2025-03-30 01:55:21 +08:00
|
|
|
|
{
|
|
|
|
|
|
"cells": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "79a7758178bafdd3",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"jupyter": {
|
|
|
|
|
|
"source_hidden": true
|
|
|
|
|
|
},
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:33:30.607252Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:33:30.170544Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"# %load_ext autoreload\n",
|
|
|
|
|
|
"# %autoreload 2\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"import pandas as pd\n",
|
|
|
|
|
|
"import warnings\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"warnings.filterwarnings(\"ignore\")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"pd.set_option('display.max_columns', None)\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 1
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "a79cafb06a7e0e43",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"scrolled": true,
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:34:19.160370Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:33:30.794750Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"from utils.utils import read_and_merge_h5_data\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"print('daily data')\n",
|
|
|
|
|
|
"df = read_and_merge_h5_data('../../data/daily_data.h5', key='daily_data',\n",
|
|
|
|
|
|
" columns=['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'pct_chg'],\n",
|
|
|
|
|
|
" df=None)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"print('daily basic')\n",
|
|
|
|
|
|
"df = read_and_merge_h5_data('../../data/daily_basic.h5', key='daily_basic',\n",
|
|
|
|
|
|
" columns=['ts_code', 'trade_date', 'turnover_rate', 'pe_ttm', 'circ_mv', 'volume_ratio',\n",
|
|
|
|
|
|
" 'is_st'], df=df, join='inner')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"print('stk limit')\n",
|
|
|
|
|
|
"df = read_and_merge_h5_data('../../data/stk_limit.h5', key='stk_limit',\n",
|
|
|
|
|
|
" columns=['ts_code', 'trade_date', 'pre_close', 'up_limit', 'down_limit'],\n",
|
|
|
|
|
|
" df=df)\n",
|
|
|
|
|
|
"print('money flow')\n",
|
|
|
|
|
|
"df = read_and_merge_h5_data('../../data/money_flow.h5', key='money_flow',\n",
|
|
|
|
|
|
" columns=['ts_code', 'trade_date', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol',\n",
|
|
|
|
|
|
" 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol'],\n",
|
|
|
|
|
|
" df=df)\n",
|
|
|
|
|
|
"print('cyq perf')\n",
|
|
|
|
|
|
"df = read_and_merge_h5_data('../../data/cyq_perf.h5', key='cyq_perf',\n",
|
|
|
|
|
|
" columns=['ts_code', 'trade_date', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct',\n",
|
|
|
|
|
|
" 'cost_50pct',\n",
|
|
|
|
|
|
" 'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate'],\n",
|
|
|
|
|
|
" df=df)\n",
|
|
|
|
|
|
"print(df.info())"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"daily data\n",
|
|
|
|
|
|
"daily basic\n",
|
|
|
|
|
|
"stk limit\n",
|
|
|
|
|
|
"money flow\n",
|
|
|
|
|
|
"cyq perf\n",
|
|
|
|
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"RangeIndex: 8477357 entries, 0 to 8477356\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Data columns (total 31 columns):\n",
|
|
|
|
|
|
" # Column Dtype \n",
|
|
|
|
|
|
"--- ------ ----- \n",
|
|
|
|
|
|
" 0 ts_code object \n",
|
|
|
|
|
|
" 1 trade_date datetime64[ns]\n",
|
|
|
|
|
|
" 2 open float64 \n",
|
|
|
|
|
|
" 3 close float64 \n",
|
|
|
|
|
|
" 4 high float64 \n",
|
|
|
|
|
|
" 5 low float64 \n",
|
|
|
|
|
|
" 6 vol float64 \n",
|
|
|
|
|
|
" 7 pct_chg float64 \n",
|
|
|
|
|
|
" 8 turnover_rate float64 \n",
|
|
|
|
|
|
" 9 pe_ttm float64 \n",
|
|
|
|
|
|
" 10 circ_mv float64 \n",
|
|
|
|
|
|
" 11 volume_ratio float64 \n",
|
|
|
|
|
|
" 12 is_st bool \n",
|
|
|
|
|
|
" 13 up_limit float64 \n",
|
|
|
|
|
|
" 14 down_limit float64 \n",
|
|
|
|
|
|
" 15 buy_sm_vol float64 \n",
|
|
|
|
|
|
" 16 sell_sm_vol float64 \n",
|
|
|
|
|
|
" 17 buy_lg_vol float64 \n",
|
|
|
|
|
|
" 18 sell_lg_vol float64 \n",
|
|
|
|
|
|
" 19 buy_elg_vol float64 \n",
|
|
|
|
|
|
" 20 sell_elg_vol float64 \n",
|
|
|
|
|
|
" 21 net_mf_vol float64 \n",
|
|
|
|
|
|
" 22 his_low float64 \n",
|
|
|
|
|
|
" 23 his_high float64 \n",
|
|
|
|
|
|
" 24 cost_5pct float64 \n",
|
|
|
|
|
|
" 25 cost_15pct float64 \n",
|
|
|
|
|
|
" 26 cost_50pct float64 \n",
|
|
|
|
|
|
" 27 cost_85pct float64 \n",
|
|
|
|
|
|
" 28 cost_95pct float64 \n",
|
|
|
|
|
|
" 29 weight_avg float64 \n",
|
|
|
|
|
|
" 30 winner_rate float64 \n",
|
|
|
|
|
|
"dtypes: bool(1), datetime64[ns](1), float64(28), object(1)\n",
|
|
|
|
|
|
"memory usage: 1.9+ GB\n",
|
|
|
|
|
|
"None\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"execution_count": 2
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "cac01788dac10678",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"jupyter": {
|
|
|
|
|
|
"source_hidden": true
|
|
|
|
|
|
},
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:34:30.996034Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:34:19.168375Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"print('industry')\n",
|
|
|
|
|
|
"industry_df = read_and_merge_h5_data('../../data/industry_data.h5', key='industry_data',\n",
|
|
|
|
|
|
" columns=['ts_code', 'l2_code', 'in_date'],\n",
|
|
|
|
|
|
" df=None, on=['ts_code'], join='left')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def merge_with_industry_data(df, industry_df):\n",
|
|
|
|
|
|
" # 确保日期字段是 datetime 类型\n",
|
|
|
|
|
|
" df['trade_date'] = pd.to_datetime(df['trade_date'])\n",
|
|
|
|
|
|
" industry_df['in_date'] = pd.to_datetime(industry_df['in_date'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 对 industry_df 按 ts_code 和 in_date 排序\n",
|
|
|
|
|
|
" industry_df_sorted = industry_df.sort_values(['in_date', 'ts_code'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 对原始 df 按 ts_code 和 trade_date 排序\n",
|
|
|
|
|
|
" df_sorted = df.sort_values(['trade_date', 'ts_code'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 使用 merge_asof 进行向后合并\n",
|
|
|
|
|
|
" merged = pd.merge_asof(\n",
|
|
|
|
|
|
" df_sorted,\n",
|
|
|
|
|
|
" industry_df_sorted,\n",
|
|
|
|
|
|
" by='ts_code', # 按 ts_code 分组\n",
|
|
|
|
|
|
" left_on='trade_date',\n",
|
|
|
|
|
|
" right_on='in_date',\n",
|
|
|
|
|
|
" direction='backward'\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 获取每个 ts_code 的最早 in_date 记录\n",
|
|
|
|
|
|
" min_in_date_per_ts = (industry_df_sorted\n",
|
|
|
|
|
|
" .groupby('ts_code')\n",
|
|
|
|
|
|
" .first()\n",
|
|
|
|
|
|
" .reset_index()[['ts_code', 'l2_code']])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 填充未匹配到的记录（trade_date 早于所有 in_date 的情况）\n",
|
|
|
|
|
|
" merged['l2_code'] = merged['l2_code'].fillna(\n",
|
|
|
|
|
|
" merged['ts_code'].map(min_in_date_per_ts.set_index('ts_code')['l2_code'])\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 保留需要的列并重置索引\n",
|
|
|
|
|
|
" result = merged.reset_index(drop=True)\n",
|
|
|
|
|
|
" return result\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# 使用示例\n",
|
|
|
|
|
|
"df = merge_with_industry_data(df, industry_df)\n",
|
|
|
|
|
|
"# print(mdf[mdf['ts_code'] == '600751.SH'][['ts_code', 'trade_date', 'l2_code']])"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"industry\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"execution_count": 3
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "c4e9e1d31da6dba6",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:34:31.276589Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:34:31.060910Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"def calculate_indicators(df):\n",
|
|
|
|
|
|
" \"\"\"\n",
|
|
|
|
|
|
" 计算四个指标：当日涨跌幅、5日移动平均、RSI、MACD。\n",
|
|
|
|
|
|
" \"\"\"\n",
|
|
|
|
|
|
" df = df.sort_values('trade_date')\n",
|
|
|
|
|
|
" df['daily_return'] = (df['close'] - df['pre_close']) / df['pre_close'] * 100\n",
|
|
|
|
|
|
" # df['5_day_ma'] = df['close'].rolling(window=5).mean()\n",
|
|
|
|
|
|
" delta = df['close'].diff()\n",
|
|
|
|
|
|
" gain = delta.where(delta > 0, 0)\n",
|
|
|
|
|
|
" loss = -delta.where(delta < 0, 0)\n",
|
|
|
|
|
|
" avg_gain = gain.rolling(window=14).mean()\n",
|
|
|
|
|
|
" avg_loss = loss.rolling(window=14).mean()\n",
|
|
|
|
|
|
" rs = avg_gain / avg_loss\n",
|
|
|
|
|
|
" df['RSI'] = 100 - (100 / (1 + rs))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算MACD\n",
|
|
|
|
|
|
" ema12 = df['close'].ewm(span=12, adjust=False).mean()\n",
|
|
|
|
|
|
" ema26 = df['close'].ewm(span=26, adjust=False).mean()\n",
|
|
|
|
|
|
" df['MACD'] = ema12 - ema26\n",
|
|
|
|
|
|
" df['Signal_line'] = df['MACD'].ewm(span=9, adjust=False).mean()\n",
|
|
|
|
|
|
" df['MACD_hist'] = df['MACD'] - df['Signal_line']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 4. 情绪因子1：市场上涨比例（Up Ratio）\n",
|
|
|
|
|
|
" df['up_ratio'] = df['daily_return'].apply(lambda x: 1 if x > 0 else 0)\n",
|
|
|
|
|
|
" df['up_ratio_20d'] = df['up_ratio'].rolling(window=20).mean() # 过去20天上涨比例\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 5. 情绪因子2：成交量变化率（Volume Change Rate）\n",
|
|
|
|
|
|
" df['volume_mean'] = df['vol'].rolling(window=20).mean() # 过去20天的平均成交量\n",
|
|
|
|
|
|
" df['volume_change_rate'] = (df['vol'] - df['volume_mean']) / df['volume_mean'] * 100 # 成交量变化率\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 6. 情绪因子3：波动率（Volatility）\n",
|
|
|
|
|
|
" df['volatility'] = df['daily_return'].rolling(window=20).std() # 过去20天的日收益率标准差\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 7. 情绪因子4：成交额变化率（Amount Change Rate）\n",
|
|
|
|
|
|
" df['amount_mean'] = df['amount'].rolling(window=20).mean() # 过去20天的平均成交额\n",
|
|
|
|
|
|
" df['amount_change_rate'] = (df['amount'] - df['amount_mean']) / df['amount_mean'] * 100 # 成交额变化率\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return df\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def generate_index_indicators(h5_filename):\n",
|
|
|
|
|
|
" df = pd.read_hdf(h5_filename, key='index_data')\n",
|
|
|
|
|
|
" df['trade_date'] = pd.to_datetime(df['trade_date'], format='%Y%m%d')\n",
