -1.358101 ┆ -0.036045 ┆ 0.001988 │\n",
|
|||
|
|
"│ 000010.SZ ┆ 20250102 ┆ -0.289132 ┆ 0.530622 ┆ … ┆ -0.872494 ┆ -1.382331 ┆ 0.092123 ┆ -0.00750 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ ┆ ┆ 5 │\n",
|
|||
|
|
"│ 000011.SZ ┆ 20250102 ┆ -0.233641 ┆ -0.493267 ┆ … ┆ -0.098467 ┆ -1.409992 ┆ -0.022094 ┆ -0.00158 │\n",
|
|||
|
|
"│ ┆ ┆ ┆ ┆ ┆ ┆ ┆ ┆ 6 │\n",
|
|||
|
|
"│ 000012.SZ ┆ 20250102 ┆ 0.540518 ┆ -0.084753 ┆ … ┆ 1.006268 ┆ -1.411495 ┆ -0.029188 ┆ 0.000647 │\n",
|
|||
|
|
"└───────────┴───────────┴───────────┴───────────┴───┴───────────┴───────────┴───────────┴──────────┘\n",
|
|||
|
|
"\n",
|
|||
|
|
"结果后5行预览:\n",
|
|||
|
|
"shape: (5, 25)\n",
|
|||
|
|
"┌───────────┬───────────┬───────────┬───────────┬───┬───────────┬───────────┬──────────┬───────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_dat ┆ high ┆ vol ┆ … ┆ market_ca ┆ high_low_ ┆ return_5 ┆ predictio │\n",
|
|||
|
|
"│ --- ┆ e ┆ --- ┆ --- ┆ ┆ p_rank ┆ ratio ┆ --- ┆ n │\n",
|
|||
|
|
"│ str ┆ --- ┆ f64 ┆ f64 ┆ ┆ --- ┆ --- ┆ f64 ┆ --- │\n",
|
|||
|
|
"│ ┆ str ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ ┆ f64 │\n",
|
|||
|
|
"╞═══════════╪═══════════╪═══════════╪═══════════╪═══╪═══════════╪═══════════╪══════════╪═══════════╡\n",
|
|||
|
|
"│ 605588.SH ┆ 20251231 ┆ -0.155411 ┆ -0.600921 ┆ … ┆ -1.041064 ┆ 0.083361 ┆ null ┆ 0.002664 │\n",
|
|||
|
|
"│ 605589.SH ┆ 20251231 ┆ -0.286677 ┆ -0.172371 ┆ … ┆ 1.082326 ┆ 0.586743 ┆ null ┆ 0.003911 │\n",
|
|||
|
|
"│ 605598.SH ┆ 20251231 ┆ 0.167069 ┆ -0.264286 ┆ … ┆ 0.865913 ┆ 1.46704 ┆ null ┆ -0.004255 │\n",
|
|||
|
|
"│ 605599.SH ┆ 20251231 ┆ -0.361225 ┆ -0.487294 ┆ … ┆ 0.623404 ┆ 1.560273 ┆ null ┆ 0.004604 │\n",
|
|||
|
|
"│ 689009.SH ┆ 20251231 ┆ -0.110062 ┆ -0.485904 ┆ … ┆ 1.304467 ┆ -1.339619 ┆ null ┆ -0.000968 │\n",
|
|||
|
|
"└───────────┴───────────┴───────────┴───────────┴───┴───────────┴───────────┴──────────┴───────────┘\n",
|
|||
|
|
"\n",
|
|||
|
|
"每日预测样本数统计:\n",
|
|||
|
|
" 最小: 3147\n",
|
|||
|
|
" 最大: 3186\n",
|
|||
|
|
" 平均: 3173.69\n",
|
|||
|
|
"\n",
|
|||
|
|
"示例日期 20250102 的前10条预测:\n",
|
|||
|
|
"shape: (10, 4)\n",
|
|||
|
|
"┌───────────┬────────────┬───────────┬────────────┐\n",
|
|||
|
|
"│ ts_code ┆ trade_date ┆ return_5 ┆ prediction │\n",
|
|||
|
|
"│ --- ┆ --- ┆ --- ┆ --- │\n",
|
|||
|
|
"│ str ┆ str ┆ f64 ┆ f64 │\n",
|
|||
|
|
"╞═══════════╪════════════╪═══════════╪════════════╡\n",
|
|||
|
|
"│ 000001.SZ ┆ 20250102 ┆ -0.002622 ┆ -0.004473 │\n",
|
|||
|
|
"│ 000002.SZ ┆ 20250102 ┆ -0.022509 ┆ -0.007369 │\n",
|
|||
|
|
"│ 000004.SZ ┆ 20250102 ┆ -0.064897 ┆ 0.017464 │\n",
|
|||
|
|
"│ 000006.SZ ┆ 20250102 ┆ -0.048278 ┆ -0.004657 │\n",
|
|||
|
|
"│ 000007.SZ ┆ 20250102 ┆ 0.015649 ┆ -0.00109 │\n",
|
|||
|
|
"│ 000008.SZ ┆ 20250102 ┆ -0.066939 ┆ -0.009319 │\n",
|
|||
|
|
"│ 000009.SZ ┆ 20250102 ┆ -0.036045 ┆ 0.001988 │\n",
|
|||
|
|
"│ 000010.SZ ┆ 20250102 ┆ 0.092123 ┆ -0.007505 │\n",
|
|||
|
|
"│ 000011.SZ ┆ 20250102 ┆ -0.022094 ┆ -0.001586 │\n",
|
|||
|
|
"│ 000012.SZ ┆ 20250102 ┆ -0.029188 ┆ 0.000647 │\n",
|
|||
|
|
"└───────────┴────────────┴───────────┴────────────┘\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 12
