3889 lines
182 KiB
Plaintext
3889 lines
182 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"id": "79a7758178bafdd3",
|
||
"metadata": {
|
||
"jupyter": {
|
||
"source_hidden": true
|
||
},
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:35:12.553694Z",
|
||
"start_time": "2025-04-04T15:35:12.549140Z"
|
||
}
|
||
},
|
||
"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": 30
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "a79cafb06a7e0e43",
|
||
"metadata": {
|
||
"scrolled": true,
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:36:03.894111Z",
|
||
"start_time": "2025-04-04T15:35:12.573328Z"
|
||
}
|
||
},
|
||
"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",
|
||
"inner merge on ['ts_code', 'trade_date']\n",
|
||
"stk limit\n",
|
||
"left merge on ['ts_code', 'trade_date']\n",
|
||
"money flow\n",
|
||
"left merge on ['ts_code', 'trade_date']\n",
|
||
"cyq perf\n",
|
||
"left merge on ['ts_code', 'trade_date']\n",
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"RangeIndex: 8477357 entries, 0 to 8477356\n",
|
||
"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": 31
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "cac01788dac10678",
|
||
"metadata": {
|
||
"jupyter": {
|
||
"source_hidden": true
|
||
},
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:36:18.904551Z",
|
||
"start_time": "2025-04-04T15:36:04.059865Z"
|
||
}
|
||
},
|
||
"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": 32
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "c4e9e1d31da6dba6",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:36:19.231919Z",
|
||
"start_time": "2025-04-04T15:36:19.058570Z"
|
||
}
|
||
},
|
||
"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": 33
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "a735bc02ceb4d872",
|
||
"metadata": {
|
||
"jupyter": {
|
||
"source_hidden": true
|
||
},
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:36:19.280300Z",
|
||
"start_time": "2025-04-04T15:36:19.231919Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"import talib\n",
|
||
"\n",
|
||
"\n",
|
||
"def get_rolling_factor(df):\n",
|
||
" old_columns = df.columns.tolist()[:]\n",
|
||
"\n",
|
||
" # 按股票和日期排序（如果尚未排序）\n",
|
||
" df = df.sort_values(by=['ts_code', 'trade_date'])\n",
|
||
"\n",
|
||
" grouped = df.groupby('ts_code', group_keys=False)\n",
|
||
"\n",
|
||
" # 提前计算布尔掩码\n",
|
||
" window = 5\n",
|
||
" return_threshold = 0.0\n",
|
||
"\n",
|
||
" df['_is_upside'] = df['pct_chg'] > return_threshold\n",
|
||
" df['_is_downside'] = df['pct_chg'] < -return_threshold\n",
|
||
"\n",
|
||
" # # 1. 上行波动率 (20日)\n",
|
||
" # def rolling_upside_volatility(series, _is_upside, window):\n",
|
||
" # # 提取正收益\n",
|
||
" # positive_returns = series.where(_is_upside, np.nan)\n",
|
||
" # # 计算滚动窗口标准差\n",
|
||
" # return positive_returns.rolling(window=window, min_periods=2).std()\n",
|
||
" #\n",
|
||
" # df[f'upside_volatility_{window}'] = grouped.apply(\n",
|
||
" # lambda x: rolling_upside_volatility(x['pct_chg'], x['_is_upside'], window)\n",
|
||
" # ).reset_index(level=0, drop=True)\n",
|
||
" #\n",
|
||
" # # 2. 下行波动率 (20日)\n",
|
||
" # def rolling_downside_volatility(series, _is_downside, window):\n",
|
||
" # # 提取负收益\n",
|
||
" # negative_returns = series.where(_is_downside, np.nan)\n",
|
||
" # # 计算滚动窗口标准差\n",
|
||
" # return negative_returns.rolling(window=window, min_periods=2).std()\n",
|
||
" #\n",
|
||
" # df[f'downside_volatility_{window}'] = grouped.apply(\n",
|
||
" # lambda x: rolling_downside_volatility(x['pct_chg'], x['_is_downside'], window)\n",
|
||
" # ).reset_index(level=0, drop=True)\n",
|
||
" #\n",
|
||
" # # 3. 上行/下行波动率比率 (20日)\n",
|
||
" # df[f'volatility_ratio_{window}'] = df[f'upside_volatility_{window}'] / (df[f'downside_volatility_{window}'] + 1e-8)\n",
|
||
" #\n",
|
||
" # # 4. 上行半方差 (20日)\n",
|
||
" # def rolling_upside_semi_variance(series, _is_upside, window, threshold):\n",
|
||
" # # 提取正收益\n",
|
||
" # positive_returns = series.where(_is_upside, np.nan)\n",
|
||
" # # 计算平方偏差\n",
|
||
" # squared_deviation = (positive_returns - threshold) ** 2\n",
|
||
" # # 计算滚动窗口均值\n",
|
||
" # return squared_deviation.rolling(window=window, min_periods=2).mean()\n",
|
||
" #\n",
|
||
" # df[f'upside_semi_variance_{window}'] = grouped.apply(\n",
|
||
" # lambda x: rolling_upside_semi_variance(x['pct_chg'], x['_is_upside'], window, return_threshold)\n",
|
||
" # ).reset_index(level=0, drop=True)\n",
|
||
" #\n",
|
||
" # # 5. 下行半方差 (20日)\n",
|
||
" # def rolling_downside_semi_variance(series, _is_downside, window, threshold):\n",
|
||
" # # 提取负收益\n",
|
||
" # negative_returns = series.where(_is_downside, np.nan)\n",
|
||
" # # 计算平方偏差\n",
|
||
" # squared_deviation = (negative_returns - (-threshold)) ** 2\n",
|
||
" # # 计算滚动窗口均值\n",
|
||
" # return squared_deviation.rolling(window=window, min_periods=2).mean()\n",
|
||
" #\n",
|
||
" # df[f'downside_semi_variance_{window}'] = grouped.apply(\n",
|
||
" # lambda x: rolling_downside_semi_variance(x['pct_chg'], x['_is_downside'], window, return_threshold)\n",
|
||
" # ).reset_index(level=0, drop=True)\n",
|
||
" #\n",
|
||
" # # 8. 正负收益天数比率 (20日)\n",
|
||
" # df[f'positive_negative_days_ratio_{window}'] = grouped['pct_chg'].rolling(window=window, min_periods=2).apply(\n",
|
||
" # lambda x: np.sum(x > 0) / (np.sum(x < 0) + 1e-8)).reset_index(level=0, drop=True)\n",
|
||
" #\n",
|
||
" # # 9. 正收益幅度均值 (20日)\n",
|
||
" # def average_positive_return_magnitude(series):\n",
|
||
" # positive_returns = series[series > return_threshold]\n",
|
||
" # if positive_returns.empty:\n",
|
||
" # return 0\n",
|
||
" # return positive_returns.mean()\n",
|
||
" #\n",
|
||
" # df[f'avg_positive_return_magnitude_{window}'] = grouped['pct_chg'].rolling(window=window, min_periods=2).apply(\n",
|
||
" # average_positive_return_magnitude).reset_index(level=0, drop=True)\n",
|
||
" #\n",
|
||
" # # 10. 负收益幅度均值 (20日)\n",
|
||
" # def average_negative_return_magnitude(series):\n",
|
||
" # negative_returns = series[series < -return_threshold]\n",
|
||
" # if negative_returns.empty:\n",
|
||
" # return 0\n",
|
||
" # return np.abs(negative_returns.mean())\n",
|
||
" #\n",
|
||
" # df[f'avg_negative_return_magnitude_{window}'] = grouped['pct_chg'].rolling(window=window, min_periods=2).apply(\n",
|
||
" # average_negative_return_magnitude).reset_index(level=0, drop=True)\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": 34
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "53f86ddc0677a6d7",
|
||
"metadata": {
|
||
"jupyter": {
|
||
"source_hidden": true
|
||
},
|
||
"scrolled": true,
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:36:25.455672Z",
|
||
"start_time": "2025-04-04T15:36:19.322099Z"
|
||
}
|
||
},
|
||
"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": 35
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "dbe2fd8021b9417f",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:36:25.503415Z",
|
||
"start_time": "2025-04-04T15:36:25.498021Z"
|
||
}
|
||
},
|
||
"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": 36
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "85c3e3d0235ffffa",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:38:25.829052Z",
|
||
"start_time": "2025-04-04T15:36:25.591562Z"
|
||
}
|
||
},
|
||
"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",
|
||
"Index: 5118212 entries, 0 to 5118211\n",
|
||
"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": 37
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "f4f16d63ad18d1bc",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:38:26.184750Z",
|
||
"start_time": "2025-04-04T15:38:26.172896Z"
|
||
}
|
||
},
|
||
"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": 38
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "40e6b68a91b30c79",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:38:27.360168Z",
|
||
"start_time": "2025-04-04T15:38:26.400810Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"\n",
|
||
"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, feature_columns, ks_threshold=0.05, wasserstein_threshold=0.1, size=0.8, log=True):\n",
|
||
" dropped_features = []\n",
|
||
"\n",
|
||
" all_dates = sorted(train_data['trade_date'].unique().tolist()) # 获取所有唯一的 trade_date\n",
|
||
" split_date = all_dates[int(len(all_dates) * size)] # 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",
|
||
" # **统计数据漂移**\n",
|
||
" numeric_columns = train_data_split.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_split[feature], val_data_split[feature])\n",
|
||
" wasserstein_dist = wasserstein_distance(train_data_split[feature], val_data_split[feature])\n",
|
||
"\n",
|
||
" if p_value < ks_threshold or wasserstein_dist > wasserstein_threshold:\n",
|
||
" dropped_features.append(feature)\n",
|
||
" if log:\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",
|
||
"\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",
|
||
" # 使用已有的 pct_chg 字段计算波动率\n",
|
||
" volatility = stock_df['pct_chg'].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",
|
||
" return score\n",
|
||
"\n",
|
||
" # # 确保 DataFrame 按照股票代码和交易日期排序\n",
|
||
" # df = df.sort_values(by=['ts_code', 'trade_date'])\n",
|
||
"\n",
|
||
" # 对每个股票分别计算 score\n",
|
||
" df['score'] = df.groupby('ts_code').apply(compute_stock_score).reset_index(level=0, drop=True)\n",
|
||
"\n",
|
||
" return df['score']\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",
|
||
"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()\n",
|
||
"\n",
|
||
"\n",
|
||
"def mad_filter(df, features, n=3):\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",
|
||
"def percentile_filter(df, features, lower_percentile=0.01, upper_percentile=0.99):\n",
|
||
" for col in features:\n",
|
||
" # 按日期分组计算上下百分位数\n",
|
||
" lower_bound = df.groupby('trade_date')[col].transform(\n",
|
||
" lambda x: x.quantile(lower_percentile)\n",
|
||
" )\n",
|
||
" upper_bound = df.groupby('trade_date')[col].transform(\n",
|
||
" lambda x: x.quantile(upper_percentile)\n",
|
||
" )\n",
|
||
" # 截断超出范围的值\n",
|
||
" df[col] = np.clip(df[col], lower_bound, upper_bound)\n",
|
||
" return df\n",
|
||
"\n",
|
||
"\n",
|
||
"from scipy.stats import iqr\n",
|
||
"\n",
|
||
"\n",
|
||
"def iqr_filter(df, features):\n",
|
||
" for col in features:\n",
|
||
" df[col] = df.groupby('trade_date')[col].transform(\n",
|
||
" lambda x: (x - x.median()) / iqr(x) if iqr(x) != 0 else x\n",
|
||
" )\n",
|
||
" return df\n",
|
||
"\n",
|
||
"\n",
|
||
"def quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99, window=60):\n",
|
||
" df = df.copy()\n",
|
||
" for col in features:\n",
|
||
" # 计算 rolling 统计量，需要按日期进行 groupby\n",
|
||
" rolling_lower = df.groupby('trade_date')[col].transform(\n",
|
||
" lambda x: x.rolling(window=min(len(x), window)).quantile(lower_quantile))\n",
|
||
" rolling_upper = df.groupby('trade_date')[col].transform(\n",
|
||
" lambda x: x.rolling(window=min(len(x), window)).quantile(upper_quantile))\n",
|
||
"\n",
|
||
" # 对数据进行裁剪\n",
|
||
" df[col] = np.clip(df[col], rolling_lower, rolling_upper)\n",
|
||
"\n",
|
||
" return df\n"
|
||
],
|
||
"outputs": [],
|
||
"execution_count": 39
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "1c46817a-b5dd-4bec-8bb4-e6e80bfd9d66",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:38:27.370464Z",
|
||
"start_time": "2025-04-04T15:38:27.360168Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"# print(test_data.head()[['act_factor1', 'act_factor2', 'ts_code', 'trade_date']])"
|
||
],
|
||
"outputs": [],
|
||
"execution_count": 40
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "da2bb202843d9275",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:38:27.480633Z",
|
||
"start_time": "2025-04-04T15:38:27.463576Z"
|
||
}
|
||
},
|
||
"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",
|
||
" if validation_days == 0:\n",
|
||
" split_date = all_dates[-1]\n",
|
||
" else:\n",
|
||