|
|
|
|
|
|
" df = df.sort_values('trade_date')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算每个ts_code的相关指标\n",
|
|
|
|
|
|
" df_indicators = []\n",
|
|
|
|
|
|
" for ts_code in df['ts_code'].unique():\n",
|
|
|
|
|
|
" df_index = df[df['ts_code'] == ts_code].copy()\n",
|
|
|
|
|
|
" df_index = calculate_indicators(df_index)\n",
|
|
|
|
|
|
" df_indicators.append(df_index)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 合并所有指数的结果\n",
|
|
|
|
|
|
" df_all_indicators = pd.concat(df_indicators, ignore_index=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 保留trade_date列，并将同一天的数据按ts_code合并成一行\n",
|
|
|
|
|
|
" df_final = df_all_indicators.pivot_table(\n",
|
|
|
|
|
|
" index='trade_date',\n",
|
|
|
|
|
|
" columns='ts_code',\n",
|
|
|
|
|
|
" values=['daily_return', 'RSI', 'MACD', 'Signal_line',\n",
|
|
|
|
|
|
" 'MACD_hist', 'up_ratio_20d', 'volume_change_rate', 'volatility',\n",
|
|
|
|
|
|
" 'amount_change_rate', 'amount_mean'],\n",
|
|
|
|
|
|
" aggfunc='last'\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df_final.columns = [f\"{col[1]}_{col[0]}\" for col in df_final.columns]\n",
|
|
|
|
|
|
" df_final = df_final.reset_index()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return df_final\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# 使用函数\n",
|
|
|
|
|
|
"h5_filename = '../../data/index_data.h5'\n",
|
|
|
|
|
|
"index_data = generate_index_indicators(h5_filename)\n",
|
|
|
|
|
|
"index_data = index_data.dropna()\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 4
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "a735bc02ceb4d872",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"jupyter": {
|
|
|
|
|
|
"source_hidden": true
|
|
|
|
|
|
},
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:34:31.348068Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:34:31.304847Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"import numpy as np\n",
|
|
|
|
|
|
"import talib\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def get_rolling_factor(df):\n",
|
|
|
|
|
|
" old_columns = df.columns.tolist()[:]\n",
|
|
|
|
|
|
" # 按股票和日期排序\n",
|
|
|
|
|
|
" df = df.sort_values(by=['ts_code', 'trade_date'])\n",
|
|
|
|
|
|
" grouped = df.groupby('ts_code', group_keys=False)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # df[\"gap_next_open\"] = (df[\"open\"].shift(-1) - df[\"close\"]) / df[\"close\"]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['return_skew'] = grouped['pct_chg'].rolling(window=5).skew().reset_index(0, drop=True)\n",
|
|
|
|
|
|
" df['return_kurtosis'] = grouped['pct_chg'].rolling(window=5).kurt().reset_index(0, drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 因子 1：短期成交量变化率\n",
|
|
|
|
|
|
" df['volume_change_rate'] = (\n",
|
|
|
|
|
|
" grouped['vol'].rolling(window=2).mean() /\n",
|
|
|
|
|
|
" grouped['vol'].rolling(window=10).mean() - 1\n",
|
|
|
|
|
|
" ).reset_index(level=0, drop=True) # 确保索引对齐\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 因子 2：成交量突破信号\n",
|
|
|
|
|
|
" max_volume = grouped['vol'].rolling(window=5).max().reset_index(level=0, drop=True) # 确保索引对齐\n",
|
|
|
|
|
|
" df['cat_volume_breakout'] = (df['vol'] > max_volume)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 因子 3：换手率均线偏离度\n",
|
|
|
|
|
|
" mean_turnover = grouped['turnover_rate'].rolling(window=3).mean().reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
" std_turnover = grouped['turnover_rate'].rolling(window=3).std().reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
" df['turnover_deviation'] = (df['turnover_rate'] - mean_turnover) / std_turnover\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 因子 4：换手率激增信号\n",
|
|
|
|
|
|
" df['cat_turnover_spike'] = (df['turnover_rate'] > mean_turnover + 2 * std_turnover)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 因子 5：量比均值\n",
|
|
|
|
|
|
" df['avg_volume_ratio'] = grouped['volume_ratio'].rolling(window=3).mean().reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 因子 6：量比突破信号\n",
|
|
|
|
|
|
" max_volume_ratio = grouped['volume_ratio'].rolling(window=5).max().reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
" df['cat_volume_ratio_breakout'] = (df['volume_ratio'] > max_volume_ratio)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['vol_spike'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(x['vol'].rolling(20).mean(), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['vol_std_5'] = df['vol'].pct_change().rolling(5).std()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算 ATR\n",
|
|
|
|
|
|
" df['atr_14'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.ATR(x['high'].values, x['low'].values, x['close'].values, timeperiod=14),\n",
|
|
|
|
|
|
" index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['atr_6'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.ATR(x['high'].values, x['low'].values, x['close'].values, timeperiod=6),\n",
|
|
|
|
|
|
" index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算 OBV 及其均线\n",
|
|
|
|
|
|
" df['obv'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.OBV(x['close'].values, x['vol'].values), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['maobv_6'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.SMA(x['obv'].values, timeperiod=6), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['rsi_3'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.RSI(x['close'].values, timeperiod=3), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" # df['rsi_6'] = grouped.apply(\n",
|
|
|
|
|
|
" # lambda x: pd.Series(talib.RSI(x['close'].values, timeperiod=6), index=x.index)\n",
|
|
|
|
|
|
" # )\n",
|
|
|
|
|
|
" # df['rsi_9'] = grouped.apply(\n",
|
|
|
|
|
|
" # lambda x: pd.Series(talib.RSI(x['close'].values, timeperiod=9), index=x.index)\n",
|
|
|
|
|
|
" # )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算 return_10 和 return_20\n",
|
|
|
|
|
|
" df['return_5'] = grouped['close'].apply(lambda x: x / x.shift(5) - 1)\n",
|
|
|
|
|
|
" # df['return_10'] = grouped['close'].apply(lambda x: x / x.shift(10) - 1)\n",
|
|
|
|
|
|
" df['return_20'] = grouped['close'].apply(lambda x: x / x.shift(20) - 1)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # df['avg_close_5'] = grouped['close'].apply(lambda x: x.rolling(window=5).mean() / x)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算标准差指标\n",
|
|
|
|
|
|
" df['std_return_5'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=5).std())\n",
|
|
|
|
|
|
" # df['std_return_15'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=15).std())\n",
|
|
|
|
|
|
" # df['std_return_25'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=25).std())\n",
|
|
|
|
|
|
" df['std_return_90'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=90).std())\n",
|
|
|
|
|
|
" df['std_return_90_2'] = grouped['close'].apply(lambda x: x.shift(10).pct_change().rolling(window=90).std())\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算 EMA 指标\n",
|
|
|
|
|
|
" df['_ema_5'] = grouped['close'].apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=5), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['_ema_13'] = grouped['close'].apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=13), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['_ema_20'] = grouped['close'].apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=20), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['_ema_60'] = grouped['close'].apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=60), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算 act_factor1, act_factor2, act_factor3, act_factor4\n",
|
|
|
|
|
|
" df['act_factor1'] = grouped['_ema_5'].apply(\n",
|
|
|
|
|
|
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 50\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['act_factor2'] = grouped['_ema_13'].apply(\n",
|
|
|
|
|
|
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 40\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['act_factor3'] = grouped['_ema_20'].apply(\n",
|
|
|
|
|
|
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 21\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" df['act_factor4'] = grouped['_ema_60'].apply(\n",
|
|
|
|
|
|
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 10\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 根据 trade_date 截面计算排名\n",
|
|
|
|
|
|
" df['rank_act_factor1'] = df.groupby('trade_date', group_keys=False)['act_factor1'].rank(ascending=False, pct=True)\n",
|
|
|
|
|
|
" df['rank_act_factor2'] = df.groupby('trade_date', group_keys=False)['act_factor2'].rank(ascending=False, pct=True)\n",
|
|
|
|
|
|
" df['rank_act_factor3'] = df.groupby('trade_date', group_keys=False)['act_factor3'].rank(ascending=False, pct=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['log(circ_mv)'] = np.log(df['circ_mv'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def rolling_covariance(x, y, window):\n",
|
|
|
|
|
|
" return x.rolling(window).cov(y)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def delta(series, period):\n",
|
|
|
|
|
|
" return series.diff(period)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def rank(series):\n",
|
|
|
|
|
|
" return series.rank(pct=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def stddev(series, window):\n",
|
|
|
|
|
|
" return series.rolling(window).std()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" window_high_volume = 5\n",
|
|
|
|
|
|
" window_close_stddev = 20\n",
|
|
|
|
|
|
" period_delta = 5\n",
|
|
|
|
|
|
" df['cov'] = rolling_covariance(df['high'], df['vol'], window_high_volume)\n",
|
|
|
|
|
|
" df['delta_cov'] = delta(df['cov'], period_delta)\n",
|
|
|
|
|
|
" df['_rank_stddev'] = rank(stddev(df['close'], window_close_stddev))\n",
|
|
|
|
|
|
" df['alpha_22_improved'] = -1 * df['delta_cov'] * df['_rank_stddev']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['alpha_003'] = np.where(df['high'] != df['low'],\n",
|
|
|
|
|
|
" (df['close'] - df['open']) / (df['high'] - df['low']),\n",
|
|
|
|
|
|