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 4.4 保存结果"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:55:05.827674Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:05.522095Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"# 保存每日 Top5\n",
|
|||
|
|
"print(\"\\n[1/1] 保存每日 Top5 股票...\")\n",
|
|||
|
|
"top5_output_path = os.path.join(OUTPUT_DIR, f\"top5_{date_str}.csv\")\n",
|
|||
|
|
"\n",
|
|||
|
|
"# 按日期分组，取每日 top5\n",
|
|||
|
|
"top5_by_date = []\n",
|
|||
|
|
"unique_dates = results[\"trade_date\"].unique().sort()\n",
|
|||
|
|
"for date in unique_dates:\n",
|
|||
|
|
" day_data = results.filter(results[\"trade_date\"] == date)\n",
|
|||
|
|
" # 按 prediction 降序排序，取前5\n",
|
|||
|
|
" top5 = day_data.sort(\"prediction\", descending=True).head(5)\n",
|
|||
|
|
" top5_by_date.append(top5)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# 合并所有日期的 top5\n",
|
|||
|
|
"top5_results = pl.concat(top5_by_date)\n",
|
|||
|
|
"\n",
|
|||
|
|
"# 格式化日期并调整列顺序：日期、分数、股票\n",
|
|||
|
|
"top5_to_save = top5_results.select(\n",
|
|||
|
|
" [\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",
|
|||
|
|
"# top5_to_save.write_csv(top5_output_path, include_header=True)\n",
|
|||
|
|
"print(f\" 保存路径: {top5_output_path}\")\n",
|
|||
|
|
"print(f\" 保存行数: {len(top5_to_save)}（{len(unique_dates)}个交易日 × 每日top5）\")\n",
|
|||
|
|
"print(f\"\\n 预览（前15行）:\")\n",
|
|||
|
|
"print(top5_to_save.head(15))"
|
|||
|
|
],
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"\n",
|
|||
|
|
"================================================================================\n",
|
|||
|
|
"保存预测结果\n",
|
|||
|
|
"================================================================================\n",
|
|||
|
|
"\n",
|
|||
|
|
"[1/1] 保存每日 Top5 股票...\n",
|
|||
|
|
" 保存路径: output\\top5_20250101_20251231.csv\n",
|
|||
|
|
" 保存行数: 1215（243个交易日 × 每日top5）\n",
|
|||
|
|
"\n",
|
|||
|
|
" 预览（前15行）:\n",
|
|||
|
|
"shape: (15, 3)\n",
|
|||
|
|
"┌────────────┬──────────┬───────────┐\n",
|
|||
|
|
"│ trade_date ┆ score ┆ ts_code │\n",
|
|||
|
|
"│ --- ┆ --- ┆ --- │\n",
|
|||
|
|
"│ str ┆ f64 ┆ str │\n",
|
|||
|
|
"╞════════════╪══════════╪═══════════╡\n",
|
|||
|
|
"│ 2025-01-02 ┆ 0.130576 ┆ 603007.SH │\n",
|
|||
|
|
"│ 2025-01-02 ┆ 0.088839 ┆ 603559.SH │\n",
|
|||
|
|
"│ 2025-01-02 ┆ 0.060968 ┆ 000595.SZ │\n",
|
|||
|
|
"│ 2025-01-02 ┆ 0.054302 ┆ 600811.SH │\n",
|
|||
|
|
"│ 2025-01-02 ┆ 0.045811 ┆ 603366.SH │\n",
|
|||
|
|
"│ … ┆ … ┆ … │\n",
|
|||
|
|
"│ 2025-01-06 ┆ 0.143688 ┆ 603007.SH │\n",
|
|||
|
|
"│ 2025-01-06 ┆ 0.063078 ┆ 002691.SZ │\n",
|
|||
|
|
"│ 2025-01-06 ┆ 0.062373 ┆ 603959.SH │\n",
|
|||
|
|
"│ 2025-01-06 ┆ 0.055252 ┆ 000638.SZ │\n",
|
|||
|
|
"│ 2025-01-06 ┆ 0.047705 ┆ 002713.SZ │\n",
|
|||
|
|
"└────────────┴──────────┴───────────┘\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 13
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 4.5 特征重要性"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "code",
|
|||
|
|
"metadata": {
|
|||
|
|
"ExecuteTime": {
|
|||
|
|
"end_time": "2026-03-05T15:55:05.840200Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:05.836355Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"return_10 3244.585386\n",