" split_date = all_dates[-validation_days] # 划分点为倒数第 validation_days 天\n",
|
||
" if validation_days == 0:\n",
|
||
" train_data_split = train_data_df\n",
|
||
" else:\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",
|
||
" # 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": 41
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:39:38.894592Z",
|
||
"start_time": "2025-04-04T15:38:27.482638Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"\n",
|
||
"days = 2\n",
|
||
"df = df.sort_values(by=['ts_code', 'trade_date'])\n",
|
||
"# df['future_return'] = df.groupby('ts_code', group_keys=False)['close'].apply(lambda x: x.shift(-days) / x - 1)\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')['pct_chg']\n",
|
||
" .transform(lambda x: x.rolling(days).std().shift(-days))\n",
|
||
")\n",
|
||
"df['future_score'] = calculate_score(df, days=2, lambda_param=0.3)\n",
|
||
"df['label'] = df.groupby('trade_date', group_keys=False)['future_score'].transform(\n",
|
||
" lambda x: pd.qcut(x, q=20, labels=False, duplicates='drop')\n",
|
||
")\n",
|
||
"# df['label'] = df.groupby('trade_date', group_keys=False)['future_score'].transform(\n",
|
||
"# lambda x: pd.qcut(x.rank(method='first'), q=20, labels=False, duplicates='raise')\n",
|
||
"# )\n",
|
||
"# df['future_score'] = (\n",
|
||
"# 0.7 * df['future_return']\n",
|
||
"# * 0.3 * df['future_volatility']\n",
|
||
"# )"
|
||
],
|
||
"id": "ff19e3f1e051a489",
|
||
"outputs": [],
|
||
"execution_count": 42
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:39:51.373402Z",
|
||
"start_time": "2025-04-04T15:39:38.993074Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"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",
|
||
"\n",
|
||
"pdf = select_pre_zt_stocks_dynamic(df)\n",
|
||
"filter_index = pdf['future_return'].between(pdf['future_return'].quantile(0.01), pdf['future_return'].quantile(0.99))\n",
|
||
"\n",
|
||
"# filter_index = pdf['future_volatility'].between(pdf['future_volatility'].quantile(0.01),\n",
|
||
"# pdf['future_volatility'].quantile(0.99)) | filter_index"
|
||
],
|
||
"id": "27dba27b2e108316",
|
||
"outputs": [],
|
||
"execution_count": 43
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:39:58.079901Z",
|
||
"start_time": "2025-04-04T15:39:51.374912Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"\n",
|
||
"pdf = pdf.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n",
|
||
"pdf = pdf.sort_values(['trade_date'])\n",
|
||
"pdf = pdf.replace([np.inf, -np.inf], np.nan)\n",
|
||
"\n",
|
||
"feature_columns = [col for col in pdf.columns if col in pdf.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 'pe_ttm' not in col]\n",
|
||
"feature_columns = [col for col in feature_columns if 'volatility' 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 = pdf.select_dtypes(include=['float64', 'int64']).columns\n",
|
||
"numeric_columns = [col for col in numeric_columns if col in feature_columns]"
|
||
],
|
||
"id": "ca96fb81e17c4a90",
|
||
"outputs": [],
|
||
"execution_count": 44
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:46:05.915307Z",
|
||
"start_time": "2025-04-04T15:39:58.224302Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"pdf = quantile_filter(pdf, numeric_columns)\n",
|
||
"\n",
|
||
"pdf = cross_sectional_standardization(pdf, numeric_columns)\n",
|
||
"\n",
|
||
"# print('去极值')\n",
|
||
"# train_data = quantile_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 = quantile_filter(test_data, numeric_columns) # 去极值\n",
|
||
"\n",
|
||
"feature_columns = remove_highly_correlated_features(pdf,\n",
|
||
" feature_columns)\n",
|
||
"print(len(pdf))"
|
||
],
|
||
"id": "81d4570663ae21d7",
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"1755000\n"
|
||
]
|
||
}
|
||
],
|
||
"execution_count": 45
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "92428d543f4727ad",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:46:06.774220Z",
|
||
"start_time": "2025-04-04T15:46:06.034832Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"# print('train data size: ', len(train_data))\n",
|
||
"\n",
|
||
"label_gain = list(range(len(df['label'].unique())))\n",
|
||
"label_gain = [gain * gain for gain in label_gain]\n",
|
||
"light_params = {\n",
|
||
" 'label_gain': label_gain,\n",
|
||
" 'objective': 'lambdarank',\n",
|
||
" 'metric': 'ndcg',\n",
|
||
" 'learning_rate': 0.03,\n",
|
||
" 'num_leaves': 32,\n",
|
||
" # 'min_data_in_leaf': 128,\n",
|
||
" 'max_depth': 8,\n",
|
||
" 'max_bin': 32,\n",
|
||
" 'feature_fraction': 0.7,\n",
|
||
" # 'bagging_fraction': 0.7,\n",
|
||
" 'bagging_freq': 5,\n",
|
||
" 'lambda_l1': 0.1,\n",
|
||
" 'lambda_l2': 0.1,\n",
|
||
" 'boosting': 'gbdt',\n",
|
||
" 'verbosity': -1,\n",
|
||
" 'extra_trees': True,\n",
|
||
" 'max_position': 5,\n",
|
||
" 'ndcg_at': 1,\n",
|
||
" 'quant_train_renew_leaf': True,\n",
|
||
" 'lambdarank_truncation_level': 3,\n",
|
||
" # 'lambdarank_position_bias_regularization': 1,\n",
|
||
" 'seed': 7\n",
|
||
"}\n",
|
||
"evals = {}\n",
|
||
"\n",
|
||
"gc.collect()"
|
||
],
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"0"
|
||
]
|
||
},
|
||
"execution_count": 46,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"execution_count": 46
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "8f134d435f71e9e2",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:46:06.992779Z",
|
||
"start_time": "2025-04-04T15:46:06.838417Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"gc.collect()\n",
|
||
"\n",
|
||
"\n",
|
||
"def rolling_train_predict(df, train_days, test_days, feature_columns_origin, days=5, use_pca=False, validation_days=60,\n",
|
||
" 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",
|
||
"\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",
|
||
" test_data = df[df['trade_date'].isin(test_dates)]\n",
|
||
"\n",
|
||
" train_data = train_data.sort_values('trade_date')\n",
|
||
" test_data = test_data.sort_values('trade_date')\n",
|
||
"\n",
|
||
" feature_columns, _ = remove_shifted_features(train_data, feature_columns_origin, size=0.8, log=False)\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 + 1) * (gain + 1) 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(100, first_metric_only=True)\n",
|
||
" ], evals,\n",
|
||
" num_boost_round=100, validation_days=validation_days,\n",
|
||
" print_feature_importance=False, use_pca=False)\n",
|
||
"\n",
|
||
" score_df = test_data.copy()\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": [],
|
||
"execution_count": 47
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "63235069-dc59-48fb-961a-e80373e41a61",
|
||
"metadata": {
|
||
"editable": true,
|
||
"scrolled": true,
|
||
"slideshow": {
|
||
"slide_type": ""
|
||
},
|
||
"tags": [],
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:58:02.493421Z",
|
||
"start_time": "2025-04-04T15:46:06.999789Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"\n",
|
||
"gc.collect()\n",
|
||
"\n",
|
||
"print(df[df['ts_code'] == '000001.SZ'].tail(1)[['act_factor1', 'act_factor2']])\n",
|
||
"print('finish')\n",
|
||
"# qdf = qdf[qdf['trade_date'] >= '2022-01-01']\n",
|
||
"\n",
|
||
"final_predictions = rolling_train_predict(pdf[pdf['trade_date'] >= '2023-01-01'], 20, 1, feature_columns,\n",
|
||
" days=days, validation_days=0, filter_index=filter_index)\n",
|
||
"final_predictions.to_csv('predictions_test.tsv', index=False)\n"
|
||
],
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" act_factor1 act_factor2\n",
|
||
"5115129 -0.222482 -0.256946\n",
|
||
"finish\n",
|
||
"最大日期: 2023-02-07\n",
|
||
"原始训练集大小: 6846\n",
|
||
"划分后的训练集大小: 6846, 验证集大小: 355\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-08\n",
|
||
"原始训练集大小: 6811\n",
|
||
"划分后的训练集大小: 6811, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-02-09\n",
|
||
"原始训练集大小: 6872\n",
|
||
"划分后的训练集大小: 6872, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-10\n",
|
||
"原始训练集大小: 6853\n",
|
||
"划分后的训练集大小: 6853, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.954\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-02-13\n",
|
||
"原始训练集大小: 6838\n",
|
||
"划分后的训练集大小: 6838, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-14\n",
|
||
"原始训练集大小: 6853\n",
|
||
"划分后的训练集大小: 6853, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-15\n",
|
||
"原始训练集大小: 6828\n",
|
||
"划分后的训练集大小: 6828, 验证集大小: 328\n",
|
||
"[100]\ttrain's ndcg@1: 0.945\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-02-16\n",
|
||
"原始训练集大小: 6850\n",
|
||
"划分后的训练集大小: 6850, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-02-17\n",
|
||
"原始训练集大小: 6860\n",
|
||
"划分后的训练集大小: 6860, 验证集大小: 362\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-20\n",
|
||
"原始训练集大小: 6818\n",
|
||
"划分后的训练集大小: 6818, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-21\n",
|
||
"原始训练集大小: 6862\n",
|
||
"划分后的训练集大小: 6862, 验证集大小: 342\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-22\n",
|
||
"原始训练集大小: 6855\n",
|
||
"划分后的训练集大小: 6855, 验证集大小: 359\n",
|
||
"[100]\ttrain's ndcg@1: 0.952\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-02-23\n",
|
||
"原始训练集大小: 6822\n",
|
||
"划分后的训练集大小: 6822, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-24\n",
|
||
"原始训练集大小: 6857\n",
|
||
"划分后的训练集大小: 6857, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-27\n",
|
||
"原始训练集大小: 6854\n",
|
||
"划分后的训练集大小: 6854, 验证集大小: 371\n",
|
||
"[100]\ttrain's ndcg@1: 0.95175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-02-28\n",
|
||
"原始训练集大小: 6813\n",
|
||
"划分后的训练集大小: 6813, 验证集大小: 310\n",
|
||
"[100]\ttrain's ndcg@1: 0.957375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-01\n",
|
||
"原始训练集大小: 6858\n",
|
||
"划分后的训练集大小: 6858, 验证集大小: 346\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-03-02\n",
|
||
"原始训练集大小: 6845\n",
|
||
"划分后的训练集大小: 6845, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-03-03\n",
|
||
"原始训练集大小: 6842\n",
|
||
"划分后的训练集大小: 6842, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-06\n",
|
||
"原始训练集大小: 6868\n",
|
||
"划分后的训练集大小: 6868, 验证集大小: 351\n",
|
||
"[100]\ttrain's ndcg@1: 0.937875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-07\n",
|
||
"原始训练集大小: 6858\n",
|
||
"划分后的训练集大小: 6858, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.930125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-08\n",
|
||
"原始训练集大小: 6833\n",
|
||
"划分后的训练集大小: 6833, 验证集大小: 302\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-09\n",
|
||
"原始训练集大小: 6835\n",
|
||
"划分后的训练集大小: 6835, 验证集大小: 358\n",
|
||
"[100]\ttrain's ndcg@1: 0.97225\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-10\n",
|
||
"原始训练集大小: 6838\n",
|
||
"划分后的训练集大小: 6838, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-13\n",
|
||
"原始训练集大小: 6808\n",
|
||
"划分后的训练集大小: 6808, 验证集大小: 310\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-14\n",
|
||
"原始训练集大小: 6846\n",
|
||
"划分后的训练集大小: 6846, 验证集大小: 383\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-15\n",
|
||
"原始训练集大小: 6843\n",
|
||
"划分后的训练集大小: 6843, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.97075\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-03-16\n",
|
||
"原始训练集大小: 6822\n",
|
||
"划分后的训练集大小: 6822, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.9435\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-17\n",
|
||
"原始训练集大小: 6839\n",
|
||
"划分后的训练集大小: 6839, 验证集大小: 379\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-03-20\n",
|
||
"原始训练集大小: 6829\n",
|
||
"划分后的训练集大小: 6829, 验证集大小: 315\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-03-21\n",
|
||
"原始训练集大小: 6828\n",
|
||
"划分后的训练集大小: 6828, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-22\n",
|
||
"原始训练集大小: 6822\n",
|
||
"划分后的训练集大小: 6822, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-23\n",
|
||
"原始训练集大小: 6817\n",
|
||
"划分后的训练集大小: 6817, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-24\n",
|
||
"原始训练集大小: 6845\n",
|
||
"划分后的训练集大小: 6845, 验证集大小: 371\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-27\n",
|
||
"原始训练集大小: 6811\n",
|
||