" 0)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['alpha_007'] = grouped.apply(lambda x: x['close'].rolling(5).corr(x['vol'])).reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
" df['alpha_007'] = df.groupby('trade_date', group_keys=False)['alpha_007'].rank(ascending=True, pct=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['alpha_013'] = grouped['close'].transform(lambda x: x.rolling(5).sum() - x.rolling(20).sum())\n",
|
|
|
|
|
|
" df['alpha_013'] = df.groupby('trade_date', group_keys=False)['alpha_013'].rank(ascending=True, pct=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['cat_up_limit'] = (df['close'] == df['up_limit']) # 是否涨停（1表示涨停，0表示未涨停）\n",
|
|
|
|
|
|
" df['cat_down_limit'] = (df['close'] == df['down_limit']) # 是否跌停（1表示跌停，0表示未跌停）\n",
|
|
|
|
|
|
" df['up_limit_count_10d'] = grouped['cat_up_limit'].rolling(window=10, min_periods=1).sum().reset_index(level=0,\n",
|
|
|
|
|
|
" drop=True)\n",
|
|
|
|
|
|
" df['down_limit_count_10d'] = grouped['cat_down_limit'].rolling(window=10, min_periods=1).sum().reset_index(level=0,\n",
|
|
|
|
|
|
" drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 3. 最近连续涨跌停天数\n",
|
|
|
|
|
|
" def calculate_consecutive_limits(series):\n",
|
|
|
|
|
|
" \"\"\"\n",
|
|
|
|
|
|
" 计算连续涨停/跌停天数。\n",
|
|
|
|
|
|
" \"\"\"\n",
|
|
|
|
|
|
" consecutive_up = series * (series.groupby((series != series.shift()).cumsum()).cumcount() + 1)\n",
|
|
|
|
|
|
" consecutive_down = series * (series.groupby((series != series.shift()).cumsum()).cumcount() + 1)\n",
|
|
|
|
|
|
" return consecutive_up, consecutive_down\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 连续涨停天数\n",
|
|
|
|
|
|
" df['consecutive_up_limit'] = grouped['cat_up_limit'].apply(\n",
|
|
|
|
|
|
" lambda x: calculate_consecutive_limits(x)[0]\n",
|
|
|
|
|
|
" ).reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['vol_break'] = np.where((df['close'] > df['cost_85pct']) & (df['volume_ratio'] > 2), 1, 0)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['weight_roc5'] = grouped['weight_avg'].apply(lambda x: x.pct_change(5))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def rolling_corr(group):\n",
|
|
|
|
|
|
" roc_close = group['close'].pct_change()\n",
|
|
|
|
|
|
" roc_weight = group['weight_avg'].pct_change()\n",
|
|
|
|
|
|
" return roc_close.rolling(10).corr(roc_weight)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['price_cost_divergence'] = grouped.apply(rolling_corr)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['smallcap_concentration'] = (1 / df['log(circ_mv)']) * (df['cost_85pct'] - df['cost_15pct'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 16. 筹码稳定性指数 (20日波动率)\n",
|
|
|
|
|
|
" df['weight_std20'] = grouped['weight_avg'].apply(lambda x: x.rolling(20).std())\n",
|
|
|
|
|
|
" df['cost_stability'] = df['weight_std20'] / grouped['weight_avg'].transform(lambda x: x.rolling(20).mean())\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 17. 成本区间突破标记\n",
|
|
|
|
|
|
" df['high_cost_break_days'] = grouped.apply(lambda g: g['close'].gt(g['cost_95pct']).rolling(5).sum())\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 20. 筹码-流动性风险\n",
|
|
|
|
|
|
" df['liquidity_risk'] = (df['cost_95pct'] - df['cost_5pct']) * (\n",
|
|
|
|
|
|
" 1 / grouped['vol'].transform(lambda x: x.rolling(10).mean()))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 7. 市值波动率因子\n",
|
|
|
|
|
|
" df['turnover_std'] = grouped['turnover_rate'].rolling(window=20).std().reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
" df['mv_volatility'] = grouped.apply(lambda x: x['turnover_std'] / x['log(circ_mv)']).reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 8. 市值成长性因子\n",
|
|
|
|
|
|
" df['volume_growth'] = grouped['vol'].pct_change(periods=20).reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
" df['mv_growth'] = grouped.apply(lambda x: x['volume_growth'] / x['log(circ_mv)']).reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df[\"ar\"] = df[\"high\"].div(df[\"open\"]).rolling(3).sum() / df[\"open\"].div(df[\"low\"]).rolling(3).sum() * 100\n",
|
|
|
|
|
|
" # 计算 BR 指标\n",
|
|
|
|
|
|
" df[\"pre_close\"] = df[\"close\"].shift(1)\n",
|
|
|
|
|
|
" df[\"br_up\"] = (df[\"high\"] - df[\"pre_close\"]).clip(lower=0)\n",
|
|
|
|
|
|
" df[\"br_down\"] = (df[\"pre_close\"] - df[\"low\"]).clip(lower=0)\n",
|
|
|
|
|
|
" df[\"br\"] = df[\"br_up\"].rolling(3).sum() / df[\"br_down\"].rolling(3).sum() * 100\n",
|
|
|
|
|
|
" df['arbr'] = df['ar'] - df['br']\n",
|
|
|
|
|
|
" df.drop(columns=[\"pre_close\", \"br_up\", \"br_down\", 'ar', 'br'], inplace=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df.drop(columns=['weight_std20'], inplace=True, errors='ignore')\n",
|
|
|
|
|
|
" new_columns = [col for col in df.columns.tolist()[:] if col not in old_columns]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return df, new_columns\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def get_simple_factor(df):\n",
|
|
|
|
|
|
" old_columns = df.columns.tolist()[:]\n",
|
|
|
|
|
|
" df = df.sort_values(by=['ts_code', 'trade_date'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" alpha = 0.5\n",
|
|
|
|
|
|
" df['momentum_factor'] = df['volume_change_rate'] + alpha * df['turnover_deviation']\n",
|
|
|
|
|
|
" df['resonance_factor'] = df['volume_ratio'] * df['pct_chg']\n",
|
|
|
|
|
|
" df['log_close'] = np.log(df['close'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['cat_vol_spike'] = df['vol'] > 2 * df['vol_spike']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['up'] = (df['high'] - df[['close', 'open']].max(axis=1)) / df['close']\n",
|
|
|
|
|
|
" df['down'] = (df[['close', 'open']].min(axis=1) - df['low']) / df['close']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['obv-maobv_6'] = df['obv'] - df['maobv_6']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算比值指标\n",
|
|
|
|
|
|
" df['std_return_5 / std_return_90'] = df['std_return_5'] / df['std_return_90']\n",
|
|
|
|
|
|
" # df['std_return_5 / std_return_25'] = df['std_return_5'] / df['std_return_25']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算标准差差值\n",
|
|
|
|
|
|
" df['std_return_90 - std_return_90_2'] = df['std_return_90'] - df['std_return_90_2']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # df['cat_af1'] = df['act_factor1'] > 0\n",
|
|
|
|
|
|
" df['cat_af2'] = df['act_factor2'] > df['act_factor1']\n",
|
|
|
|
|
|
" df['cat_af3'] = df['act_factor3'] > df['act_factor2']\n",
|
|
|
|
|
|
" df['cat_af4'] = df['act_factor4'] > df['act_factor3']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算 act_factor5 和 act_factor6\n",
|
|
|
|
|
|
" df['act_factor5'] = df['act_factor1'] + df['act_factor2'] + df['act_factor3'] + df['act_factor4']\n",
|
|
|
|
|
|
" df['act_factor6'] = (df['act_factor1'] - df['act_factor2']) / np.sqrt(\n",
|
|
|
|
|
|
" df['act_factor1'] ** 2 + df['act_factor2'] ** 2)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['active_buy_volume_large'] = df['buy_lg_vol'] / df['net_mf_vol']\n",
|
|
|
|
|
|
" df['active_buy_volume_big'] = df['buy_elg_vol'] / df['net_mf_vol']\n",
|
|
|
|
|
|
" df['active_buy_volume_small'] = df['buy_sm_vol'] / df['net_mf_vol']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['buy_lg_vol_minus_sell_lg_vol'] = (df['buy_lg_vol'] - df['sell_lg_vol']) / df['net_mf_vol']\n",
|
|
|
|
|
|
" df['buy_elg_vol_minus_sell_elg_vol'] = (df['buy_elg_vol'] - df['sell_elg_vol']) / df['net_mf_vol']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['log(circ_mv)'] = np.log(df['circ_mv'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['ctrl_strength'] = (df['cost_85pct'] - df['cost_15pct']) / (df['his_high'] - df['his_low'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['low_cost_dev'] = (df['close'] - df['cost_5pct']) / (df['cost_50pct'] - df['cost_5pct'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['asymmetry'] = (df['cost_95pct'] - df['cost_50pct']) / (df['cost_50pct'] - df['cost_5pct'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['lock_factor'] = df['turnover_rate'] * (\n",
|
|
|
|
|
|
" 1 - (df['cost_95pct'] - df['cost_5pct']) / (df['his_high'] - df['his_low']))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['cat_vol_break'] = (df['close'] > df['cost_85pct']) & (df['volume_ratio'] > 2)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['cost_atr_adj'] = (df['cost_95pct'] - df['cost_5pct']) / df['atr_14']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 12. 小盘股筹码集中度\n",
|
|
|
|
|
|
" df['smallcap_concentration'] = (1 / df['log(circ_mv)']) * (df['cost_85pct'] - df['cost_15pct'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['cat_golden_resonance'] = ((df['close'] > df['weight_avg']) &\n",
|
|
|
|
|
|
" (df['volume_ratio'] > 1.5) &\n",
|
|
|
|
|
|
" (df['winner_rate'] > 0.7))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['mv_turnover_ratio'] = df['turnover_rate'] / df['log(circ_mv)']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['mv_adjusted_volume'] = df['vol'] / df['log(circ_mv)']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['mv_weighted_turnover'] = df['turnover_rate'] * (1 / df['log(circ_mv)'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['nonlinear_mv_volume'] = df['vol'] / df['log(circ_mv)']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['mv_volume_ratio'] = df['volume_ratio'] / df['log(circ_mv)']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['mv_momentum'] = df['turnover_rate'] * df['volume_ratio'] / df['log(circ_mv)']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" drop_columns = [col for col in df.columns if col.startswith('_')]\n",
|
|
|
|
|
|
" df.drop(columns=drop_columns, inplace=True, errors='ignore')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" new_columns = [col for col in df.columns.tolist()[:] if col not in old_columns]\n",
|
|
|
|
|
|
" return df, new_columns\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 5
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "53f86ddc0677a6d7",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"jupyter": {