|
|||
|
|
"ma_ratio 2871.645070\n",
|
|||
|
|
"return_20 2686.807540\n",
|
|||
|
|
"vol_ratio 2667.200664\n",
|
|||
|
|
"high_low_ratio 2461.679219\n",
|
|||
|
|
"return_diff 1491.578852\n",
|
|||
|
|
"volatility_5 1360.579366\n",
|
|||
|
|
"market_cap_rank 697.769018\n",
|
|||
|
|
"vol_ma5 665.639110\n",
|
|||
|
|
"vol_ma20 640.332628\n",
|
|||
|
|
"n_income 536.010082\n",
|
|||
|
|
"ma5 489.527820\n",
|
|||
|
|
"ma20 481.715007\n",
|
|||
|
|
"ma10 303.121463\n",
|
|||
|
|
"volatility_20 224.481188\n",
|
|||
|
|
"dtype: float64\n",
|
|||
|
|
"\n",
|
|||
|
|
"================================================================================\n",
|
|||
|
|
"训练完成！\n",
|
|||
|
|
"================================================================================\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 14
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"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": {
|
|||
|
|
"end_time": "2026-03-05T15:55:06.004470Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:05.857163Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"特征数量: 15\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 15
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"cell_type": "markdown",
|
|||
|
|
"metadata": {},
|
|||
|
|
"source": [
|
|||
|
|
"### 5.1 绘制特征重要性（辅助特征选择）\n",
|
|||
|
|
"\n",
|
|||
|
|
"**解读**：\n",
|
|||
|
|
"- 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": {
|
|||
|
|
"end_time": "2026-03-05T15:55:06.162872Z",
|
|||
|
|
"start_time": "2026-03-05T15:55:06.013403Z"
|
|||
|
|
}
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
" 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'),\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，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\")"
|
|||
|
|
],
|
|||
|
|
"outputs": [
|
|||
|
|
{
|
|||
|
|
"name": "stdout",
|
|||
|
|
"output_type": "stream",
|
|||
|
|
"text": [
|
|||
|
|
"绘制特征重要性...\n"
|
|||
|
|
]
|
|||
|
|
},
|
|||
|
|
{
|
|||
|
|
"data": {
|
|||
|
|
"text/plain": [
|
|||
|
|
"<Figure size 1000x800 with 1 Axes>"
|
|||
|
|
],
|
|||
|
|
"image/png": "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
|
|||
|
|
},
|
|||
|
|
"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",
|
|||
|
|
"return_10 3244.585386\n",
|
|||
|
|
"ma_ratio 2871.645070\n",
|
|||
|
|
"return_20 2686.807540\n",
|
|||
|
|
"vol_ratio 2667.200664\n",
|
|||
|
|
"high_low_ratio 2461.679219\n",
|
|||
|
|
"return_diff 1491.578852\n",
|
|||
|
|
"volatility_5 1360.579366\n",
|
|||
|
|
"market_cap_rank 697.769018\n",
|
|||
|
|
"vol_ma5 665.639110\n",
|
|||
|
|
"vol_ma20 640.332628\n",
|
|||
|
|
"n_income 536.010082\n",
|
|||
|
|
"ma5 489.527820\n",
|
|||
|
|
"ma20 481.715007\n",
|
|||
|
|
"ma10 303.121463\n",
|
|||
|
|
"volatility_20 224.481188\n",
|
|||
|
|
"dtype: float64\n",
|
|||
|
|
"\n",
|
|||
|
|
"所有特征都有一定重要性\n"
|
|||
|
|
]
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"execution_count": 16
|
|||
|
|
}
|
|||
|
|
],
|
|||
|
|
"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
|
|||
|
|
}
|