"划分后的训练集大小: 6811, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-28\n",
|
||
"原始训练集大小: 6825\n",
|
||
"划分后的训练集大小: 6825, 验证集大小: 324\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-29\n",
|
||
"原始训练集大小: 6841\n",
|
||
"划分后的训练集大小: 6841, 验证集大小: 362\n",
|
||
"[100]\ttrain's ndcg@1: 0.97225\tvalid's ndcg@1: 0.64\n",
|
||
"最大日期: 2023-03-30\n",
|
||
"原始训练集大小: 6838\n",
|
||
"划分后的训练集大小: 6838, 验证集大小: 350\n",
|
||
"[100]\ttrain's ndcg@1: 0.967625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-03-31\n",
|
||
"原始训练集大小: 6803\n",
|
||
"划分后的训练集大小: 6803, 验证集大小: 298\n",
|
||
"[100]\ttrain's ndcg@1: 0.957875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-03\n",
|
||
"原始训练集大小: 6829\n",
|
||
"划分后的训练集大小: 6829, 验证集大小: 377\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-04\n",
|
||
"原始训练集大小: 6817\n",
|
||
"划分后的训练集大小: 6817, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-04-06\n",
|
||
"原始训练集大小: 6834\n",
|
||
"划分后的训练集大小: 6834, 验证集大小: 319\n",
|
||
"[100]\ttrain's ndcg@1: 0.948125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-07\n",
|
||
"原始训练集大小: 6843\n",
|
||
"划分后的训练集大小: 6843, 验证集大小: 367\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-04-10\n",
|
||
"原始训练集大小: 6823\n",
|
||
"划分后的训练集大小: 6823, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.976375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-11\n",
|
||
"原始训练集大小: 6851\n",
|
||
"划分后的训练集大小: 6851, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-12\n",
|
||
"原始训练集大小: 6791\n",
|
||
"划分后的训练集大小: 6791, 验证集大小: 323\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-13\n",
|
||
"原始训练集大小: 6815\n",
|
||
"划分后的训练集大小: 6815, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.957875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-14\n",
|
||
"原始训练集大小: 6830\n",
|
||
"划分后的训练集大小: 6830, 验证集大小: 342\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-17\n",
|
||
"原始训练集大小: 6777\n",
|
||
"划分后的训练集大小: 6777, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.957375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-18\n",
|
||
"原始训练集大小: 6787\n",
|
||
"划分后的训练集大小: 6787, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-19\n",
|
||
"原始训练集大小: 6800\n",
|
||
"划分后的训练集大小: 6800, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-20\n",
|
||
"原始训练集大小: 6774\n",
|
||
"划分后的训练集大小: 6774, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.949375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-04-21\n",
|
||
"原始训练集大小: 6784\n",
|
||
"划分后的训练集大小: 6784, 验证集大小: 335\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-24\n",
|
||
"原始训练集大小: 6771\n",
|
||
"划分后的训练集大小: 6771, 验证集大小: 358\n",
|
||
"[100]\ttrain's ndcg@1: 0.968375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-25\n",
|
||
"原始训练集大小: 6759\n",
|
||
"划分后的训练集大小: 6759, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.96275\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-26\n",
|
||
"原始训练集大小: 6759\n",
|
||
"划分后的训练集大小: 6759, 验证集大小: 324\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-04-27\n",
|
||
"原始训练集大小: 6777\n",
|
||
"划分后的训练集大小: 6777, 验证集大小: 380\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-04-28\n",
|
||
"原始训练集大小: 6706\n",
|
||
"划分后的训练集大小: 6706, 验证集大小: 279\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-04\n",
|
||
"原始训练集大小: 6760\n",
|
||
"划分后的训练集大小: 6760, 验证集大小: 352\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-05\n",
|
||
"原始训练集大小: 6756\n",
|
||
"划分后的训练集大小: 6756, 验证集大小: 373\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-08\n",
|
||
"原始训练集大小: 6729\n",
|
||
"划分后的训练集大小: 6729, 验证集大小: 306\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-09\n",
|
||
"原始训练集大小: 6759\n",
|
||
"划分后的训练集大小: 6759, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-10\n",
|
||
"原始训练集大小: 6758\n",
|
||
"划分后的训练集大小: 6758, 验证集大小: 366\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-11\n",
|
||
"原始训练集大小: 6753\n",
|
||
"划分后的训练集大小: 6753, 验证集大小: 322\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-12\n",
|
||
"原始训练集大小: 6760\n",
|
||
"划分后的训练集大小: 6760, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-05-15\n",
|
||
"原始训练集大小: 6776\n",
|
||
"划分后的训练集大小: 6776, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.967125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-16\n",
|
||
"原始训练集大小: 6750\n",
|
||
"划分后的训练集大小: 6750, 验证集大小: 323\n",
|
||
"[100]\ttrain's ndcg@1: 0.939625\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-05-17\n",
|
||
"原始训练集大小: 6772\n",
|
||
"划分后的训练集大小: 6772, 验证集大小: 364\n",
|
||
"[100]\ttrain's ndcg@1: 0.9535\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-18\n",
|
||
"原始训练集大小: 6754\n",
|
||
"划分后的训练集大小: 6754, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.939375\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-05-19\n",
|
||
"原始训练集大小: 6773\n",
|
||
"划分后的训练集大小: 6773, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.955375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-22\n",
|
||
"原始训练集大小: 6790\n",
|
||
"划分后的训练集大小: 6790, 验证集大小: 371\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-23\n",
|
||
"原始训练集大小: 6754\n",
|
||
"划分后的训练集大小: 6754, 验证集大小: 291\n",
|
||
"[100]\ttrain's ndcg@1: 0.946\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-05-24\n",
|
||
"原始训练集大小: 6768\n",
|
||
"划分后的训练集大小: 6768, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.976625\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-05-25\n",
|
||
"原始训练集大小: 6752\n",
|
||
"划分后的训练集大小: 6752, 验证集大小: 342\n",
|
||
"[100]\ttrain's ndcg@1: 0.976375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-26\n",
|
||
"原始训练集大小: 6757\n",
|
||
"划分后的训练集大小: 6757, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.941125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-29\n",
|
||
"原始训练集大小: 6776\n",
|
||
"划分后的训练集大小: 6776, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.96475\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-30\n",
|
||
"原始训练集大小: 6724\n",
|
||
"划分后的训练集大小: 6724, 验证集大小: 328\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-05-31\n",
|
||
"原始训练集大小: 6782\n",
|
||
"划分后的训练集大小: 6782, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 0.938125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-01\n",
|
||
"原始训练集大小: 6770\n",
|
||
"划分后的训练集大小: 6770, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.927\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-02\n",
|
||
"原始训练集大小: 6728\n",
|
||
"划分后的训练集大小: 6728, 验证集大小: 331\n",
|
||
"[100]\ttrain's ndcg@1: 0.92725\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-05\n",
|
||
"原始训练集大小: 6745\n",
|
||
"划分后的训练集大小: 6745, 验证集大小: 323\n",
|
||
"[100]\ttrain's ndcg@1: 0.94325\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-06\n",
|
||
"原始训练集大小: 6764\n",
|
||
"划分后的训练集大小: 6764, 验证集大小: 368\n",
|
||
"[100]\ttrain's ndcg@1: 0.919375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-07\n",
|
||
"原始训练集大小: 6692\n",
|
||
"划分后的训练集大小: 6692, 验证集大小: 294\n",
|
||
"[100]\ttrain's ndcg@1: 0.943\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-08\n",
|
||
"原始训练集大小: 6698\n",
|
||
"划分后的训练集大小: 6698, 验证集大小: 328\n",
|
||
"[100]\ttrain's ndcg@1: 0.93375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-09\n",
|
||
"原始训练集大小: 6723\n",
|
||
"划分后的训练集大小: 6723, 验证集大小: 370\n",
|
||
"[100]\ttrain's ndcg@1: 0.93425\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-12\n",
|
||
"原始训练集大小: 6693\n",
|
||
"划分后的训练集大小: 6693, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-13\n",
|
||
"原始训练集大小: 6709\n",
|
||
"划分后的训练集大小: 6709, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.91675\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-14\n",
|
||
"原始训练集大小: 6688\n",
|
||
"划分后的训练集大小: 6688, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-15\n",
|
||
"原始训练集大小: 6711\n",
|
||
"划分后的训练集大小: 6711, 验证集大小: 331\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-16\n",
|
||
"原始训练集大小: 6716\n",
|
||
"划分后的训练集大小: 6716, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.962\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-19\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-20\n",
|
||
"原始训练集大小: 6707\n",
|
||
"划分后的训练集大小: 6707, 验证集大小: 314\n",
|
||
"[100]\ttrain's ndcg@1: 0.94275\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-06-21\n",
|
||
"原始训练集大小: 6712\n",
|
||
"划分后的训练集大小: 6712, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.9435\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-26\n",
|
||
"原始训练集大小: 6686\n",
|
||
"划分后的训练集大小: 6686, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.962\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-06-27\n",
|
||
"原始训练集大小: 6668\n",
|
||
"划分后的训练集大小: 6668, 验证集大小: 312\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-28\n",
|
||
"原始训练集大小: 6708\n",
|
||
"划分后的训练集大小: 6708, 验证集大小: 383\n",
|
||
"[100]\ttrain's ndcg@1: 0.956375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-29\n",
|
||
"原始训练集大小: 6652\n",
|
||
"划分后的训练集大小: 6652, 验证集大小: 272\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-06-30\n",
|
||
"原始训练集大小: 6685\n",
|
||
"划分后的训练集大小: 6685, 验证集大小: 370\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-03\n",
|
||
"原始训练集大小: 6714\n",
|
||
"划分后的训练集大小: 6714, 验证集大小: 369\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-04\n",
|
||
"原始训练集大小: 6666\n",
|
||
"划分后的训练集大小: 6666, 验证集大小: 283\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-05\n",
|
||
"原始训练集大小: 6723\n",
|
||
"划分后的训练集大小: 6723, 验证集大小: 380\n",
|
||
"[100]\ttrain's ndcg@1: 0.943\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-06\n",
|
||
"原始训练集大小: 6698\n",
|
||
"划分后的训练集大小: 6698, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.95275\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-07-07\n",
|
||
"原始训练集大小: 6719\n",
|
||
"划分后的训练集大小: 6719, 验证集大小: 315\n",
|
||
"[100]\ttrain's ndcg@1: 0.942\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-07-10\n",
|
||
"原始训练集大小: 6746\n",
|
||
"划分后的训练集大小: 6746, 验证集大小: 355\n",
|
||
"[100]\ttrain's ndcg@1: 0.95175\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-07-11\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-07-12\n",
|
||
"原始训练集大小: 6729\n",
|
||
"划分后的训练集大小: 6729, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-13\n",
|
||
"原始训练集大小: 6746\n",
|
||
"划分后的训练集大小: 6746, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-14\n",
|
||
"原始训练集大小: 6685\n",
|
||
"划分后的训练集大小: 6685, 验证集大小: 282\n",
|
||
"[100]\ttrain's ndcg@1: 0.946875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-17\n",
|
||
"原始训练集大小: 6703\n",
|
||
"划分后的训练集大小: 6703, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-18\n",
|
||
"原始训练集大小: 6742\n",
|
||
"划分后的训练集大小: 6742, 验证集大小: 388\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 0.7225\n",
|
||
"最大日期: 2023-07-19\n",
|
||
"原始训练集大小: 6664\n",
|
||
"划分后的训练集大小: 6664, 验证集大小: 261\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-20\n",
|
||
"原始训练集大小: 6704\n",
|
||
"划分后的训练集大小: 6704, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-21\n",
|
||
"原始训练集大小: 6747\n",
|
||
"划分后的训练集大小: 6747, 验证集大小: 397\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-24\n",
|
||
"原始训练集大小: 6703\n",
|
||
"划分后的训练集大小: 6703, 验证集大小: 272\n",
|
||
"[100]\ttrain's ndcg@1: 0.966625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-25\n",
|
||
"原始训练集大小: 6590\n",
|
||
"划分后的训练集大小: 6590, 验证集大小: 199\n",
|
||
"[100]\ttrain's ndcg@1: 0.97075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-26\n",
|
||
"原始训练集大小: 6331\n",
|
||
"划分后的训练集大小: 6331, 验证集大小: 124\n",
|
||
"[100]\ttrain's ndcg@1: 0.9625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-07-27\n",
|
||
"原始训练集大小: 6179\n",
|
||
"划分后的训练集大小: 6179, 验证集大小: 120\n",
|
||
"[100]\ttrain's ndcg@1: 0.939375\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-07-28\n",
|
||
"原始训练集大小: 6139\n",
|
||
"划分后的训练集大小: 6139, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.961\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-07-31\n",
|
||
"原始训练集大小: 6079\n",
|
||
"划分后的训练集大小: 6079, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-01\n",
|
||
"原始训练集大小: 6130\n",
|
||
"划分后的训练集大小: 6130, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.938375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-02\n",