|
|
|
|
|
|
"source_hidden": true
|
|
|
|
|
|
},
|
|
|
|
|
|
"scrolled": true,
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:34:36.714777Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:34:31.369443Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"from utils.factor import get_act_factor\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def read_industry_data(h5_filename):\n",
|
|
|
|
|
|
" # 读取 H5 文件中所有的行业数据\n",
|
|
|
|
|
|
" industry_data = pd.read_hdf(h5_filename, key='sw_daily', columns=[\n",
|
|
|
|
|
|
" 'ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'pe', 'pb', 'vol'\n",
|
|
|
|
|
|
" ]) # 假设 H5 文件的键是 'industry_data'\n",
|
|
|
|
|
|
" industry_data = industry_data.sort_values(by=['ts_code', 'trade_date'])\n",
|
|
|
|
|
|
" industry_data = industry_data.reindex()\n",
|
|
|
|
|
|
" industry_data['trade_date'] = pd.to_datetime(industry_data['trade_date'], format='%Y%m%d')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" grouped = industry_data.groupby('ts_code', group_keys=False)\n",
|
|
|
|
|
|
" industry_data['obv'] = grouped.apply(\n",
|
|
|
|
|
|
" lambda x: pd.Series(talib.OBV(x['close'].values, x['vol'].values), index=x.index)\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" industry_data['return_5'] = grouped['close'].apply(lambda x: x / x.shift(5) - 1)\n",
|
|
|
|
|
|
" industry_data['return_20'] = grouped['close'].apply(lambda x: x / x.shift(20) - 1)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" industry_data = get_act_factor(industry_data, cat=False)\n",
|
|
|
|
|
|
" industry_data = industry_data.sort_values(by=['trade_date', 'ts_code'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # # 计算每天每个 ts_code 的因子和当天所有 ts_code 的中位数的偏差\n",
|
|
|
|
|
|
" # factor_columns = ['obv', 'return_5', 'return_20', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4'] # 因子列\n",
|
|
|
|
|
|
" # \n",
|
|
|
|
|
|
" # for factor in factor_columns:\n",
|
|
|
|
|
|
" # if factor in industry_data.columns:\n",
|
|
|
|
|
|
" # # 计算每天每个 ts_code 的因子值与当天所有 ts_code 的中位数的偏差\n",
|
|
|
|
|
|
" # industry_data[f'{factor}_deviation'] = industry_data.groupby('trade_date')[factor].transform(\n",
|
|
|
|
|
|
" # lambda x: x - x.mean())\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" industry_data['return_5_percentile'] = industry_data.groupby('trade_date')['return_5'].transform(\n",
|
|
|
|
|
|
" lambda x: x.rank(pct=True))\n",
|
|
|
|
|
|
" industry_data['return_20_percentile'] = industry_data.groupby('trade_date')['return_20'].transform(\n",
|
|
|
|
|
|
" lambda x: x.rank(pct=True))\n",
|
|
|
|
|
|
" industry_data = industry_data.drop(columns=['open', 'close', 'high', 'low', 'pe', 'pb', 'vol'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" industry_data = industry_data.rename(\n",
|
|
|
|
|
|
" columns={col: f'industry_{col}' for col in industry_data.columns if col not in ['ts_code', 'trade_date']})\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" industry_data = industry_data.rename(columns={'ts_code': 'cat_l2_code'})\n",
|
|
|
|
|
|
" return industry_data\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"industry_df = read_industry_data('../../data/sw_daily.h5')\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 6
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "dbe2fd8021b9417f",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:34:36.727797Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:34:36.724265Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"origin_columns = df.columns.tolist()\n",
|
|
|
|
|
|
"origin_columns = [col for col in origin_columns if\n",
|
|
|
|
|
|
" col not in ['turnover_rate', 'pe_ttm', 'volume_ratio', 'vol', 'pct_chg', 'l2_code', 'winner_rate']]\n",
|
|
|
|
|
|
"origin_columns = [col for col in origin_columns if col not in index_data.columns]\n",
|
|
|
|
|
|
"origin_columns = [col for col in origin_columns if 'cyq' not in col]\n",
|
|
|
|
|
|
"print(origin_columns)"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"['ts_code', 'open', 'close', 'high', 'low', 'circ_mv', 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol', 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol', 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct', 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'in_date']\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"execution_count": 7
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "85c3e3d0235ffffa",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:37:04.071963Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:34:36.756415Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"def filter_data(df):\n",
|
|
|
|
|
|
" # df = df.groupby('trade_date').apply(lambda x: x.nlargest(1000, 'act_factor1'))\n",
|
|
|
|
|
|
" df = df[~df['is_st']]\n",
|
|
|
|
|
|
" df = df[~df['ts_code'].str.endswith('BJ')]\n",
|
|
|
|
|
|
" df = df[~df['ts_code'].str.startswith('30')]\n",
|
|
|
|
|
|
" df = df[~df['ts_code'].str.startswith('68')]\n",
|
|
|
|
|
|
" df = df[~df['ts_code'].str.startswith('8')]\n",
|
|
|
|
|
|
" df = df[df['trade_date'] >= '20180101']\n",
|
|
|
|
|
|
" df = df.drop(columns=['in_date'])\n",
|
|
|
|
|
|
" df = df.reset_index(drop=True)\n",
|
|
|
|
|
|
" return df\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"df = filter_data(df)\n",
|
|
|
|
|
|
"# df = get_technical_factor(df)\n",
|
|
|
|
|
|
"# df = get_act_factor(df)\n",
|
|
|
|
|
|
"# df = get_money_flow_factor(df)\n",
|
|
|
|
|
|
"# df = get_alpha_factor(df)\n",
|
|
|
|
|
|
"# df = get_limit_factor(df)\n",
|
|
|
|
|
|
"# df = get_cyp_perf_factor(df)\n",
|
|
|
|
|
|
"# df = get_mv_factors(df)\n",
|
|
|
|
|
|
"df, _ = get_rolling_factor(df)\n",
|
|
|
|
|
|
"df, _ = get_simple_factor(df)\n",
|
|
|
|
|
|
"# df = df.merge(industry_df, on=['l2_code', 'trade_date'], how='left')\n",
|
|
|
|
|
|
"df = df.rename(columns={'l2_code': 'cat_l2_code'})\n",
|
|
|
|
|
|
"# df = df.merge(index_data, on='trade_date', how='left')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"print(df.info())"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"Index: 5118212 entries, 0 to 5118211\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Columns: 115 entries, ts_code to mv_momentum\n",
|
|
|
|
|
|
"dtypes: bool(12), datetime64[ns](1), float64(98), int32(1), int64(1), object(2)\n",
|
|
|
|
|
|
"memory usage: 4.0+ GB\n",
|
|
|
|
|
|
"None\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"execution_count": 8
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "92d84ce15a562ec6",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:37:05.401297Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:37:04.287413Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"from scipy.stats import ks_2samp, wasserstein_distance\n",
|
|
|
|
|
|
"from sklearn.metrics import roc_auc_score\n",
|
|
|
|
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
|
|
|
|
"from sklearn.preprocessing import StandardScaler\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def remove_shifted_features(train_data, test_data, feature_columns, ks_threshold=0.05, wasserstein_threshold=0.1,\n",
|
|
|
|
|
|
" importance_threshold=0.05):\n",
|
|
|
|
|
|
" dropped_features = []\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # **统计数据漂移**\n",
|
|
|
|
|
|
" numeric_columns = train_data.select_dtypes(include=['float64', 'int64']).columns\n",
|
|
|
|
|
|
" numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
|
|
|
|
|
|
" for feature in numeric_columns:\n",
|
|
|
|
|
|
" ks_stat, p_value = ks_2samp(train_data[feature], test_data[feature])\n",
|
|
|
|
|
|
" wasserstein_dist = wasserstein_distance(train_data[feature], test_data[feature])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" if p_value < ks_threshold and wasserstein_dist > wasserstein_threshold:\n",
|
|
|
|
|
|
" dropped_features.append(feature)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" print(f\"检测到 {len(dropped_features)} 个可能漂移的特征: {dropped_features}\")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # **应用阈值进行最终筛选**\n",
|
|
|
|
|
|
" filtered_features = [f for f in feature_columns if f not in dropped_features]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return filtered_features, dropped_features\n",
|
|
|
|
|
|
"\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 9
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "f4f16d63ad18d1bc",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"jupyter": {
|
|
|
|
|
|
"source_hidden": true
|
|
|
|
|
|
},
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:37:05.435586Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:37:05.429705Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"def create_deviation_within_dates(df, feature_columns):\n",
|
|
|
|
|
|
" groupby_col = 'cat_l2_code' # 使用 trade_date 进行分组\n",
|
|
|
|
|
|
" new_columns = {}\n",
|
|
|
|
|
|
" ret_feature_columns = feature_columns[:]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 自动选择所有数值型特征\n",
|
|
|
|
|
|
" num_features = [col for col in feature_columns if 'cat' not in col and 'index' not in col]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # num_features = ['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'cat_vol_spike', 'obv', 'maobv_6', 'return_5', 'return_10', 'return_20', 'std_return_5', 'std_return_15', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'act_factor5', 'act_factor6', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'alpha_022', 'alpha_003', 'alpha_007', 'alpha_013']\n",
|
|
|
|
|
|
" num_features = [col for col in num_features if 'cat' not in col and 'industry' not in col]\n",
|
|
|
|
|
|
" num_features = [col for col in num_features if 'limit' not in col]\n",
|
|
|
|
|
|
" num_features = [col for col in num_features if 'cyq' not in col]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 遍历所有数值型特征\n",
|
|
|
|
|
|
" for feature in num_features:\n",
|
|
|
|
|
|
" if feature == 'trade_date': # 不需要对 'trade_date' 计算偏差\n",
|
|
|
|
|
|