|
||
"原始训练集大小: 6050\n",
|
||
"划分后的训练集大小: 6050, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-03\n",
|
||
"原始训练集大小: 5975\n",
|
||
"划分后的训练集大小: 5975, 验证集大小: 268\n",
|
||
"[100]\ttrain's ndcg@1: 0.965875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-04\n",
|
||
"原始训练集大小: 5968\n",
|
||
"划分后的训练集大小: 5968, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-07\n",
|
||
"原始训练集大小: 5960\n",
|
||
"划分后的训练集大小: 5960, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.937625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-08-08\n",
|
||
"原始训练集大小: 5938\n",
|
||
"划分后的训练集大小: 5938, 验证集大小: 286\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-09\n",
|
||
"原始训练集大小: 5908\n",
|
||
"划分后的训练集大小: 5908, 验证集大小: 324\n",
|
||
"[100]\ttrain's ndcg@1: 0.943\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-08-10\n",
|
||
"原始训练集大小: 5897\n",
|
||
"划分后的训练集大小: 5897, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.966625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-11\n",
|
||
"原始训练集大小: 5909\n",
|
||
"划分后的训练集大小: 5909, 验证集大小: 294\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-08-14\n",
|
||
"原始训练集大小: 5900\n",
|
||
"划分后的训练集大小: 5900, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-15\n",
|
||
"原始训练集大小: 5846\n",
|
||
"划分后的训练集大小: 5846, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-16\n",
|
||
"原始训练集大小: 5904\n",
|
||
"划分后的训练集大小: 5904, 验证集大小: 319\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-17\n",
|
||
"原始训练集大小: 5883\n",
|
||
"划分后的训练集大小: 5883, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.959875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-18\n",
|
||
"原始训练集大小: 5783\n",
|
||
"划分后的训练集大小: 5783, 验证集大小: 297\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-21\n",
|
||
"原始训练集大小: 5827\n",
|
||
"划分后的训练集大小: 5827, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-22\n",
|
||
"原始训练集大小: 5989\n",
|
||
"划分后的训练集大小: 5989, 验证集大小: 361\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-23\n",
|
||
"原始训练集大小: 6164\n",
|
||
"划分后的训练集大小: 6164, 验证集大小: 299\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-08-24\n",
|
||
"原始训练集大小: 6373\n",
|
||
"划分后的训练集大小: 6373, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.976375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-25\n",
|
||
"原始训练集大小: 6421\n",
|
||
"划分后的训练集大小: 6421, 验证集大小: 378\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-28\n",
|
||
"原始训练集大小: 6382\n",
|
||
"划分后的训练集大小: 6382, 验证集大小: 270\n",
|
||
"[100]\ttrain's ndcg@1: 0.986125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-29\n",
|
||
"原始训练集大小: 6400\n",
|
||
"划分后的训练集大小: 6400, 验证集大小: 352\n",
|
||
"[100]\ttrain's ndcg@1: 0.98125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-30\n",
|
||
"原始训练集大小: 6467\n",
|
||
"划分后的训练集大小: 6467, 验证集大小: 367\n",
|
||
"[100]\ttrain's ndcg@1: 0.966625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-08-31\n",
|
||
"原始训练集大小: 6481\n",
|
||
"划分后的训练集大小: 6481, 验证集大小: 282\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-01\n",
|
||
"原始训练集大小: 6512\n",
|
||
"划分后的训练集大小: 6512, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.94375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-04\n",
|
||
"原始训练集大小: 6525\n",
|
||
"划分后的训练集大小: 6525, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-09-05\n",
|
||
"原始训练集大小: 6555\n",
|
||
"划分后的训练集大小: 6555, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.957125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-09-06\n",
|
||
"原始训练集大小: 6572\n",
|
||
"划分后的训练集大小: 6572, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-07\n",
|
||
"原始训练集大小: 6556\n",
|
||
"划分后的训练集大小: 6556, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-08\n",
|
||
"原始训练集大小: 6582\n",
|
||
"划分后的训练集大小: 6582, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.95375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-11\n",
|
||
"原始训练集大小: 6603\n",
|
||
"划分后的训练集大小: 6603, 验证集大小: 361\n",
|
||
"[100]\ttrain's ndcg@1: 0.939125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-12\n",
|
||
"原始训练集大小: 6586\n",
|
||
"划分后的训练集大小: 6586, 验证集大小: 317\n",
|
||
"[100]\ttrain's ndcg@1: 0.957875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-13\n",
|
||
"原始训练集大小: 6581\n",
|
||
"划分后的训练集大小: 6581, 验证集大小: 314\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-09-14\n",
|
||
"原始训练集大小: 6630\n",
|
||
"划分后的训练集大小: 6630, 验证集大小: 382\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-15\n",
|
||
"原始训练集大小: 6625\n",
|
||
"划分后的训练集大小: 6625, 验证集大小: 292\n",
|
||
"[100]\ttrain's ndcg@1: 0.967375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-18\n",
|
||
"原始训练集大小: 6650\n",
|
||
"划分后的训练集大小: 6650, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.958875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-19\n",
|
||
"原始训练集大小: 6665\n",
|
||
"划分后的训练集大小: 6665, 验证集大小: 376\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-09-20\n",
|
||
"原始训练集大小: 6662\n",
|
||
"划分后的训练集大小: 6662, 验证集大小: 296\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-21\n",
|
||
"原始训练集大小: 6676\n",
|
||
"划分后的训练集大小: 6676, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.9535\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-22\n",
|
||
"原始训练集大小: 6642\n",
|
||
"划分后的训练集大小: 6642, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-25\n",
|
||
"原始训练集大小: 6685\n",
|
||
"划分后的训练集大小: 6685, 验证集大小: 313\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-26\n",
|
||
"原始训练集大小: 6671\n",
|
||
"划分后的训练集大小: 6671, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-27\n",
|
||
"原始训练集大小: 6622\n",
|
||
"划分后的训练集大小: 6622, 验证集大小: 318\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-09-28\n",
|
||
"原始训练集大小: 6647\n",
|
||
"划分后的训练集大小: 6647, 验证集大小: 307\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-09\n",
|
||
"原始训练集大小: 6697\n",
|
||
"划分后的训练集大小: 6697, 验证集大小: 389\n",
|
||
"[100]\ttrain's ndcg@1: 0.94325\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-10\n",
|
||
"原始训练集大小: 6637\n",
|
||
"划分后的训练集大小: 6637, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-10-11\n",
|
||
"原始训练集大小: 6621\n",
|
||
"划分后的训练集大小: 6621, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-12\n",
|
||
"原始训练集大小: 6688\n",
|
||
"划分后的训练集大小: 6688, 验证集大小: 408\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-13\n",
|
||
"原始训练集大小: 6609\n",
|
||
"划分后的训练集大小: 6609, 验证集大小: 250\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-16\n",
|
||
"原始训练集大小: 6596\n",
|
||
"划分后的训练集大小: 6596, 验证集大小: 307\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-17\n",
|
||
"原始训练集大小: 6571\n",
|
||
"划分后的训练集大小: 6571, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-18\n",
|
||
"原始训练集大小: 6511\n",
|
||
"划分后的训练集大小: 6511, 验证集大小: 257\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-19\n",
|
||
"原始训练集大小: 6519\n",
|
||
"划分后的训练集大小: 6519, 验证集大小: 322\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-20\n",
|
||
"原始训练集大小: 6482\n",
|
||
"划分后的训练集大小: 6482, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-23\n",
|
||
"原始训练集大小: 6507\n",
|
||
"划分后的训练集大小: 6507, 验证集大小: 317\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-24\n",
|
||
"原始训练集大小: 6524\n",
|
||
"划分后的训练集大小: 6524, 验证集大小: 358\n",
|
||
"[100]\ttrain's ndcg@1: 0.9905\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-25\n",
|
||
"原始训练集大小: 6484\n",
|
||
"划分后的训练集大小: 6484, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-10-26\n",
|
||
"原始训练集大小: 6482\n",
|
||
"划分后的训练集大小: 6482, 验证集大小: 294\n",
|
||
"[100]\ttrain's ndcg@1: 0.9905\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-27\n",
|
||
"原始训练集大小: 6523\n",
|
||
"划分后的训练集大小: 6523, 验证集大小: 384\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-30\n",
|
||
"原始训练集大小: 6488\n",
|
||
"划分后的训练集大小: 6488, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-10-31\n",
|
||
"原始训练集大小: 6484\n",
|
||
"划分后的训练集大小: 6484, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-01\n",
|
||
"原始训练集大小: 6566\n",
|
||
"划分后的训练集大小: 6566, 验证集大小: 420\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-02\n",
|
||
"原始训练集大小: 6512\n",
|
||
"划分后的训练集大小: 6512, 验证集大小: 264\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-03\n",
|
||
"原始训练集大小: 6531\n",
|
||
"划分后的训练集大小: 6531, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-06\n",
|
||
"原始训练集大小: 6539\n",
|
||
"划分后的训练集大小: 6539, 验证集大小: 397\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-07\n",
|
||
"原始训练集大小: 6520\n",
|
||
"划分后的训练集大小: 6520, 验证集大小: 281\n",
|
||
"[100]\ttrain's ndcg@1: 0.97175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-08\n",
|
||
"原始训练集大小: 6571\n",
|
||
"划分后的训练集大小: 6571, 验证集大小: 351\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-09\n",
|
||
"原始训练集大小: 6500\n",
|
||
"划分后的训练集大小: 6500, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-10\n",
|
||
"原始训练集大小: 6552\n",
|
||
"划分后的训练集大小: 6552, 验证集大小: 302\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-13\n",
|
||
"原始训练集大小: 6594\n",
|
||
"划分后的训练集大小: 6594, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-11-14\n",
|
||
"原始训练集大小: 6601\n",
|
||
"划分后的训练集大小: 6601, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-15\n",
|
||
"原始训练集大小: 6647\n",
|
||
"划分后的训练集大小: 6647, 验证集大小: 303\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-16\n",
|
||
"原始训练集大小: 6694\n",
|
||
"划分后的训练集大小: 6694, 验证集大小: 369\n",
|
||
"[100]\ttrain's ndcg@1: 0.977125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-17\n",
|
||
"原始训练集大小: 6650\n",
|
||
"划分后的训练集大小: 6650, 验证集大小: 301\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-20\n",
|
||
"原始训练集大小: 6645\n",
|
||
"划分后的训练集大小: 6645, 验证集大小: 312\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-21\n",
|
||
"原始训练集大小: 6674\n",
|
||
"划分后的训练集大小: 6674, 验证集大小: 387\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-22\n",
|
||
"原始训练集大小: 6617\n",
|
||
"划分后的训练集大小: 6617, 验证集大小: 279\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-23\n",
|
||
"原始训练集大小: 6661\n",
|
||
"划分后的训练集大小: 6661, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-24\n",
|
||
"原始训练集大小: 6633\n",
|
||
"划分后的训练集大小: 6633, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2023-11-27\n",
|
||
"原始训练集大小: 6610\n",
|
||
"划分后的训练集大小: 6610, 验证集大小: 286\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-28\n",
|
||
"原始训练集大小: 6663\n",
|
||
"划分后的训练集大小: 6663, 验证集大小: 362\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-29\n",
|
||
"原始训练集大小: 6572\n",
|
||
"划分后的训练集大小: 6572, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-11-30\n",
|
||
"原始训练集大小: 6611\n",
|
||
"划分后的训练集大小: 6611, 验证集大小: 303\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-01\n",
|
||
"原始训练集大小: 6619\n",
|
||
"划分后的训练集大小: 6619, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-12-04\n",
|
||
"原始训练集大小: 6536\n",
|
||
"划分后的训练集大小: 6536, 验证集大小: 314\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-05\n",
|
||
"原始训练集大小: 6551\n",
|
||
"划分后的训练集大小: 6551, 验证集大小: 296\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-06\n",
|
||
"原始训练集大小: 6557\n",
|
||
"划分后的训练集大小: 6557, 验证集大小: 357\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-07\n",
|
||
"原始训练集大小: 6549\n",
|
||
"划分后的训练集大小: 6549, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.97075\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-12-08\n",
|
||
"原始训练集大小: 6557\n",
|
||
"划分后的训练集大小: 6557, 验证集大小: 310\n",
|
||
"[100]\ttrain's ndcg@1: 0.98125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-11\n",
|
||
"原始训练集大小: 6551\n",
|
||
"划分后的训练集大小: 6551, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-12\n",
|
||
"原始训练集大小: 6565\n",
|
||
"划分后的训练集大小: 6565, 验证集大小: 357\n",
|
||
"[100]\ttrain's ndcg@1: 0.9515\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-13\n",
|
||
"原始训练集大小: 6560\n",
|
||
"划分后的训练集大小: 6560, 验证集大小: 298\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-14\n",
|
||
"原始训练集大小: 6550\n",
|
||
"划分后的训练集大小: 6550, 验证集大小: 359\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-15\n",
|
||
"原始训练集大小: 6588\n",
|
||
"划分后的训练集大小: 6588, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.976375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-18\n",
|
||
"原始训练集大小: 6560\n",
|
||
"划分后的训练集大小: 6560, 验证集大小: 284\n",
|
||
"[100]\ttrain's ndcg@1: 0.98125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-19\n",
|
||
"原始训练集大小: 6523\n",
|
||
"划分后的训练集大小: 6523, 验证集大小: 350\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2023-12-20\n",
|
||
"原始训练集大小: 6573\n",
|
||
"划分后的训练集大小: 6573, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-21\n",
|
||
"原始训练集大小: 6553\n",
|
||
"划分后的训练集大小: 6553, 验证集大小: 318\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-22\n",
|
||
"原始训练集大小: 6534\n",
|
||
"划分后的训练集大小: 6534, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-25\n",
|
||
"原始训练集大小: 6586\n",
|
||
"划分后的训练集大小: 6586, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-26\n",
|
||
"原始训练集大小: 6544\n",
|
||
"划分后的训练集大小: 6544, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-27\n",
|
||
"原始训练集大小: 6571\n",
|
||
"划分后的训练集大小: 6571, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.947625\tvalid's ndcg@1: 0.7225\n",
|
||
"最大日期: 2023-12-28\n",
|
||
"原始训练集大小: 6607\n",
|
||
"划分后的训练集大小: 6607, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2023-12-29\n",
|
||
"原始训练集大小: 6568\n",
|
||
"划分后的训练集大小: 6568, 验证集大小: 295\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-01-02\n",
|
||
"原始训练集大小: 6627\n",
|
||
"划分后的训练集大小: 6627, 验证集大小: 373\n",
|
||
"[100]\ttrain's ndcg@1: 0.98125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-03\n",
|
||
"原始训练集大小: 6670\n",
|
||
"划分后的训练集大小: 6670, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.962\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-04\n",
|
||
"原始训练集大小: 6647\n",
|
||
"划分后的训练集大小: 6647, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-05\n",
|
||
"原始训练集大小: 6643\n",
|
||
"划分后的训练集大小: 6643, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-08\n",
|
||
"原始训练集大小: 6649\n",
|
||
"划分后的训练集大小: 6649, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-09\n",
|
||
"原始训练集大小: 6636\n",
|
||
"划分后的训练集大小: 6636, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-10\n",
|
||
"原始训练集大小: 6626\n",
|
||
"划分后的训练集大小: 6626, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.957875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-11\n",
|
||
"原始训练集大小: 6628\n",
|
||
"划分后的训练集大小: 6628, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.968125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-12\n",
|
||
"原始训练集大小: 6601\n",
|
||
"划分后的训练集大小: 6601, 验证集大小: 332\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-01-15\n",
|
||
"原始训练集大小: 6603\n",
|
||
"划分后的训练集大小: 6603, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-16\n",
|
||
"原始训练集大小: 6632\n",
|
||
"划分后的训练集大小: 6632, 验证集大小: 313\n",
|
||
"[100]\ttrain's ndcg@1: 0.957375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-17\n",
|
||
"原始训练集大小: 6647\n",
|
||
"划分后的训练集大小: 6647, 验证集大小: 365\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-18\n",
|
||
"原始训练集大小: 6648\n",
|
||
"划分后的训练集大小: 6648, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-19\n",
|
||
"原始训练集大小: 6646\n",
|
||
"划分后的训练集大小: 6646, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.919125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-22\n",
|
||
"原始训练集大小: 6669\n",
|
||
"划分后的训练集大小: 6669, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-01-23\n",
|
||
"原始训练集大小: 6660\n",
|
||
"划分后的训练集大小: 6660, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-24\n",
|
||
"原始训练集大小: 6649\n",
|
||
"划分后的训练集大小: 6649, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-01-25\n",
|
||
"原始训练集大小: 6649\n",
|
||
"划分后的训练集大小: 6649, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-26\n",
|
||
"原始训练集大小: 6626\n",
|
||
"划分后的训练集大小: 6626, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-01-29\n",
|
||
"原始训练集大小: 6666\n",
|
||
"划分后的训练集大小: 6666, 验证集大小: 335\n",
|
||
"[100]\ttrain's ndcg@1: 0.95275\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-30\n",
|
||
"原始训练集大小: 6636\n",
|
||
"划分后的训练集大小: 6636, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.976125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-01-31\n",
|
||
"原始训练集大小: 6595\n",
|
||
"划分后的训练集大小: 6595, 验证集大小: 298\n",
|
||
"[100]\ttrain's ndcg@1: 0.9335\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-02-01\n",
|
||
"原始训练集大小: 6607\n",
|
||
"划分后的训练集大小: 6607, 验证集大小: 346\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-02\n",
|
||
"原始训练集大小: 6646\n",
|
||
"划分后的训练集大小: 6646, 验证集大小: 364\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-05\n",
|
||
"原始训练集大小: 6645\n",
|
||
"划分后的训练集大小: 6645, 验证集大小: 315\n",
|
||
"[100]\ttrain's ndcg@1: 0.962\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-06\n",
|
||
"原始训练集大小: 6659\n",
|
||
"划分后的训练集大小: 6659, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.920875\tvalid's ndcg@1: 0.64\n",
|
||
"最大日期: 2024-02-07\n",
|
||
"原始训练集大小: 6657\n",
|
||
"划分后的训练集大小: 6657, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.949125\tvalid's ndcg@1: 0.5625\n",
|
||
"最大日期: 2024-02-08\n",
|
||
"原始训练集大小: 6677\n",
|
||
"划分后的训练集大小: 6677, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.941719\tvalid's ndcg@1: 0.224377\n",
|
||
"最大日期: 2024-02-19\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.870884\tvalid's ndcg@1: 0.64\n",
|
||
"最大日期: 2024-02-20\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.938647\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-02-21\n",
|
||
"原始训练集大小: 6708\n",
|
||
"划分后的训练集大小: 6708, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 0.903469\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-02-22\n",
|
||
"原始训练集大小: 6667\n",
|
||
"划分后的训练集大小: 6667, 验证集大小: 324\n",
|
||
"[100]\ttrain's ndcg@1: 0.943663\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-23\n",
|
||
"原始训练集大小: 6691\n",
|
||
"划分后的训练集大小: 6691, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.858945\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-26\n",
|
||
"原始训练集大小: 6709\n",
|
||
"划分后的训练集大小: 6709, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.838375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-02-27\n",
|
||
"原始训练集大小: 6702\n",
|
||
"划分后的训练集大小: 6702, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.88207\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-28\n",
|
||
"原始训练集大小: 6691\n",
|
||
"划分后的训练集大小: 6691, 验证集大小: 318\n",
|
||
"[100]\ttrain's ndcg@1: 0.919707\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-02-29\n",
|
||
"原始训练集大小: 6737\n",
|
||
"划分后的训练集大小: 6737, 验证集大小: 355\n",
|
||
"[100]\ttrain's ndcg@1: 0.841\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-01\n",
|
||
"原始训练集大小: 6721\n",
|
||
"划分后的训练集大小: 6721, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.896375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-04\n",
|
||
"原始训练集大小: 6753\n",
|
||
"划分后的训练集大小: 6753, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.907413\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-05\n",
|
||
"原始训练集大小: 6749\n",
|
||
"划分后的训练集大小: 6749, 验证集大小: 331\n",
|
||
"[100]\ttrain's ndcg@1: 0.88975\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-06\n",
|
||
"原始训练集大小: 6762\n",
|
||
"划分后的训练集大小: 6762, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.892788\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-07\n",
|
||
"原始训练集大小: 6814\n",
|
||
"划分后的训练集大小: 6814, 验证集大小: 350\n",
|
||
"[100]\ttrain's ndcg@1: 0.885288\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-08\n",
|
||
"原始训练集大小: 6771\n",
|
||
"划分后的训练集大小: 6771, 验证集大小: 303\n",
|
||
"[100]\ttrain's ndcg@1: 0.930288\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-11\n",
|
||
"原始训练集大小: 6755\n",
|
||
"划分后的训练集大小: 6755, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.948125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-12\n",
|
||
"原始训练集大小: 6780\n",
|
||
"划分后的训练集大小: 6780, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.910375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-13\n",
|
||
"原始训练集大小: 6752\n",
|
||
"划分后的训练集大小: 6752, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.905522\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-14\n",
|
||
"原始训练集大小: 6745\n",
|
||
"划分后的训练集大小: 6745, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.935163\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-15\n",
|
||
"原始训练集大小: 6760\n",
|
||
"划分后的训练集大小: 6760, 验证集大小: 335\n",
|
||
"[100]\ttrain's ndcg@1: 0.933\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-18\n",
|
||
"原始训练集大小: 6751\n",
|
||
"划分后的训练集大小: 6751, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.9425\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-19\n",
|
||
"原始训练集大小: 6717\n",
|
||
"划分后的训练集大小: 6717, 验证集大小: 307\n",
|
||
"[100]\ttrain's ndcg@1: 0.947125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-20\n",
|
||
"原始训练集大小: 6729\n",
|
||
"划分后的训练集大小: 6729, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.947375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-21\n",
|
||
"原始训练集大小: 6738\n",
|
||
"划分后的训练集大小: 6738, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-22\n",
|
||
"原始训练集大小: 6692\n",
|
||
"划分后的训练集大小: 6692, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.95225\tvalid's ndcg@1: 0.7225\n",
|
||
"最大日期: 2024-03-25\n",
|
||
"原始训练集大小: 6690\n",
|
||
"划分后的训练集大小: 6690, 验证集大小: 332\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-03-26\n",
|
||
"原始训练集大小: 6663\n",
|
||
"划分后的训练集大小: 6663, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-27\n",
|
||
"原始训练集大小: 6705\n",
|
||
"划分后的训练集大小: 6705, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-28\n",
|
||
"原始训练集大小: 6647\n",
|
||
"划分后的训练集大小: 6647, 验证集大小: 297\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-03-29\n",
|
||
"原始训练集大小: 6666\n",
|
||
"划分后的训练集大小: 6666, 验证集大小: 359\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-04-01\n",
|
||
"原始训练集大小: 6640\n",
|
||
"划分后的训练集大小: 6640, 验证集大小: 322\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-02\n",
|
||
"原始训练集大小: 6617\n",
|
||
"划分后的训练集大小: 6617, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-04-03\n",
|
||
"原始训练集大小: 6594\n",
|
||
"划分后的训练集大小: 6594, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.962\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-08\n",
|
||
"原始训练集大小: 6569\n",
|
||
"划分后的训练集大小: 6569, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-04-09\n",
|
||
"原始训练集大小: 6604\n",
|
||
"划分后的训练集大小: 6604, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-04-10\n",
|
||
"原始训练集大小: 6582\n",
|
||
"划分后的训练集大小: 6582, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-11\n",
|
||
"原始训练集大小: 6588\n",
|
||
"划分后的训练集大小: 6588, 验证集大小: 346\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-12\n",
|
||
"原始训练集大小: 6605\n",
|
||
"划分后的训练集大小: 6605, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-15\n",
|
||
"原始训练集大小: 6594\n",
|
||
"划分后的训练集大小: 6594, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-16\n",
|
||
"原始训练集大小: 6562\n",
|
||
"划分后的训练集大小: 6562, 验证集大小: 303\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-17\n",
|
||
"原始训练集大小: 6585\n",
|
||
"划分后的训练集大小: 6585, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.947875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-04-18\n",
|
||
"原始训练集大小: 6625\n",
|
||
"划分后的训练集大小: 6625, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.925\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-19\n",
|
||
"原始训练集大小: 6593\n",
|
||
"划分后的训练集大小: 6593, 验证集大小: 317\n",
|
||
"[100]\ttrain's ndcg@1: 0.9535\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-22\n",
|
||
"原始训练集大小: 6617\n",
|
||
"划分后的训练集大小: 6617, 验证集大小: 357\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-23\n",
|
||
"原始训练集大小: 6675\n",
|
||
"划分后的训练集大小: 6675, 验证集大小: 366\n",
|
||
"[100]\ttrain's ndcg@1: 0.9635\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-24\n",
|
||
"原始训练集大小: 6662\n",
|
||
"划分后的训练集大小: 6662, 验证集大小: 319\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-04-25\n",
|
||
"原始训练集大小: 6681\n",
|
||
"划分后的训练集大小: 6681, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.8925\tvalid's ndcg@1: 0.7225\n",
|
||
"最大日期: 2024-04-26\n",
|
||
"原始训练集大小: 6668\n",
|
||
"划分后的训练集大小: 6668, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.940625\tvalid's ndcg@1: 0.49\n",
|
||
"最大日期: 2024-04-29\n",
|
||
"原始训练集大小: 6714\n",
|
||
"划分后的训练集大小: 6714, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-04-30\n",