" continue\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # grouped_mean = df.groupby(['trade_date'])[feature].transform('mean')\n",
|
|
|
|
|
|
" # deviation_col_name = f'deviation_mean_{feature}'\n",
|
|
|
|
|
|
" # new_columns[deviation_col_name] = df[feature] - grouped_mean\n",
|
|
|
|
|
|
" # ret_feature_columns.append(deviation_col_name)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" grouped_mean = df.groupby(['trade_date', groupby_col])[feature].transform('mean')\n",
|
|
|
|
|
|
" deviation_col_name = f'deviation_mean_{feature}'\n",
|
|
|
|
|
|
" new_columns[deviation_col_name] = df[feature] - grouped_mean\n",
|
|
|
|
|
|
" ret_feature_columns.append(deviation_col_name)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 将新计算的偏差特征与原始 DataFrame 合并\n",
|
|
|
|
|
|
" df = pd.concat([df, pd.DataFrame(new_columns)], axis=1)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # for feature in ['obv', 'return_20', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4']:\n",
|
|
|
|
|
|
" # df[f'deviation_industry_{feature}'] = df[feature] - df[f'industry_{feature}']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return df, ret_feature_columns\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 10
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "40e6b68a91b30c79",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:37:05.994210Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:37:05.479565Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"import pandas as pd\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def remove_outliers_label_percentile(label: pd.Series, lower_percentile: float = 0.01, upper_percentile: float = 0.99,\n",
|
|
|
|
|
|
" log=True):\n",
|
|
|
|
|
|
" if not (0 <= lower_percentile < upper_percentile <= 1):\n",
|
|
|
|
|
|
" raise ValueError(\"Percentile values must satisfy 0 <= lower_percentile < upper_percentile <= 1.\")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # Calculate lower and upper bounds based on percentiles\n",
|
|
|
|
|
|
" lower_bound = label.quantile(lower_percentile)\n",
|
|
|
|
|
|
" upper_bound = label.quantile(upper_percentile)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # Filter out values outside the bounds\n",
|
|
|
|
|
|
" filtered_label = label[(label >= lower_bound) & (label <= upper_bound)]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # Print the number of removed outliers\n",
|
|
|
|
|
|
" if log:\n",
|
|
|
|
|
|
" print(f\"Removed {len(label) - len(filtered_label)} outliers.\")\n",
|
|
|
|
|
|
" return filtered_label\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def calculate_risk_adjusted_target(df, days=5):\n",
|
|
|
|
|
|
" df = df.sort_values(by=['ts_code', 'trade_date'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['future_close'] = df.groupby('ts_code')['close'].shift(-days)\n",
|
|
|
|
|
|
" df['future_open'] = df.groupby('ts_code')['open'].shift(-1)\n",
|
|
|
|
|
|
" df['future_return'] = (df['future_close'] - df['future_open']) / df['future_open']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df['future_volatility'] = df.groupby('ts_code')['future_return'].rolling(days, min_periods=1).std().reset_index(\n",
|
|
|
|
|
|
" level=0, drop=True)\n",
|
|
|
|
|
|
" sharpe_ratio = df['future_return'] * df['future_volatility']\n",
|
|
|
|
|
|
" sharpe_ratio.replace([np.inf, -np.inf], np.nan, inplace=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return sharpe_ratio\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def calculate_score(df, days=5, lambda_param=1.0):\n",
|
|
|
|
|
|
" def calculate_max_drawdown(prices):\n",
|
|
|
|
|
|
" peak = prices.iloc[0] # 初始化峰值\n",
|
|
|
|
|
|
" max_drawdown = 0 # 初始化最大回撤\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" for price in prices:\n",
|
|
|
|
|
|
" if price > peak:\n",
|
|
|
|
|
|
" peak = price # 更新峰值\n",
|
|
|
|
|
|
" else:\n",
|
|
|
|
|
|
" drawdown = (peak - price) / peak # 计算当前回撤\n",
|
|
|
|
|
|
" max_drawdown = max(max_drawdown, drawdown) # 更新最大回撤\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return max_drawdown\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def compute_stock_score(stock_df):\n",
|
|
|
|
|
|
" stock_df = stock_df.sort_values(by=['trade_date'])\n",
|
|
|
|
|
|
" future_return = stock_df['future_return']\n",
|
|
|
|
|
|
" volatility = stock_df['close'].pct_change().rolling(days).std().shift(-days)\n",
|
|
|
|
|
|
" max_drawdown = stock_df['close'].rolling(days).apply(calculate_max_drawdown, raw=False).shift(-days)\n",
|
|
|
|
|
|
" score = future_return - lambda_param * max_drawdown\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return score\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" scores = df.groupby('ts_code').apply(lambda x: compute_stock_score(x))\n",
|
|
|
|
|
|
" scores = scores.reset_index(level=0, drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return scores\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def remove_highly_correlated_features(df, feature_columns, threshold=0.9):\n",
|
|
|
|
|
|
" numeric_features = df[feature_columns].select_dtypes(include=[np.number]).columns.tolist()\n",
|
|
|
|
|
|
" if not numeric_features:\n",
|
|
|
|
|
|
" raise ValueError(\"No numeric features found in the provided data.\")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" corr_matrix = df[numeric_features].corr().abs()\n",
|
|
|
|
|
|
" upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))\n",
|
|
|
|
|
|
" to_drop = [column for column in upper.columns if any(upper[column] > threshold)]\n",
|
|
|
|
|
|
" remaining_features = [col for col in feature_columns if col not in to_drop\n",
|
|
|
|
|
|
" or 'act' in col or 'af' in col]\n",
|
|
|
|
|
|
" return remaining_features\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"import pandas as pd\n",
|
|
|
|
|
|
"from sklearn.preprocessing import StandardScaler\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def cross_sectional_standardization(df, features):\n",
|
|
|
|
|
|
" df_sorted = df.sort_values(by='trade_date') # 按时间排序\n",
|
|
|
|
|
|
" df_standardized = df_sorted.copy()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" for date in df_sorted['trade_date'].unique():\n",
|
|
|
|
|
|
" # 获取当前时间点的数据\n",
|
|
|
|
|
|
" current_data = df_standardized[df_standardized['trade_date'] == date]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 只对指定特征进行标准化\n",
|
|
|
|
|
|
" scaler = StandardScaler()\n",
|
|
|
|
|
|
" standardized_values = scaler.fit_transform(current_data[features])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 将标准化结果重新赋值回去\n",
|
|
|
|
|
|
" df_standardized.loc[df_standardized['trade_date'] == date, features] = standardized_values\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return df_standardized\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"import numpy as np\n",
|
|
|
|
|
|
"import pandas as pd\n",
|
|
|
|
|
|
"import statsmodels.api as sm\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def mad_filter(df, features, n=3):\n",
|
|
|
|
|
|
" \"\"\" 使用中位数绝对偏差（MAD）去极值 \"\"\"\n",
|
|
|
|
|
|
" df = df.copy()\n",
|
|
|
|
|
|
" for col in features:\n",
|
|
|
|
|
|
" median = df[col].median()\n",
|
|
|
|
|
|
" mad = np.median(np.abs(df[col] - median))\n",
|
|
|
|
|
|
" upper = median + n * mad\n",
|
|
|
|
|
|
" lower = median - n * mad\n",
|
|
|
|
|
|
" df[col] = np.clip(df[col], lower, upper) # 截断极值\n",
|
|
|
|
|
|
" return df\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"from concurrent.futures import ProcessPoolExecutor\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def neutralize_manual(df, features, industry_col, mkt_cap_col):\n",
|
|
|
|
|
|
" \"\"\" 手动实现简单回归以提升速度 \"\"\"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" for col in features:\n",
|
|
|
|
|
|
" residuals = []\n",
|
|
|
|
|
|
" for _, group in df.groupby(industry_col):\n",
|
|
|
|
|
|
" if len(group) > 1:\n",
|
|
|
|
|
|
" x = np.log(group[mkt_cap_col]) # 市值对数\n",
|
|
|
|
|
|
" y = group[col] # 因子值\n",
|
|
|
|
|
|
" beta = np.cov(y, x)[0, 1] / np.var(x) # 计算斜率\n",
|
|
|
|
|
|
" alpha = np.mean(y) - beta * np.mean(x) # 计算截距\n",
|
|
|
|
|
|
" resid = y - (alpha + beta * x) # 计算残差\n",
|
|
|
|
|
|
" residuals.extend(resid)\n",
|
|
|
|
|
|
" else:\n",
|
|
|
|
|
|
" residuals.extend(group[col]) # 样本不足时保留原值\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" df[col] = residuals\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return df\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"import gc\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"gc.collect()"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"data": {
|
|
|
|
|
|
"text/plain": [
|
|
|
|
|
|
"0"
|
|
|
|
|
|
]
|
|
|
|
|
|
},
|
|
|
|
|
|
"execution_count": 11,
|
|
|
|
|
|
"metadata": {},
|
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"execution_count": 11
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "1c46817a-b5dd-4bec-8bb4-e6e80bfd9d66",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:37:06.026489Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:37:06.024035Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": "# print(test_data.head()[['act_factor1', 'act_factor2', 'ts_code', 'trade_date']])",
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 12
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "da2bb202843d9275",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:37:06.597135Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:37:06.031495Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"from sklearn.preprocessing import StandardScaler\n",
|
|
|
|
|
|
"import lightgbm as lgb\n",
|
|
|
|
|
|
"import matplotlib.pyplot as plt\n",
|
|
|
|
|
|
"from sklearn.decomposition import PCA\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def train_light_model(train_data_df, params, feature_columns, callbacks, evals,\n",
|
|
|
|
|
|
" print_feature_importance=True, num_boost_round=100,\n",
|
|
|
|
|
|
" validation_days=180, use_pca=False, split_date=None): # 新增参数：validation_days\n",
|
|
|
|
|
|
" # 确保数据按时间排序\n",
|
|
|
|
|
|