|
||
"原始训练集大小: 6699\n",
|
||
"划分后的训练集大小: 6699, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.894\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-06\n",
|
||
"原始训练集大小: 6703\n",
|
||
"划分后的训练集大小: 6703, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-07\n",
|
||
"原始训练集大小: 6733\n",
|
||
"划分后的训练集大小: 6733, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.93525\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-08\n",
|
||
"原始训练集大小: 6753\n",
|
||
"划分后的训练集大小: 6753, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-09\n",
|
||
"原始训练集大小: 6731\n",
|
||
"划分后的训练集大小: 6731, 验证集大小: 303\n",
|
||
"[100]\ttrain's ndcg@1: 0.97175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-10\n",
|
||
"原始训练集大小: 6763\n",
|
||
"划分后的训练集大小: 6763, 验证集大小: 370\n",
|
||
"[100]\ttrain's ndcg@1: 0.894875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-13\n",
|
||
"原始训练集大小: 6786\n",
|
||
"划分后的训练集大小: 6786, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-05-14\n",
|
||
"原始训练集大小: 6780\n",
|
||
"划分后的训练集大小: 6780, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.95225\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-05-15\n",
|
||
"原始训练集大小: 6790\n",
|
||
"划分后的训练集大小: 6790, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.917125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-16\n",
|
||
"原始训练集大小: 6807\n",
|
||
"划分后的训练集大小: 6807, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.913\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-17\n",
|
||
"原始训练集大小: 6886\n",
|
||
"划分后的训练集大小: 6886, 验证集大小: 382\n",
|
||
"[100]\ttrain's ndcg@1: 0.94625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-20\n",
|
||
"原始训练集大小: 6860\n",
|
||
"划分后的训练集大小: 6860, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.950875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-05-21\n",
|
||
"原始训练集大小: 6813\n",
|
||
"划分后的训练集大小: 6813, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.947625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-05-22\n",
|
||
"原始训练集大小: 6880\n",
|
||
"划分后的训练集大小: 6880, 验证集大小: 384\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-23\n",
|
||
"原始训练集大小: 6877\n",
|
||
"划分后的训练集大小: 6877, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-05-24\n",
|
||
"原始训练集大小: 6791\n",
|
||
"划分后的训练集大小: 6791, 验证集大小: 280\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-05-27\n",
|
||
"原始训练集大小: 6854\n",
|
||
"划分后的训练集大小: 6854, 验证集大小: 382\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-28\n",
|
||
"原始训练集大小: 6877\n",
|
||
"划分后的训练集大小: 6877, 验证集大小: 368\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-29\n",
|
||
"原始训练集大小: 6838\n",
|
||
"划分后的训练集大小: 6838, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-05-30\n",
|
||
"原始训练集大小: 6858\n",
|
||
"划分后的训练集大小: 6858, 验证集大小: 363\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-05-31\n",
|
||
"原始训练集大小: 6854\n",
|
||
"划分后的训练集大小: 6854, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.947625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-03\n",
|
||
"原始训练集大小: 6907\n",
|
||
"划分后的训练集大小: 6907, 验证集大小: 379\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-06-04\n",
|
||
"原始训练集大小: 6899\n",
|
||
"划分后的训练集大小: 6899, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-06-05\n",
|
||
"原始训练集大小: 6867\n",
|
||
"划分后的训练集大小: 6867, 验证集大小: 321\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-06-06\n",
|
||
"原始训练集大小: 6950\n",
|
||
"划分后的训练集大小: 6950, 验证集大小: 386\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-07\n",
|
||
"原始训练集大小: 6911\n",
|
||
"划分后的训练集大小: 6911, 验证集大小: 331\n",
|
||
"[100]\ttrain's ndcg@1: 0.943\tvalid's ndcg@1: 0.7225\n",
|
||
"最大日期: 2024-06-11\n",
|
||
"原始训练集大小: 6863\n",
|
||
"划分后的训练集大小: 6863, 验证集大小: 301\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-12\n",
|
||
"原始训练集大小: 6904\n",
|
||
"划分后的训练集大小: 6904, 验证集大小: 381\n",
|
||
"[100]\ttrain's ndcg@1: 0.952\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-06-13\n",
|
||
"原始训练集大小: 6876\n",
|
||
"划分后的训练集大小: 6876, 验证集大小: 315\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-06-14\n",
|
||
"原始训练集大小: 6876\n",
|
||
"划分后的训练集大小: 6876, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.97075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-17\n",
|
||
"原始训练集大小: 6845\n",
|
||
"划分后的训练集大小: 6845, 验证集大小: 351\n",
|
||
"[100]\ttrain's ndcg@1: 0.947375\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-06-18\n",
|
||
"原始训练集大小: 6848\n",
|
||
"划分后的训练集大小: 6848, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-19\n",
|
||
"原始训练集大小: 6946\n",
|
||
"划分后的训练集大小: 6946, 验证集大小: 398\n",
|
||
"[100]\ttrain's ndcg@1: 0.952\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-20\n",
|
||
"原始训练集大小: 6866\n",
|
||
"划分后的训练集大小: 6866, 验证集大小: 304\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-21\n",
|
||
"原始训练集大小: 6860\n",
|
||
"划分后的训练集大小: 6860, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-24\n",
|
||
"原始训练集大小: 6960\n",
|
||
"划分后的训练集大小: 6960, 验证集大小: 380\n",
|
||
"[100]\ttrain's ndcg@1: 0.93475\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-25\n",
|
||
"原始训练集大小: 6902\n",
|
||
"划分后的训练集大小: 6902, 验证集大小: 324\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-06-26\n",
|
||
"原始训练集大小: 6868\n",
|
||
"划分后的训练集大小: 6868, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-27\n",
|
||
"原始训练集大小: 6921\n",
|
||
"划分后的训练集大小: 6921, 验证集大小: 361\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-06-28\n",
|
||
"原始训练集大小: 6897\n",
|
||
"划分后的训练集大小: 6897, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.9435\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-07-01\n",
|
||
"原始训练集大小: 6877\n",
|
||
"划分后的训练集大小: 6877, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.953\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-02\n",
|
||
"原始训练集大小: 6869\n",
|
||
"划分后的训练集大小: 6869, 验证集大小: 371\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-03\n",
|
||
"原始训练集大小: 6844\n",
|
||
"划分后的训练集大小: 6844, 验证集大小: 305\n",
|
||
"[100]\ttrain's ndcg@1: 0.947125\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-07-04\n",
|
||
"原始训练集大小: 6917\n",
|
||
"划分后的训练集大小: 6917, 验证集大小: 394\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-07-05\n",
|
||
"原始训练集大小: 6850\n",
|
||
"划分后的训练集大小: 6850, 验证集大小: 319\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-07-08\n",
|
||
"原始训练集大小: 6848\n",
|
||
"划分后的训练集大小: 6848, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-09\n",
|
||
"原始训练集大小: 6940\n",
|
||
"划分后的训练集大小: 6940, 验证集大小: 393\n",
|
||
"[100]\ttrain's ndcg@1: 0.956875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-10\n",
|
||
"原始训练集大小: 6855\n",
|
||
"划分后的训练集大小: 6855, 验证集大小: 296\n",
|
||
"[100]\ttrain's ndcg@1: 0.97175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-11\n",
|
||
"原始训练集大小: 6888\n",
|
||
"划分后的训练集大小: 6888, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-12\n",
|
||
"原始训练集大小: 6896\n",
|
||
"划分后的训练集大小: 6896, 验证集大小: 352\n",
|
||
"[100]\ttrain's ndcg@1: 0.91725\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-07-15\n",
|
||
"原始训练集大小: 6879\n",
|
||
"划分后的训练集大小: 6879, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.97325\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-16\n",
|
||
"原始训练集大小: 6851\n",
|
||
"划分后的训练集大小: 6851, 验证集大小: 302\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-07-17\n",
|
||
"原始训练集大小: 6827\n",
|
||
"划分后的训练集大小: 6827, 验证集大小: 374\n",
|
||
"[100]\ttrain's ndcg@1: 0.956375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-18\n",
|
||
"原始训练集大小: 6863\n",
|
||
"划分后的训练集大小: 6863, 验证集大小: 340\n",
|
||
"[100]\ttrain's ndcg@1: 0.953\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-19\n",
|
||
"原始训练集大小: 6868\n",
|
||
"划分后的训练集大小: 6868, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-22\n",
|
||
"原始训练集大小: 6832\n",
|
||
"划分后的训练集大小: 6832, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.968375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-23\n",
|
||
"原始训练集大小: 6846\n",
|
||
"划分后的训练集大小: 6846, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-24\n",
|
||
"原始训练集大小: 6888\n",
|
||
"划分后的训练集大小: 6888, 验证集大小: 376\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-25\n",
|
||
"原始训练集大小: 6824\n",
|
||
"划分后的训练集大小: 6824, 验证集大小: 297\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-26\n",
|
||
"原始训练集大小: 6839\n",
|
||
"划分后的训练集大小: 6839, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-29\n",
|
||
"原始训练集大小: 6889\n",
|
||
"划分后的训练集大小: 6889, 验证集大小: 370\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-30\n",
|
||
"原始训练集大小: 6855\n",
|
||
"划分后的训练集大小: 6855, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-07-31\n",
|
||
"原始训练集大小: 6856\n",
|
||
"划分后的训练集大小: 6856, 验证集大小: 306\n",
|
||
"[100]\ttrain's ndcg@1: 0.96275\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-01\n",
|
||
"原始训练集大小: 6841\n",
|
||
"划分后的训练集大小: 6841, 验证集大小: 379\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-02\n",
|
||
"原始训练集大小: 6847\n",
|
||
"划分后的训练集大小: 6847, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-08-05\n",
|
||
"原始训练集大小: 6850\n",
|
||
"划分后的训练集大小: 6850, 验证集大小: 332\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-06\n",
|
||
"原始训练集大小: 6811\n",
|
||
"划分后的训练集大小: 6811, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-07\n",
|
||
"原始训练集大小: 6849\n",
|
||
"划分后的训练集大小: 6849, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.97225\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-08\n",
|
||
"原始训练集大小: 6869\n",
|
||
"划分后的训练集大小: 6869, 验证集大小: 368\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-09\n",
|
||
"原始训练集大小: 6837\n",
|
||
"划分后的训练集大小: 6837, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-12\n",
|
||
"原始训练集大小: 6834\n",
|
||
"划分后的训练集大小: 6834, 验证集大小: 331\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-13\n",
|
||
"原始训练集大小: 6893\n",
|
||
"划分后的训练集大小: 6893, 验证集大小: 361\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-08-14\n",
|
||
"原始训练集大小: 6855\n",
|
||
"划分后的训练集大小: 6855, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-15\n",
|
||
"原始训练集大小: 6840\n",
|
||
"划分后的训练集大小: 6840, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 1\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-16\n",
|
||
"原始训练集大小: 6847\n",
|
||
"划分后的训练集大小: 6847, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-19\n",
|
||
"原始训练集大小: 6872\n",
|
||
"划分后的训练集大小: 6872, 验证集大小: 369\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-20\n",
|
||
"原始训练集大小: 6834\n",
|
||
"划分后的训练集大小: 6834, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-21\n",
|
||
"原始训练集大小: 6833\n",
|
||
"划分后的训练集大小: 6833, 验证集大小: 375\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-22\n",
|
||
"原始训练集大小: 6880\n",
|
||
"划分后的训练集大小: 6880, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-23\n",
|
||
"原始训练集大小: 6853\n",
|
||
"划分后的训练集大小: 6853, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.981\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-26\n",
|
||
"原始训练集大小: 6837\n",
|
||
"划分后的训练集大小: 6837, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-08-27\n",
|
||
"原始训练集大小: 6830\n",
|
||
"划分后的训练集大小: 6830, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-08-28\n",
|
||
"原始训练集大小: 6880\n",
|
||
"划分后的训练集大小: 6880, 验证集大小: 356\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-08-29\n",
|
||
"原始训练集大小: 6851\n",
|
||
"划分后的训练集大小: 6851, 验证集大小: 350\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-08-30\n",
|
||
"原始训练集大小: 6837\n",
|
||
"划分后的训练集大小: 6837, 验证集大小: 311\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-02\n",
|
||
"原始训练集大小: 6849\n",
|
||
"划分后的训练集大小: 6849, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-03\n",
|
||
"原始训练集大小: 6855\n",
|
||
"划分后的训练集大小: 6855, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.94325\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-09-04\n",
|
||
"原始训练集大小: 6806\n",
|
||
"划分后的训练集大小: 6806, 验证集大小: 285\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-05\n",
|
||
"原始训练集大小: 6817\n",
|
||
"划分后的训练集大小: 6817, 验证集大小: 379\n",
|
||
"[100]\ttrain's ndcg@1: 0.937625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-09-06\n",
|
||
"原始训练集大小: 6860\n",
|
||
"划分后的训练集大小: 6860, 验证集大小: 363\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-09\n",
|
||
"原始训练集大小: 6838\n",
|
||
"划分后的训练集大小: 6838, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-10\n",
|
||
"原始训练集大小: 6845\n",
|
||
"划分后的训练集大小: 6845, 验证集大小: 368\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-11\n",
|
||
"原始训练集大小: 6848\n",
|
||
"划分后的训练集大小: 6848, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-12\n",
|
||
"原始训练集大小: 6883\n",
|
||
"划分后的训练集大小: 6883, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-13\n",
|
||
"原始训练集大小: 6857\n",
|
||
"划分后的训练集大小: 6857, 验证集大小: 334\n",
|
||
"[100]\ttrain's ndcg@1: 0.957375\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-09-18\n",
|
||
"原始训练集大小: 6814\n",
|
||
"划分后的训练集大小: 6814, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-19\n",
|
||
"原始训练集大小: 6888\n",
|
||
"划分后的训练集大小: 6888, 验证集大小: 374\n",
|
||
"[100]\ttrain's ndcg@1: 0.967375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-20\n",
|
||
"原始训练集大小: 6852\n",
|
||
"划分后的训练集大小: 6852, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-23\n",
|
||
"原始训练集大小: 6799\n",
|
||
"划分后的训练集大小: 6799, 验证集大小: 291\n",
|
||
"[100]\ttrain's ndcg@1: 0.953\tvalid's ndcg@1: 0.64\n",
|
||
"最大日期: 2024-09-24\n",
|
||
"原始训练集大小: 6825\n",
|
||
"划分后的训练集大小: 6825, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-09-25\n",
|
||
"原始训练集大小: 6841\n",
|
||
"划分后的训练集大小: 6841, 验证集大小: 370\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-26\n",
|
||
"原始训练集大小: 6782\n",
|
||
"划分后的训练集大小: 6782, 验证集大小: 271\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-09-27\n",
|
||
"原始训练集大小: 6800\n",
|
||
"划分后的训练集大小: 6800, 验证集大小: 374\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-09-30\n",
|
||
"原始训练集大小: 6786\n",
|
||
"划分后的训练集大小: 6786, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.957625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-08\n",
|
||
"原始训练集大小: 6757\n",
|
||
"划分后的训练集大小: 6757, 验证集大小: 282\n",
|
||
"[100]\ttrain's ndcg@1: 0.947875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-09\n",
|
||
"原始训练集大小: 6616\n",
|
||
"划分后的训练集大小: 6616, 验证集大小: 203\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-10\n",
|
||
"原始训练集大小: 6577\n",
|
||
"划分后的训练集大小: 6577, 验证集大小: 321\n",
|
||
"[100]\ttrain's ndcg@1: 0.95225\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-11\n",
|
||
"原始训练集大小: 6635\n",
|
||
"划分后的训练集大小: 6635, 验证集大小: 343\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-14\n",
|
||
"原始训练集大小: 6589\n",
|
||
"划分后的训练集大小: 6589, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.952\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-15\n",
|
||
"原始训练集大小: 6535\n",
|
||
"划分后的训练集大小: 6535, 验证集大小: 309\n",
|
||
"[100]\ttrain's ndcg@1: 0.9345\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-10-16\n",
|
||
"原始训练集大小: 6594\n",
|
||
"划分后的训练集大小: 6594, 验证集大小: 368\n",
|
||
"[100]\ttrain's ndcg@1: 0.957875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-10-17\n",
|
||
"原始训练集大小: 6546\n",
|
||
"划分后的训练集大小: 6546, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.9525\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-18\n",
|
||
"原始训练集大小: 6566\n",
|
||
"划分后的训练集大小: 6566, 验证集大小: 359\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-10-21\n",
|
||
"原始训练集大小: 6535\n",
|
||
"划分后的训练集大小: 6535, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.938625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-10-22\n",
|
||
"原始训练集大小: 6520\n",
|
||
"划分后的训练集大小: 6520, 验证集大小: 319\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-23\n",
|
||
"原始训练集大小: 6530\n",
|
||
"划分后的训练集大小: 6530, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-10-24\n",
|
||
"原始训练集大小: 6479\n",
|
||
"划分后的训练集大小: 6479, 验证集大小: 323\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-25\n",
|
||
"原始训练集大小: 6481\n",
|
||
"划分后的训练集大小: 6481, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-28\n",
|
||
"原始训练集大小: 6528\n",
|
||
"划分后的训练集大小: 6528, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-29\n",
|
||
"原始训练集大小: 6499\n",
|
||
"划分后的训练集大小: 6499, 验证集大小: 324\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-30\n",
|
||
"原始训练集大小: 6430\n",
|
||
"划分后的训练集大小: 6430, 验证集大小: 301\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-10-31\n",
|
||
"原始训练集大小: 6496\n",
|
||
"划分后的训练集大小: 6496, 验证集大小: 337\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-01\n",
|
||
"原始训练集大小: 6461\n",
|
||
"划分后的训练集大小: 6461, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.97225\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-04\n",
|
||
"原始训练集大小: 6447\n",
|
||
"划分后的训练集大小: 6447, 验证集大小: 322\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-05\n",
|
||
"原始训练集大小: 6494\n",
|
||
"划分后的训练集大小: 6494, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-06\n",
|
||
"原始训练集大小: 6638\n",
|
||
"划分后的训练集大小: 6638, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-11-07\n",
|
||
"原始训练集大小: 6617\n",
|
||
"划分后的训练集大小: 6617, 验证集大小: 300\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-08\n",
|
||
"原始训练集大小: 6586\n",
|
||
"划分后的训练集大小: 6586, 验证集大小: 312\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-11-11\n",
|
||
"原始训练集大小: 6501\n",
|
||
"划分后的训练集大小: 6501, 验证集大小: 248\n",
|
||
"[100]\ttrain's ndcg@1: 0.966625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-12\n",
|
||
"原始训练集大小: 6459\n",
|
||
"划分后的训练集大小: 6459, 验证集大小: 267\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-13\n",
|
||
"原始训练集大小: 6411\n",
|
||
"划分后的训练集大小: 6411, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.956625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-14\n",
|
||
"原始训练集大小: 6395\n",
|
||
"划分后的训练集大小: 6395, 验证集大小: 304\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-11-15\n",
|
||
"原始训练集大小: 6366\n",
|
||
"划分后的训练集大小: 6366, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.966875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-18\n",
|
||
"原始训练集大小: 6389\n",
|
||
"划分后的训练集大小: 6389, 验证集大小: 352\n",
|
||
"[100]\ttrain's ndcg@1: 0.957125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-11-19\n",
|
||
"原始训练集大小: 6400\n",
|
||
"划分后的训练集大小: 6400, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.937875\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-11-20\n",
|
||
"原始训练集大小: 6409\n",
|
||
"划分后的训练集大小: 6409, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.930625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-21\n",
|
||
"原始训练集大小: 6412\n",
|
||
"划分后的训练集大小: 6412, 验证集大小: 326\n",
|
||
"[100]\ttrain's ndcg@1: 0.947875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-22\n",
|
||
"原始训练集大小: 6423\n",
|
||
"划分后的训练集大小: 6423, 验证集大小: 352\n",
|
||
"[100]\ttrain's ndcg@1: 0.965875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-25\n",
|
||
"原始训练集大小: 6433\n",
|
||
"划分后的训练集大小: 6433, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.902375\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2024-11-26\n",
|
||
"原始训练集大小: 6422\n",
|
||
"划分后的训练集大小: 6422, 验证集大小: 313\n",
|
||
"[100]\ttrain's ndcg@1: 0.957375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-27\n",
|
||
"原始训练集大小: 6466\n",
|
||
"划分后的训练集大小: 6466, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-11-28\n",
|
||
"原始训练集大小: 6476\n",
|
||
"划分后的训练集大小: 6476, 验证集大小: 347\n",
|
||
"[100]\ttrain's ndcg@1: 0.914\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-11-29\n",
|
||
"原始训练集大小: 6458\n",
|
||
"划分后的训练集大小: 6458, 验证集大小: 321\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-02\n",
|
||
"原始训练集大小: 6474\n",
|
||
"划分后的训练集大小: 6474, 验证集大小: 338\n",
|
||
"[100]\ttrain's ndcg@1: 0.924\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-03\n",
|
||
"原始训练集大小: 6505\n",
|
||
"划分后的训练集大小: 6505, 验证集大小: 360\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-04\n",
|
||
"原始训练集大小: 6463\n",
|
||
"划分后的训练集大小: 6463, 验证集大小: 305\n",
|
||
"[100]\ttrain's ndcg@1: 0.915\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-12-05\n",
|
||
"原始训练集大小: 6507\n",
|
||
"划分后的训练集大小: 6507, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.938375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-06\n",
|
||
"原始训练集大小: 6520\n",
|
||
"划分后的训练集大小: 6520, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.9525\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-09\n",
|
||
"原始训练集大小: 6592\n",
|
||
"划分后的训练集大小: 6592, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.938125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2024-12-10\n",
|
||
"原始训练集大小: 6667\n",
|
||
"划分后的训练集大小: 6667, 验证集大小: 342\n",
|
||
"[100]\ttrain's ndcg@1: 0.947375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-11\n",
|
||
"原始训练集大小: 6675\n",
|
||
"划分后的训练集大小: 6675, 验证集大小: 328\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-12\n",
|
||
"原始训练集大小: 6707\n",
|
||
"划分后的训练集大小: 6707, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.9245\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-13\n",
|
||
"原始训练集大小: 6726\n",
|
||
"划分后的训练集大小: 6726, 验证集大小: 349\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-16\n",
|
||
"原始训练集大小: 6692\n",
|
||
"划分后的训练集大小: 6692, 验证集大小: 318\n",
|
||
"[100]\ttrain's ndcg@1: 0.94425\tvalid's ndcg@1: 0.5625\n",
|
||
"最大日期: 2024-12-17\n",
|
||
"原始训练集大小: 6706\n",
|
||
"划分后的训练集大小: 6706, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.948375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-18\n",
|
||
"原始训练集大小: 6707\n",
|
||
"划分后的训练集大小: 6707, 验证集大小: 346\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-19\n",
|
||
"原始训练集大小: 6694\n",
|
||
"划分后的训练集大小: 6694, 验证集大小: 313\n",
|
||
"[100]\ttrain's ndcg@1: 0.965875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-20\n",
|
||
"原始训练集大小: 6687\n",
|
||
"划分后的训练集大小: 6687, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.929875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-23\n",
|
||
"原始训练集大小: 6691\n",
|
||
"划分后的训练集大小: 6691, 验证集大小: 352\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-24\n",
|
||
"原始训练集大小: 6709\n",
|
||
"划分后的训练集大小: 6709, 验证集大小: 331\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-25\n",
|
||
"原始训练集大小: 6721\n",
|
||
"划分后的训练集大小: 6721, 验证集大小: 357\n",
|
||
"[100]\ttrain's ndcg@1: 0.956375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-26\n",
|
||
"原始训练集大小: 6696\n",
|
||
"划分后的训练集大小: 6696, 验证集大小: 322\n",
|
||
"[100]\ttrain's ndcg@1: 0.981\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-27\n",
|
||
"原始训练集大小: 6691\n",
|
||
"划分后的训练集大小: 6691, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-30\n",
|
||
"原始训练集大小: 6703\n",
|
||
"划分后的训练集大小: 6703, 验证集大小: 350\n",
|
||
"[100]\ttrain's ndcg@1: 0.957375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2024-12-31\n",
|
||
"原始训练集大小: 6696\n",
|
||
"划分后的训练集大小: 6696, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-02\n",
|
||
"原始训练集大小: 6707\n",
|
||
"划分后的训练集大小: 6707, 验证集大小: 316\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-03\n",
|
||
"原始训练集大小: 6725\n",
|
||
"划分后的训练集大小: 6725, 验证集大小: 362\n",
|
||
"[100]\ttrain's ndcg@1: 0.96175\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2025-01-06\n",
|
||
"原始训练集大小: 6742\n",
|
||
"划分后的训练集大小: 6742, 验证集大小: 342\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-07\n",
|
||
"原始训练集大小: 6742\n",
|
||
"划分后的训练集大小: 6742, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.97075\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-01-08\n",
|
||
"原始训练集大小: 6768\n",
|
||
"划分后的训练集大小: 6768, 验证集大小: 368\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-09\n",
|
||
"原始训练集大小: 6757\n",
|
||
"划分后的训练集大小: 6757, 验证集大小: 317\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-10\n",
|
||
"原始训练集大小: 6756\n",
|
||
"划分后的训练集大小: 6756, 验证集大小: 335\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-13\n",
|
||
"原始训练集大小: 6766\n",
|
||
"划分后的训练集大小: 6766, 验证集大小: 359\n",
|
||
"[100]\ttrain's ndcg@1: 0.981\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-14\n",
|
||
"原始训练集大小: 6732\n",
|
||
"划分后的训练集大小: 6732, 验证集大小: 284\n",
|
||
"[100]\ttrain's ndcg@1: 0.96125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-15\n",
|
||
"原始训练集大小: 6752\n",
|
||
"划分后的训练集大小: 6752, 验证集大小: 364\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-16\n",
|
||
"原始训练集大小: 6731\n",
|
||
"划分后的训练集大小: 6731, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-17\n",