" train_data_df = train_data_df.sort_values(by='trade_date')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" numeric_columns = train_data_df.select_dtypes(include=['float64', 'int64']).columns\n",
|
|
|
|
|
|
" numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
|
|
|
|
|
|
" # X_train.loc[:, numeric_columns] = scaler.fit_transform(X_train[numeric_columns])\n",
|
|
|
|
|
|
" # X_val.loc[:, numeric_columns] = scaler.transform(X_val[numeric_columns])\n",
|
|
|
|
|
|
" train_data_df = cross_sectional_standardization(train_data_df, numeric_columns)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 去除标签为空的样本\n",
|
|
|
|
|
|
" train_data_df = train_data_df.dropna(subset=['label'])\n",
|
|
|
|
|
|
" print('原始训练集大小: ', len(train_data_df))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 按时间顺序划分训练集和验证集\n",
|
|
|
|
|
|
" if split_date is None:\n",
|
|
|
|
|
|
" all_dates = train_data_df['trade_date'].unique() # 获取所有唯一的 trade_date\n",
|
|
|
|
|
|
" split_date = all_dates[-validation_days] # 划分点为倒数第 validation_days 天\n",
|
|
|
|
|
|
" train_data_split = train_data_df[train_data_df['trade_date'] < split_date] # 训练集\n",
|
|
|
|
|
|
" val_data_split = train_data_df[train_data_df['trade_date'] >= split_date] # 验证集\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 打印划分结果\n",
|
|
|
|
|
|
" print(f\"划分后的训练集大小: {len(train_data_split)}, 验证集大小: {len(val_data_split)}\")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 提取特征和标签\n",
|
|
|
|
|
|
" X_train = train_data_split[feature_columns]\n",
|
|
|
|
|
|
" y_train = train_data_split['label']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" X_val = val_data_split[feature_columns]\n",
|
|
|
|
|
|
" y_val = val_data_split['label']\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 标准化数值特征\n",
|
|
|
|
|
|
" scaler = StandardScaler()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算每个 trade_date 内的样本数（LTR 需要 group 信息）\n",
|
|
|
|
|
|
" train_groups = train_data_split.groupby('trade_date').size().tolist()\n",
|
|
|
|
|
|
" val_groups = val_data_split.groupby('trade_date').size().tolist()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 处理类别特征\n",
|
|
|
|
|
|
" categorical_feature = [col for col in feature_columns if 'cat' in col]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" pca = None\n",
|
|
|
|
|
|
" if use_pca:\n",
|
|
|
|
|
|
" pca = PCA(n_components=0.95) # 或指定 n_components=固定值（如 10）\n",
|
|
|
|
|
|
" numeric_features = [col for col in feature_columns if col not in categorical_feature]\n",
|
|
|
|
|
|
" numeric_pca = pca.fit_transform(X_train[numeric_features])\n",
|
|
|
|
|
|
" X_train = pd.concat([pd.DataFrame(numeric_pca, index=X_train.index), X_train[categorical_feature]], axis=1)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" numeric_pca = pca.transform(X_val[numeric_features])\n",
|
|
|
|
|
|
" X_val = pd.concat([pd.DataFrame(numeric_pca, index=X_val.index), X_val[categorical_feature]], axis=1)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 计算权重（基于时间）\n",
|
|
|
|
|
|
" # trade_date = train_data_split['trade_date'] # 交易日期\n",
|
|
|
|
|
|
" # weights = (trade_date - trade_date.min()).dt.days / (trade_date.max() - trade_date.min()).days + 1\n",
|
|
|
|
|
|
" # weights = train_data_split.groupby('trade_date')['std_return_5'].transform(\n",
|
|
|
|
|
|
" # lambda x: x / x.mean()\n",
|
|
|
|
|
|
" # )\n",
|
|
|
|
|
|
" ud = sorted(train_data_split[\"trade_date\"].unique().tolist())\n",
|
|
|
|
|
|
" date_weights = {date: weight * weight for date, weight in zip(ud, np.linspace(1, 10, len(ud)))}\n",
|
|
|
|
|
|
" params['weight'] = train_data_split[\"trade_date\"].map(date_weights).tolist()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" train_dataset = lgb.Dataset(\n",
|
|
|
|
|
|
" X_train, label=y_train, group=train_groups,\n",
|
|
|
|
|
|
" categorical_feature=categorical_feature\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # weights = val_data_split.groupby('trade_date')['std_return_5'].transform(\n",
|
|
|
|
|
|
" # lambda x: x / x.mean()\n",
|
|
|
|
|
|
" # )\n",
|
|
|
|
|
|
" val_dataset = lgb.Dataset(\n",
|
|
|
|
|
|
" X_val, label=y_val, group=val_groups,\n",
|
|
|
|
|
|
" categorical_feature=categorical_feature\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 训练模型\n",
|
|
|
|
|
|
" model = lgb.train(\n",
|
|
|
|
|
|
" params, train_dataset, num_boost_round=num_boost_round,\n",
|
|
|
|
|
|
" valid_sets=[train_dataset, val_dataset], valid_names=['train', 'valid'],\n",
|
|
|
|
|
|
" callbacks=callbacks\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 打印特征重要性（如果需要）\n",
|
|
|
|
|
|
" if print_feature_importance:\n",
|
|
|
|
|
|
" lgb.plot_metric(evals)\n",
|
|
|
|
|
|
" lgb.plot_importance(model, importance_type='split', max_num_features=20)\n",
|
|
|
|
|
|
" plt.show()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" return model, scaler, pca"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 13
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
|
|
|
|
|
"end_time": "2025-03-31T14:37:11.087120Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:37:06.619979Z"
|
|
|
|
|
|
}
|
|
|
|
|
|
},
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"cell_type": "code",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"days = 2\n",
|
|
|
|
|
|
"df['future_return'] = (df.groupby('ts_code')['close'].shift(-days) - df.groupby('ts_code')['open'].shift(-1)) / \\\n",
|
|
|
|
|
|
" df.groupby('ts_code')['open'].shift(-1)\n",
|
|
|
|
|
|
"df['future_volatility'] = (\n",
|
|
|
|
|
|
" df.groupby('ts_code')['future_return']\n",
|
|
|
|
|
|
" .transform(lambda x: x.rolling(days).std())\n",
|
|
|
|
|
|
")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"df['future_score'] = (\n",
|
|
|
|
|
|
" 0.7 * df['future_return'] +\n",
|
|
|
|
|
|
" 0.3 * df['future_volatility']\n",
|
|
|
|
|
|
")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"filter_index = df['future_return'].between(df['future_return'].quantile(0.01), df['future_return'].quantile(0.99))\n",
|
|
|
|
|
|
"filter_index = df['future_volatility'].between(df['future_volatility'].quantile(0.01),\n",
|
|
|
|
|
|
" df['future_volatility'].quantile(0.99)) | filter_index\n",
|
|
|
|
|
|
"filter_index2 = df['future_return'].between(df['future_return'].quantile(0.01), df['future_return'].quantile(0.99))\n",
|
|
|
|
|
|
"filter_index2 = df['future_volatility'].between(df['future_volatility'].quantile(0.01),\n",
|
|
|
|
|
|
" df['future_volatility'].quantile(0.99)) | filter_index2\n",
|
|
|
|
|
|
"df['label'] = df.groupby('trade_date', group_keys=False)['future_score'].transform(\n",
|
|
|
|
|
|
" lambda x: pd.qcut(x, q=50, labels=False, duplicates='drop')\n",
|
|
|
|
|
|
")\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"id": "81d4570663ae21d7",
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": 14
|
|
|
|
|
|
},
|
|
|
|
|
|
{
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:39:16.314466Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:39:15.609756Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"cell_type": "code",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"source": [
|
|
|
|
|
|
"# print('train data size: ', len(train_data))\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"# label_gain = list(range(len(train_data['label'].unique())))\n",
|
|
|
|
|
|
"# label_gain = [gain * gain for gain in label_gain]\n",
|
|
|
|
|
|
"light_params = {\n",
|
|
|
|
|
|
" 'objective': 'lambdarank',\n",
|
|
|
|
|
|
" 'metric': 'lambdarank',\n",
|
|
|
|
|
|
" 'learning_rate': 0.1,\n",
|
|
|
|
|
|
" 'num_leaves': 1024,\n",
|
|
|
|
|
|
" 'min_data_in_leaf': 128,\n",
|
|
|
|
|
|
" 'max_depth': 16,\n",
|
|
|
|
|
|
" 'max_bin': 1024,\n",
|
|
|
|
|
|
" 'feature_fraction': 0.7,\n",
|
|
|
|
|
|
" 'bagging_fraction': 1,\n",
|
|
|
|
|
|
" 'bagging_freq': 5,\n",
|
|
|
|
|
|
" 'lambda_l1': 1,\n",
|
|
|
|
|
|
" 'lambda_l2': 1,\n",
|
|
|
|
|
|
" # 'boosting': 'dart',\n",
|
|
|
|
|
|
" 'verbosity': -1,\n",
|
|
|
|
|
|
" 'extra_trees': True,\n",
|
|
|
|
|
|
" 'max_position': 5,\n",
|
|
|
|
|
|
" 'ndcg_at': 1,\n",
|
|
|
|
|
|
" 'seed': 7\n",
|
|
|
|
|
|
"}\n",
|
|
|
|
|
|
"evals = {}\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"gc.collect()"
|
|
|
|
|
|
],
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"id": "92428d543f4727ad",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"data": {
|
|
|
|
|
|
"text/plain": [
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"6302"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
]
|
|
|
|
|
|
},
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"execution_count": 21,
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"metadata": {},
|
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"execution_count": 21
|
2025-03-30 01:55:21 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "8f134d435f71e9e2",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"jupyter": {
|
|
|
|
|
|
"source_hidden": true
|
|
|
|
|
|
},
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:39:16.430821Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:39:16.321471Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"gc.collect()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"def rolling_train_predict(df, train_days, test_days, industry_df, index_df, days=5, use_pca=False, validation_days=60, filter_index=None):\n",
|
|
|
|
|
|
" # 1. 按照交易日期排序\n",
|
|
|
|
|
|
" unique_dates = df[df['trade_date'] >= '2020-01-01']['trade_date'].unique().tolist()\n",
|
|
|
|
|
|
" unique_dates = sorted(unique_dates)\n",
|
|
|
|
|
|
" n = len(unique_dates)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 2. 计算需要跳过的天数，使后续窗口对齐\n",
|
|
|
|
|
|
" extra_days = (n - train_days) % test_days\n",
|
|
|
|
|
|
" start_index = extra_days # 从此索引开始滚动\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" predictions_list = []\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" for start in range(start_index, n - train_days - test_days + 1, test_days):\n",
|
|
|
|
|
|
" gc.collect()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" train_dates = unique_dates[start: start + train_days]\n",
|
|
|
|
|
|
" test_dates = unique_dates[start + train_days: start + train_days + test_days]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # 根据日期筛选数据\n",
|
|
|
|
|
|
" train_data = df[filter_index & df['trade_date'].isin(train_dates)]\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
" test_data = df[filter_index2 & df['trade_date'].isin(test_dates)]\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"\n",
|
|
|
|
|
|
" train_data = train_data.sort_values('trade_date')\n",
|
|
|
|
|
|
" test_data = test_data.sort_values('trade_date')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" def select_pre_zt_stocks_dynamic(\n",
|
|
|
|
|
|
" stock_df,\n",
|
|
|
|
|
|
" ):\n",
|
|
|
|
|
|
" stock_df = stock_df.groupby('trade_date', group_keys=False).apply(\n",
|
|
|
|
|
|
" lambda x: x.nlargest(1000, 'return_20')\n",
|
|
|
|
|
|
" )\n",
|
|
|
|
|
|
" return stock_df\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" train_data = select_pre_zt_stocks_dynamic(train_data)\n",
|
|
|
|
|
|
" test_data = select_pre_zt_stocks_dynamic(test_data)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" industry_df = industry_df.sort_values(by=['trade_date'])\n",
|
|
|
|
|
|
" # index_df = index_df.sort_values(by=['trade_date'])\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" train_data = train_data.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n",
|
|
|
|
|
|
" # train_data = train_data.merge(index_df, on='trade_date', how='left')\n",
|
|
|
|
|
|
" test_data = test_data.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n",
|
|
|
|
|
|
" # test_data = test_data.merge(index_df, on='trade_date', how='left')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" train_data, test_data = train_data.replace([np.inf, -np.inf], np.nan), test_data.replace([np.inf, -np.inf],\n",
|
|
|
|
|
|
" np.nan)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" feature_columns = [col for col in train_data.columns if col in train_data.columns]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if col not in ['trade_date',\n",
|
|
|
|
|
|
" 'ts_code',\n",
|
|
|
|
|
|
" 'label']]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if 'future' not in col]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if 'label' not in col]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if 'score' not in col]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if 'gen' not in col]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if 'cat_l2_code' not in col]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if col not in origin_columns]\n",
|
|
|
|
|
|
" feature_columns = [col for col in feature_columns if not col.startswith('_')]\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" numeric_columns = train_data.select_dtypes(include=['float64', 'int64']).columns\n",
|
|
|
|
|
|
" numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
|
|
|
|
|
|
" print('去极值')\n",
|
|
|
|
|
|
" train_data = mad_filter(train_data, numeric_columns) # 去极值\n",
|
|
|
|
|
|
" # print('中性化')\n",
|
|
|
|
|
|
" # train_data = neutralize_manual(train_data, numeric_columns, industry_col='cat_l2_code', mkt_cap_col='log(circ_mv)') # 中性化\n",
|
|
|
|
|
|
" print('去极值')\n",
|
|
|
|
|
|
" test_data = mad_filter(test_data, numeric_columns) # 去极值\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" all_dates = train_data['trade_date'].unique() # 获取所有唯一的 trade_date\n",
|
|
|
|
|
|
" split_date = all_dates[-validation_days] # 划分点为倒数第 validation_days 天\n",
|
|
|
|
|
|
" train_data_split = train_data[train_data['trade_date'] < split_date] # 训练集\n",
|
|
|
|
|
|
" val_data_split = train_data[train_data['trade_date'] >= split_date] # 验证集\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" feature_columns, _ = remove_shifted_features(train_data_split[train_data_split['label'] == train_data_split['label'].max()],\n",
|
|
|
|
|
|
" val_data_split[val_data_split['label'] == val_data_split['label'].max()],\n",
|
|
|
|
|
|
" feature_columns)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" feature_columns = remove_highly_correlated_features(train_data[train_data['label'] == train_data['label'].max()],\n",
|
|
|
|
|
|
" feature_columns)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" train_data = train_data.dropna(subset=feature_columns)\n",
|
|
|
|
|
|
" train_data = train_data.dropna(subset=['label'])\n",
|
|
|
|
|
|
" train_data = train_data.reset_index(drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # print(test_data.tail())\n",
|
|
|
|
|
|
" test_data = test_data.dropna(subset=feature_columns)\n",
|
|
|
|
|
|
" # test_data = test_data.dropna(subset=['label'])\n",
|
|
|
|
|
|
" test_data = test_data.reset_index(drop=True)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # print(len(train_data))\n",
|
|
|
|
|
|
" print(f\"最小日期: {train_data['trade_date'].min().strftime('%Y-%m-%d')}\")\n",
|
|
|
|
|
|
" print(f\"最大日期: {train_data['trade_date'].max().strftime('%Y-%m-%d')}\")\n",
|
|
|
|
|
|
" # print(len(test_data))\n",
|
|
|
|
|
|
" print(f\"最小日期: {test_data['trade_date'].min().strftime('%Y-%m-%d')}\")\n",
|
|
|
|
|
|
" print(f\"最大日期: {test_data['trade_date'].max().strftime('%Y-%m-%d')}\")\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" cat_columns = [col for col in df.columns if col.startswith('cat')]\n",
|
|
|
|
|
|
" for col in cat_columns:\n",
|
|
|
|
|
|
" train_data[col] = train_data[col].astype('category')\n",
|
|
|
|
|
|
" test_data[col] = test_data[col].astype('category')\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" label_gain = list(range(len(train_data['label'].unique())))\n",
|
|
|
|
|
|
" label_gain = [gain * gain for gain in label_gain]\n",
|
|
|
|
|
|
" light_params['label_gain'] = label_gain\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # ud = train_data[\"trade_date\"].unique()\n",
|
|
|
|
|
|
" # date_weights = {date: weight for date, weight in zip(ud, np.linspace(1, 2, len(unique_dates)))}\n",
|
|
|
|
|
|
" # light_params['weight'] = train_data[\"trade_date\"].map(date_weights).tolist()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # print(f'feature_columns: {feature_columns}')\n",
|
|
|
|
|
|
" feature_contri = [2 if feat.startswith('act_factor') else 1 for feat in feature_columns]\n",
|
|
|
|
|
|
" light_params['feature_contri'] = feature_contri\n",
|
|
|
|
|
|
" model, _, _ = train_light_model(train_data.dropna(subset=['label']),\n",
|
|
|
|
|
|
" light_params, feature_columns,\n",
|
|
|
|
|
|
" [lgb.log_evaluation(period=100),\n",
|
|
|
|
|
|
" lgb.callback.record_evaluation(evals),\n",
|
|
|
|
|
|
" lgb.early_stopping(50, first_metric_only=True)\n",
|
|
|
|
|
|
" ], evals,\n",
|
|
|
|
|
|
" num_boost_round=3000, validation_days=validation_days,\n",
|
|
|
|
|
|
" print_feature_importance=False, use_pca=False)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" score_df = test_data.copy()\n",
|
|
|
|
|
|
" numeric_columns = score_df.select_dtypes(include=['float64', 'int64']).columns\n",
|
|
|
|
|
|
" numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
|
|
|
|
|
|
" score_df = cross_sectional_standardization(score_df, numeric_columns)\n",
|
|
|
|
|
|
" score_df['score'] = model.predict(score_df[feature_columns])\n",
|
|
|
|
|
|
" score_df = score_df.loc[score_df.groupby('trade_date')['score'].idxmax()]\n",
|
|
|
|
|
|
" score_df = score_df[['trade_date', 'score', 'ts_code']]\n",
|
|
|
|
|
|
" predictions_list.append(score_df)\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" # m = 5\n",
|
|
|
|
|
|
" # all_data = []\n",
|
|
|
|
|
|
" # for i, trade_date in enumerate(sorted(score_df['trade_date'].unique().tolist())):\n",
|
|
|
|
|
|
" # # 提取当前日期的数据\n",
|
|
|
|
|
|
" # current_data = score_df[score_df['trade_date'] == trade_date]\n",
|
|
|
|
|
|
" # all_data.append(current_data)\n",
|
|
|
|
|
|
" #\n",
|
|
|
|
|
|
" # numeric_columns = [col for col in feature_columns if col in current_data.select_dtypes(include=['float64', 'int64']).columns]\n",
|
|
|
|
|
|
" # current_data = cross_sectional_standardization(current_data, numeric_columns)\n",
|
|
|
|
|
|
" # current_data['score'] = model.predict(current_data[feature_columns])\n",
|
|
|
|
|
|
" # daily_top_score = current_data.loc[[current_data['score'].idxmax()]]\n",
|
|
|
|
|
|
" # predictions_list.append(daily_top_score[['trade_date', 'score', 'ts_code']])\n",
|
|
|
|
|
|
" #\n",
|
|
|
|
|
|
" # if i % m == 0:\n",
|
|
|
|
|
|
" # train_data_split = pd.concat(all_data)\n",
|
|
|
|
|
|
" # train_data_split = train_data_split.dropna(subset=['label'])\n",
|
|
|
|
|
|
" #\n",
|
|
|
|
|
|
" # X_train = train_data_split[feature_columns]\n",
|
|
|
|
|
|
" # y_train = train_data_split['label']\n",
|
|
|
|
|
|
" #\n",
|
|
|
|
|
|
" # train_groups = train_data_split.groupby('trade_date').size().tolist()\n",
|
|
|
|
|
|
" # categorical_feature = [col for col in feature_columns if 'cat' in col]\n",
|
|
|
|
|
|
" #\n",
|
|
|
|
|
|
" # train_dataset = lgb.Dataset(\n",
|
|
|
|
|
|
" # X_train, label=y_train, group=train_groups,\n",
|
|
|
|
|
|
" # categorical_feature=categorical_feature\n",
|
|
|
|
|
|
" # )\n",
|
|
|
|
|
|
" #\n",
|
|
|
|
|
|
" # model = lgb.train(\n",
|
|
|
|
|
|
" # light_params, train_dataset, num_boost_round=36,\n",
|
|
|
|
|
|
" # init_model=model\n",
|
|
|
|
|
|
" # )\n",
|
|
|
|
|
|
" # all_data = []\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
" final_predictions = pd.concat(predictions_list, ignore_index=True)\n",
|
|
|
|
|
|
" return final_predictions\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [],
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"execution_count": 22
|
2025-03-30 01:55:21 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"id": "63235069-dc59-48fb-961a-e80373e41a61",
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:45:27.262907Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:39:16.454548Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"source": [