|
||
"原始训练集大小: 6720\n",
|
||
"划分后的训练集大小: 6720, 验证集大小: 302\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-20\n",
|
||
"原始训练集大小: 6729\n",
|
||
"划分后的训练集大小: 6729, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.97125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-21\n",
|
||
"原始训练集大小: 6707\n",
|
||
"划分后的训练集大小: 6707, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-22\n",
|
||
"原始训练集大小: 6705\n",
|
||
"划分后的训练集大小: 6705, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-23\n",
|
||
"原始训练集大小: 6692\n",
|
||
"划分后的训练集大小: 6692, 验证集大小: 344\n",
|
||
"[100]\ttrain's ndcg@1: 0.995125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-24\n",
|
||
"原始训练集大小: 6690\n",
|
||
"划分后的训练集大小: 6690, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.9715\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-01-27\n",
|
||
"原始训练集大小: 6704\n",
|
||
"划分后的训练集大小: 6704, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.976375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-02-05\n",
|
||
"原始训练集大小: 6708\n",
|
||
"划分后的训练集大小: 6708, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-06\n",
|
||
"原始训练集大小: 6675\n",
|
||
"划分后的训练集大小: 6675, 验证集大小: 320\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-02-07\n",
|
||
"原始训练集大小: 6704\n",
|
||
"划分后的训练集大小: 6704, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.967125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-10\n",
|
||
"原始训练集大小: 6690\n",
|
||
"划分后的训练集大小: 6690, 验证集大小: 348\n",
|
||
"[100]\ttrain's ndcg@1: 0.9535\tvalid's ndcg@1: 0.7225\n",
|
||
"最大日期: 2025-02-11\n",
|
||
"原始训练集大小: 6673\n",
|
||
"划分后的训练集大小: 6673, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.985375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-12\n",
|
||
"原始训练集大小: 6686\n",
|
||
"划分后的训练集大小: 6686, 验证集大小: 333\n",
|
||
"[100]\ttrain's ndcg@1: 0.975625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-13\n",
|
||
"原始训练集大小: 6675\n",
|
||
"划分后的训练集大小: 6675, 验证集大小: 357\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-14\n",
|
||
"原始训练集大小: 6666\n",
|
||
"划分后的训练集大小: 6666, 验证集大小: 308\n",
|
||
"[100]\ttrain's ndcg@1: 0.976375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-17\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 353\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-18\n",
|
||
"原始训练集大小: 6666\n",
|
||
"划分后的训练集大小: 6666, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-19\n",
|
||
"原始训练集大小: 6705\n",
|
||
"划分后的训练集大小: 6705, 验证集大小: 323\n",
|
||
"[100]\ttrain's ndcg@1: 0.99025\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-20\n",
|
||
"原始训练集大小: 6686\n",
|
||
"划分后的训练集大小: 6686, 验证集大小: 345\n",
|
||
"[100]\ttrain's ndcg@1: 0.965875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-21\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 323\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-24\n",
|
||
"原始训练集大小: 6714\n",
|
||
"划分后的训练集大小: 6714, 验证集大小: 332\n",
|
||
"[100]\ttrain's ndcg@1: 0.967375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-25\n",
|
||
"原始训练集大小: 6701\n",
|
||
"划分后的训练集大小: 6701, 验证集大小: 341\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-26\n",
|
||
"原始训练集大小: 6684\n",
|
||
"划分后的训练集大小: 6684, 验证集大小: 313\n",
|
||
"[100]\ttrain's ndcg@1: 0.985625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-02-27\n",
|
||
"原始训练集大小: 6716\n",
|
||
"划分后的训练集大小: 6716, 验证集大小: 361\n",
|
||
"[100]\ttrain's ndcg@1: 0.966125\tvalid's ndcg@1: 0.81\n",
|
||
"最大日期: 2025-02-28\n",
|
||
"原始训练集大小: 6711\n",
|
||
"划分后的训练集大小: 6711, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.947375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-03-03\n",
|
||
"原始训练集大小: 6708\n",
|
||
"划分后的训练集大小: 6708, 验证集大小: 317\n",
|
||
"[100]\ttrain's ndcg@1: 0.957125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-04\n",
|
||
"原始训练集大小: 6729\n",
|
||
"划分后的训练集大小: 6729, 验证集大小: 351\n",
|
||
"[100]\ttrain's ndcg@1: 0.94525\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-05\n",
|
||
"原始训练集大小: 6704\n",
|
||
"划分后的训练集大小: 6704, 验证集大小: 329\n",
|
||
"[100]\ttrain's ndcg@1: 0.957125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-06\n",
|
||
"原始训练集大小: 6709\n",
|
||
"划分后的训练集大小: 6709, 验证集大小: 325\n",
|
||
"[100]\ttrain's ndcg@1: 0.953\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-07\n",
|
||
"原始训练集大小: 6703\n",
|
||
"划分后的训练集大小: 6703, 验证集大小: 339\n",
|
||
"[100]\ttrain's ndcg@1: 0.950125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-10\n",
|
||
"原始训练集大小: 6705\n",
|
||
"划分后的训练集大小: 6705, 验证集大小: 350\n",
|
||
"[100]\ttrain's ndcg@1: 0.9615\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-11\n",
|
||
"原始训练集大小: 6715\n",
|
||
"划分后的训练集大小: 6715, 验证集大小: 335\n",
|
||
"[100]\ttrain's ndcg@1: 0.932125\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-03-12\n",
|
||
"原始训练集大小: 6712\n",
|
||
"划分后的训练集大小: 6712, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.975875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-13\n",
|
||
"原始训练集大小: 6691\n",
|
||
"划分后的训练集大小: 6691, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.9435\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-14\n",
|
||
"原始训练集大小: 6704\n",
|
||
"划分后的训练集大小: 6704, 验证集大小: 321\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-17\n",
|
||
"原始训练集大小: 6709\n",
|
||
"划分后的训练集大小: 6709, 验证集大小: 358\n",
|
||
"[100]\ttrain's ndcg@1: 0.959875\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-18\n",
|
||
"原始训练集大小: 6685\n",
|
||
"划分后的训练集大小: 6685, 验证集大小: 317\n",
|
||
"[100]\ttrain's ndcg@1: 0.947375\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-19\n",
|
||
"原始训练集大小: 6697\n",
|
||
"划分后的训练集大小: 6697, 验证集大小: 335\n",
|
||
"[100]\ttrain's ndcg@1: 0.97225\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-03-20\n",
|
||
"原始训练集大小: 6698\n",
|
||
"划分后的训练集大小: 6698, 验证集大小: 346\n",
|
||
"[100]\ttrain's ndcg@1: 0.966625\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-21\n",
|
||
"原始训练集大小: 6697\n",
|
||
"划分后的训练集大小: 6697, 验证集大小: 322\n",
|
||
"[100]\ttrain's ndcg@1: 0.950125\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-24\n",
|
||
"原始训练集大小: 6701\n",
|
||
"划分后的训练集大小: 6701, 验证集大小: 336\n",
|
||
"[100]\ttrain's ndcg@1: 0.971\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-25\n",
|
||
"原始训练集大小: 6714\n",
|
||
"划分后的训练集大小: 6714, 验证集大小: 354\n",
|
||
"[100]\ttrain's ndcg@1: 0.966375\tvalid's ndcg@1: 0.9025\n",
|
||
"最大日期: 2025-03-26\n",
|
||
"原始训练集大小: 6731\n",
|
||
"划分后的训练集大小: 6731, 验证集大小: 330\n",
|
||
"[100]\ttrain's ndcg@1: 0.9805\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-27\n",
|
||
"原始训练集大小: 6697\n",
|
||
"划分后的训练集大小: 6697, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.98075\tvalid's ndcg@1: 1\n",
|
||
"最大日期: 2025-03-28\n",
|
||
"原始训练集大小: 6358\n",
|
||
"划分后的训练集大小: 6358, 验证集大小: 327\n",
|
||
"[100]\ttrain's ndcg@1: 0.887237\tvalid's ndcg@1: 0.9025\n"
|
||
]
|
||
}
|
||
],
|
||
"execution_count": 48
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "10f15e935aa02a34",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:58:02.865185Z",
|
||
"start_time": "2025-04-04T15:58:02.605106Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"print(df[df['ts_code'] == '000001.SZ'].tail(1)[['act_factor1', 'act_factor2']])\n",
|
||
"print('finish')"
|
||
],
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" act_factor1 act_factor2\n",
|
||
"5115129 -0.222482 -0.256946\n",
|
||
"finish\n"
|
||
]
|
||
}
|
||
],
|
||
"execution_count": 49
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"id": "0dc75517-c857-4f1d-8815-e807400a6d33",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:58:04.052383Z",
|
||
"start_time": "2025-04-04T15:58:02.926348Z"
|
||
}
|
||
},
|
||
"source": [
|
||
"train_data = pdf[filter_index & (pdf['trade_date'] == '2023-01-03')]\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",
|
||
"print(len(train_data))\n"
|
||
],
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"384\n"
|
||
]
|
||
}
|
||
],
|
||
"execution_count": 50
|
||
},
|
||
{
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-04T15:58:04.071469Z",
|
||
"start_time": "2025-04-04T15:58:04.052383Z"
|
||
}
|
||
},
|
||
"cell_type": "code",
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"def analyze_nan_factors(df, factor_columns):\n",
|
||
" \"\"\"\n",
|
||
" 分析 DataFrame 中指定因子列的 NaN 值情况。\n",
|
||
"\n",
|
||
" Args:\n",
|
||
" df (pd.DataFrame): 包含因子数据的 DataFrame。\n",
|
||
" factor_columns (list): 包含因子列名的列表。\n",
|
||
" \"\"\"\n",
|
||
"\n",
|
||
" print(\"### 各因子 NaN 值占比 ###\")\n",
|
||
" nan_percentage = df[factor_columns].isnull().sum() / len(df) * 100\n",
|
||
" print(nan_percentage.sort_values(ascending=False))\n",
|
||
" print(\"\\n\")\n",
|
||
"\n",
|
||
" print(\"### 包含 NaN 值最多的前 5 个因子 ###\")\n",
|
||
" top_nan_factors = nan_percentage[nan_percentage > 0].sort_values(ascending=False).head(5)\n",
|
||
" print(top_nan_factors)\n",
|
||
" print(\"\\n\")\n",
|
||
"\n",
|
||
" if not top_nan_factors.empty:\n",
|
||
" for factor in top_nan_factors.index:\n",
|
||
" print(f\"### 因子 '{factor}' 的 NaN 值分析 ###\")\n",
|
||
"\n",
|
||
" # 按交易日期分组，计算每日 NaN 值数量\n",
|
||
" nan_by_date = df.groupby('trade_date')[factor].apply(lambda x: x.isnull().sum())\n",
|
||
" print(\"\\n每日 NaN 值数量:\")\n",
|
||
" print(nan_by_date.sort_values(ascending=False).head())\n",
|
||
"\n",
|
||
" # # 按股票代码分组，计算每只股票 NaN 值数量\n",
|
||
" # nan_by_stock = df.groupby('ts_code')[factor].apply(lambda x: x.isnull().sum())\n",
|
||
" # print(\"\\n每只股票 NaN 值数量:\")\n",
|
||
" # print(nan_by_stock.sort_values(ascending=False).head())\n",
|
||
"\n",
|
||
" print(\"-\" * 30)\n",
|
||
" print(\"\\n\")\n",
|
||
"\n",
|
||
"# 假设您的 DataFrame 名称是 pdf，并且您已经定义了 feature_columns\n",
|
||
"if 'pdf' in locals() and 'feature_columns' in locals():\n",
|
||
" analyze_nan_factors(train_data.copy(), feature_columns)\n",
|
||
"else:\n",
|
||
" print(\"请确保您的 DataFrame 名称为 'pdf' 且因子列名列表为 'feature_columns' 后再运行代码。\")"
|
||
],
|
||
"id": "53ce0624ed8e3123",
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"### 各因子 NaN 值占比 ###\n",
|
||
"mv_growth 2.864583\n",
|
||
"industry_rank_act_factor3 0.781250\n",
|
||
"industry_act_factor2 0.781250\n",
|
||
"std_return_90 - std_return_90_2 0.781250\n",
|
||
"industry_obv 0.781250\n",
|
||
" ... \n",
|
||
"cat_vol_spike 0.000000\n",
|
||
"up 0.000000\n",
|
||
"down 0.000000\n",
|
||
"obv-maobv_6 0.000000\n",
|
||
"vol 0.000000\n",
|
||
"Length: 88, dtype: float64\n",
|
||
"\n",
|
||
"\n",
|
||
"### 包含 NaN 值最多的前 5 个因子 ###\n",
|
||
"mv_growth 2.864583\n",
|
||
"industry_rank_act_factor3 0.781250\n",
|
||
"industry_obv 0.781250\n",
|
||
"industry_rank_act_factor2 0.781250\n",
|
||
"industry_rank_act_factor1 0.781250\n",
|
||
"dtype: float64\n",
|
||
"\n",
|
||
"\n",
|
||
"### 因子 'mv_growth' 的 NaN 值分析 ###\n",
|
||
"\n",
|
||
"每日 NaN 值数量:\n",
|
||
"trade_date\n",
|
||
"2023-01-03 11\n",
|
||
"Name: mv_growth, dtype: int64\n",
|
||
"------------------------------\n",
|
||
"\n",
|
||
"\n",
|
||
"### 因子 'industry_rank_act_factor3' 的 NaN 值分析 ###\n",
|
||
"\n",
|
||
"每日 NaN 值数量:\n",
|
||
"trade_date\n",
|
||
"2023-01-03 3\n",
|
||
"Name: industry_rank_act_factor3, dtype: int64\n",
|
||
"------------------------------\n",
|
||
"\n",
|
||
"\n",
|
||
"### 因子 'industry_obv' 的 NaN 值分析 ###\n",
|
||
"\n",
|
||
"每日 NaN 值数量:\n",
|
||
"trade_date\n",
|
||
"2023-01-03 3\n",
|
||
"Name: industry_obv, dtype: int64\n",
|
||
"------------------------------\n",
|
||
"\n",
|
||
"\n",
|
||
"### 因子 'industry_rank_act_factor2' 的 NaN 值分析 ###\n",
|
||
"\n",
|
||
"每日 NaN 值数量:\n",
|
||
"trade_date\n",
|
||
"2023-01-03 3\n",
|
||
"Name: industry_rank_act_factor2, dtype: int64\n",
|
||
"------------------------------\n",
|
||
"\n",
|
||
"\n",
|
||
"### 因子 'industry_rank_act_factor1' 的 NaN 值分析 ###\n",
|
||
"\n",
|
||
"每日 NaN 值数量:\n",
|
||
"trade_date\n",
|
||
"2023-01-03 3\n",
|
||
"Name: industry_rank_act_factor1, dtype: int64\n",
|
||
"------------------------------\n",
|
||
"\n",
|
||
"\n"
|
||
]
|
||
}
|
||
],
|
||
"execution_count": 51
|
||
}
|
||
],
|
||
"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
|
||
}
|