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"gc.collect()\n",
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
"final_predictions = rolling_train_predict(df.sort_values(['trade_date'], ascending=[True]), 500, 60, industry_df, None,\n",
|
|
|
|
|
|
" days=days, validation_days=120, filter_index=filter_index)\n",
|
|
|
|
|
|
"final_predictions.to_csv('predictions_test.tsv', index=False)\n"
|
|
|
|
|
|
],
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 21 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'act_factor3', 'log(circ_mv)', 'cov', 'delta_cov', 'alpha_22_improved', 'turnover_std', 'log_close', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2020-03-18\n",
|
|
|
|
|
|
"最大日期: 2022-04-08\n",
|
|
|
|
|
|
"最小日期: 2022-04-11\n",
|
|
|
|
|
|
"最大日期: 2022-07-07\n",
|
|
|
|
|
|
"原始训练集大小: 402509\n",
|
|
|
|
|
|
"划分后的训练集大小: 307874, 验证集大小: 94635\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[1]\ttrain's ndcg@1: 0.519951\tvalid's ndcg@1: 0.628242\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"检测到 26 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'return_kurtosis', 'vol_spike', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'act_factor3', 'log(circ_mv)', 'cov', 'delta_cov', 'alpha_22_improved', 'turnover_std', 'resonance_factor', 'log_close', 'obv-maobv_6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"最小日期: 2020-06-16\n",
|
|
|
|
|
|
"最大日期: 2022-07-07\n",
|
|
|
|
|
|
"最小日期: 2022-07-08\n",
|
|
|
|
|
|
"最大日期: 2022-09-30\n",
|
|
|
|
|
|
"原始训练集大小: 401052\n",
|
|
|
|
|
|
"划分后的训练集大小: 306109, 验证集大小: 94943\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[19]\ttrain's ndcg@1: 0.656354\tvalid's ndcg@1: 0.628231\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 14 个可能漂移的特征: ['vol', 'turnover_rate', 'vol_spike', 'atr_14', 'atr_6', 'log(circ_mv)', 'alpha_22_improved', 'turnover_std', 'log_close', 'obv-maobv_6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_elg_vol_minus_sell_elg_vol']\n",
|
|
|
|
|
|
"最小日期: 2020-09-10\n",
|
|
|
|
|
|
"最大日期: 2022-09-30\n",
|
|
|
|
|
|
"最小日期: 2022-10-10\n",
|
|
|
|
|
|
"最大日期: 2022-12-30\n",
|
|
|
|
|
|
"原始训练集大小: 398374\n",
|
|
|
|
|
|
"划分后的训练集大小: 303799, 验证集大小: 94575\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[8]\ttrain's ndcg@1: 0.624175\tvalid's ndcg@1: 0.60186\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 17 个可能漂移的特征: ['vol', 'turnover_rate', 'return_kurtosis', 'vol_spike', 'atr_14', 'atr_6', 'act_factor3', 'log(circ_mv)', 'turnover_std', 'log_close', 'obv-maobv_6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_elg_vol_minus_sell_elg_vol', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2020-12-11\n",
|
|
|
|
|
|
"最大日期: 2022-12-30\n",
|
|
|
|
|
|
"最小日期: 2023-01-03\n",
|
|
|
|
|
|
"最大日期: 2023-04-03\n",
|
|
|
|
|
|
"原始训练集大小: 395305\n",
|
|
|
|
|
|
"划分后的训练集大小: 305409, 验证集大小: 89896\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[23]\ttrain's ndcg@1: 0.711527\tvalid's ndcg@1: 0.58914\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 18 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'return_kurtosis', 'vol_spike', 'obv', 'maobv_6', 'rsi_3', 'act_factor3', 'delta_cov', 'resonance_factor', 'obv-maobv_6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_elg_vol_minus_sell_elg_vol', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2021-03-15\n",
|
|
|
|
|
|
"最大日期: 2023-04-03\n",
|
|
|
|
|
|
"最小日期: 2023-04-04\n",
|
|
|
|
|
|
"最大日期: 2023-07-04\n",
|
|
|
|
|
|
"原始训练集大小: 394279\n",
|
|
|
|
|
|
"划分后的训练集大小: 303561, 验证集大小: 90718\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[1]\ttrain's ndcg@1: 0.570726\tvalid's ndcg@1: 0.62316\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 25 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'return_skew', 'return_kurtosis', 'vol_spike', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'act_factor2', 'act_factor3', 'log(circ_mv)', 'delta_cov', 'alpha_22_improved', 'turnover_std', 'resonance_factor', 'log_close', 'obv-maobv_6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2021-06-11\n",
|
|
|
|
|
|
"最大日期: 2023-07-04\n",
|
|
|
|
|
|
"最小日期: 2023-07-05\n",
|
|
|
|
|
|
"最大日期: 2023-09-26\n",
|
|
|
|
|
|
"原始训练集大小: 392902\n",
|
|
|
|
|
|
"划分后的训练集大小: 300091, 验证集大小: 92811\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[4]\ttrain's ndcg@1: 0.623501\tvalid's ndcg@1: 0.608889\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 11 个可能漂移的特征: ['pct_chg', 'return_skew', 'return_kurtosis', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'act_factor3', 'delta_cov', 'alpha_22_improved', 'resonance_factor']\n",
|
|
|
|
|
|
"最小日期: 2021-09-06\n",
|
|
|
|
|
|
"最大日期: 2023-09-26\n",
|
|
|
|
|
|
"最小日期: 2023-09-27\n",
|
|
|
|
|
|
"最大日期: 2023-12-27\n",
|
|
|
|
|
|
"原始训练集大小: 386164\n",
|
|
|
|
|
|
"划分后的训练集大小: 296301, 验证集大小: 89863\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[38]\ttrain's ndcg@1: 0.76403\tvalid's ndcg@1: 0.675597\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 14 个可能漂移的特征: ['pct_chg', 'turnover_rate', 'vol_spike', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'act_factor3', 'log(circ_mv)', 'cov', 'delta_cov', 'alpha_22_improved', 'turnover_std', 'log_close']\n",
|
|
|
|
|
|
"最小日期: 2021-12-08\n",
|
|
|
|
|
|
"最大日期: 2023-12-27\n",
|
|
|
|
|
|
"最小日期: 2023-12-28\n",
|
|
|
|
|
|
"最大日期: 2024-03-29\n",
|
|
|
|
|
|
"原始训练集大小: 379125\n",
|
|
|
|
|
|
"划分后的训练集大小: 293170, 验证集大小: 85955\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[17]\ttrain's ndcg@1: 0.707121\tvalid's ndcg@1: 0.6345\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 13 个可能漂移的特征: ['vol', 'turnover_rate', 'vol_spike', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'log(circ_mv)', 'turnover_std', 'log_close', 'obv-maobv_6', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2022-03-10\n",
|
|
|
|
|
|
"最大日期: 2024-03-29\n",
|
|
|
|
|
|
"最小日期: 2024-04-01\n",
|
|
|
|
|
|
"最大日期: 2024-07-01\n",
|
|
|
|
|
|
"原始训练集大小: 379627\n",
|
|
|
|
|
|
"划分后的训练集大小: 290158, 验证集大小: 89469\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[44]\ttrain's ndcg@1: 0.776797\tvalid's ndcg@1: 0.610802\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 18 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'return_kurtosis', 'vol_spike', 'atr_6', 'maobv_6', 'rsi_3', 'act_factor3', 'cov', 'delta_cov', 'alpha_22_improved', 'turnover_std', 'resonance_factor', 'log_close', 'obv-maobv_6', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2022-06-10\n",
|
|
|
|
|
|
"最大日期: 2024-07-01\n",
|
|
|
|
|
|
"最小日期: 2024-07-02\n",
|
|
|
|
|
|
"最大日期: 2024-09-25\n",
|
|
|
|
|
|
"原始训练集大小: 381403\n",
|
|
|
|
|
|
"划分后的训练集大小: 284687, 验证集大小: 96716\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[49]\ttrain's ndcg@1: 0.787077\tvalid's ndcg@1: 0.579916\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 20 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'vol_spike', 'atr_14', 'atr_6', 'obv', 'maobv_6', 'rsi_3', 'act_factor3', 'log(circ_mv)', 'cov', 'delta_cov', 'alpha_22_improved', 'turnover_std', 'resonance_factor', 'log_close', 'obv-maobv_6', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2022-09-02\n",
|
|
|
|
|
|
"最大日期: 2024-09-25\n",
|
|
|
|
|
|
"最小日期: 2024-09-26\n",
|
|
|
|
|
|
"最大日期: 2024-12-25\n",
|
|
|
|
|
|
"原始训练集大小: 378304\n",
|
|
|
|
|
|
"划分后的训练集大小: 284976, 验证集大小: 93328\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[100]\ttrain's ndcg@1: 0.840198\tvalid's ndcg@1: 0.629064\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[98]\ttrain's ndcg@1: 0.836808\tvalid's ndcg@1: 0.644301\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n",
|
|
|
|
|
|
"去极值\n",
|
|
|
|
|
|
"去极值\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"检测到 17 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'return_skew', 'obv', 'maobv_6', 'rsi_3', 'act_factor1', 'log(circ_mv)', 'cov', 'delta_cov', 'alpha_22_improved', 'resonance_factor', 'log_close', 'obv-maobv_6', 'mv_adjusted_volume', 'nonlinear_mv_volume']\n",
|
|
|
|
|
|
"最小日期: 2022-12-05\n",
|
|
|
|
|
|
"最大日期: 2024-12-25\n",
|
|
|
|
|
|
"最小日期: 2024-12-26\n",
|
|
|
|
|
|
"最大日期: 2025-03-26\n",
|
|
|
|
|
|
"原始训练集大小: 371843\n",
|
|
|
|
|
|
"划分后的训练集大小: 289769, 验证集大小: 82074\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Training until validation scores don't improve for 50 rounds\n",
|
|
|
|
|
|
"Early stopping, best iteration is:\n",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"[2]\ttrain's ndcg@1: 0.592644\tvalid's ndcg@1: 0.596307\n",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"Evaluated only: ndcg@1\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"execution_count": 23
|
2025-03-30 01:55:21 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"ExecuteTime": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"end_time": "2025-03-31T14:45:27.345941Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:45:27.342565Z"
|
2025-03-30 01:55:21 +08:00
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
|
"source": "print('finish')",
|
|
|
|
|
|
"id": "10f15e935aa02a34",
|
|
|
|
|
|
"outputs": [
|
|
|
|
|
|
{
|
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
|
"text": [
|
|
|
|
|
|
"finish\n"
|
|
|
|
|
|
]
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"execution_count": 24
|
2025-03-30 01:55:21 +08:00
|
|
|
|
},
|
|
|
|
|
|
{
|
|
|
|
|
|
"cell_type": "code",
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"id": "0dc75517-c857-4f1d-8815-e807400a6d33",
|
2025-03-30 01:55:21 +08:00
|
|
|
|
"metadata": {
|
2025-03-31 23:08:03 +08:00
|
|
|
|
"ExecuteTime": {
|
|
|
|
|
|
"end_time": "2025-03-31T14:45:27.395705Z",
|
|
|
|
|
|
"start_time": "2025-03-31T14:45:27.393319Z"
|
|
|
|
|
|
}
|
2025-03-30 01:55:21 +08:00
|
|
|
|
},
|
|
|
|
|
|
"source": [],
|
|
|
|
|
|
"outputs": [],
|
|
|
|
|
|
"execution_count": null
|
|
|
|
|
|
}
|
|
|
|
|
|
],
|
|
|
|
|
|
"metadata": {
|
|
|
|
|
|
"kernelspec": {
|
|
|
|
|
|
"display_name": "Python 3 (ipykernel)",
|
|
|
|
|
|
"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": "3.11.11"
|
|
|
|
|
|
}
|
|
|
|
|
|
},
|
|
|
|
|
|
"nbformat": 4,
|
|
|
|
|
|
"nbformat_minor": 5
|
|
|
|
|
|
}
|
