liaozhaorun/NewStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
36a6d22776c0cca55a3e4a618469d748cfcc5453
NewStock/code/train/Rank.ipynb

1686 lines
202 KiB
Plaintext
Raw Normal View History

(data leak)勉强赚钱
2025-03-27 23:07:44 +08:00
{
"cells": [
{
"cell_type": "code",
"id": "79a7758178bafdd3",
"metadata": {
"jupyter": {
"source_hidden": true
},
"ExecuteTime": {
"end_time": "2025-03-27T14:25:59.032991Z",
"start_time": "2025-03-27T14:25:59.027760Z"
}
},
"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": 33
},
{
"cell_type": "code",
"id": "a79cafb06a7e0e43",
"metadata": {
"scrolled": true,
"ExecuteTime": {
"end_time": "2025-03-27T14:26:52.270461Z",
"start_time": "2025-03-27T14:25:59.040949Z"
}
},
"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: 8450470 entries, 0 to 8450469\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": 34
},
{
"cell_type": "code",
"id": "cac01788dac10678",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:27:10.055900Z",
"start_time": "2025-03-27T14:26:52.371488Z"
}
},
"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": 35
},
{
"cell_type": "code",
"id": "c4e9e1d31da6dba6",
"metadata": {
"jupyter": {
"source_hidden": true
},
"ExecuteTime": {
"end_time": "2025-03-27T14:27:10.498744Z",
"start_time": "2025-03-27T14:27:10.308136Z"
}
},
"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": 36
},
{
"cell_type": "code",
"id": "a735bc02ceb4d872",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:27:10.555260Z",
"start_time": "2025-03-27T14:27:10.509757Z"
}
},
"source": [
"import numpy as np\n",
"import talib\n",
"\n",
"\n",
"def get_rolling_factor(df):\n",
" old_columns = df.columns.tolist()[:]\n",
" # 按股票和日期排序\n",
" df = df.sort_values(by=['ts_code', 'trade_date'])\n",
" grouped = df.groupby('ts_code', group_keys=False)\n",
"\n",
" # df[\"gap_next_open\"] = (df[\"open\"].shift(-1) - df[\"close\"]) / df[\"close\"]\n",
"\n",
" df['return_skew'] = grouped['pct_chg'].rolling(window=5).skew().reset_index(0, drop=True)\n",
" df['return_kurtosis'] = grouped['pct_chg'].rolling(window=5).kurt().reset_index(0, drop=True)\n",
"\n",
" # 因子 1：短期成交量变化率\n",
" df['volume_change_rate'] = (\n",
" grouped['vol'].rolling(window=2).mean() /\n",
" grouped['vol'].rolling(window=10).mean() - 1\n",
" ).reset_index(level=0, drop=True) # 确保索引对齐\n",
"\n",
" # 因子 2：成交量突破信号\n",
" max_volume = grouped['vol'].rolling(window=5).max().reset_index(level=0, drop=True) # 确保索引对齐\n",
" df['cat_volume_breakout'] = (df['vol'] > max_volume)\n",
"\n",
" # 因子 3：换手率均线偏离度\n",
" mean_turnover = grouped['turnover_rate'].rolling(window=3).mean().reset_index(level=0, drop=True)\n",
" std_turnover = grouped['turnover_rate'].rolling(window=3).std().reset_index(level=0, drop=True)\n",
" df['turnover_deviation'] = (df['turnover_rate'] - mean_turnover) / std_turnover\n",
"\n",
" # 因子 4：换手率激增信号\n",
" df['cat_turnover_spike'] = (df['turnover_rate'] > mean_turnover + 2 * std_turnover)\n",
"\n",
" # 因子 5：量比均值\n",
" df['avg_volume_ratio'] = grouped['volume_ratio'].rolling(window=3).mean().reset_index(level=0, drop=True)\n",
"\n",
" # 因子 6：量比突破信号\n",
" max_volume_ratio = grouped['volume_ratio'].rolling(window=5).max().reset_index(level=0, drop=True)\n",
" df['cat_volume_ratio_breakout'] = (df['volume_ratio'] > max_volume_ratio)\n",
"\n",
" df['vol_spike'] = grouped.apply(\n",
" lambda x: pd.Series(x['vol'].rolling(20).mean(), index=x.index)\n",
" )\n",
" df['vol_std_5'] = df['vol'].pct_change().rolling(5).std()\n",
"\n",
" # 计算 ATR\n",
" df['atr_14'] = grouped.apply(\n",
" lambda x: pd.Series(talib.ATR(x['high'].values, x['low'].values, x['close'].values, timeperiod=14),\n",
" index=x.index)\n",
" )\n",
" df['atr_6'] = grouped.apply(\n",
" lambda x: pd.Series(talib.ATR(x['high'].values, x['low'].values, x['close'].values, timeperiod=6),\n",
" index=x.index)\n",
" )\n",
"\n",
" # 计算 OBV 及其均线\n",
" df['obv'] = grouped.apply(\n",
" lambda x: pd.Series(talib.OBV(x['close'].values, x['vol'].values), index=x.index)\n",
" )\n",
" df['maobv_6'] = grouped.apply(\n",
" lambda x: pd.Series(talib.SMA(x['obv'].values, timeperiod=6), index=x.index)\n",
" )\n",
"\n",
" df['rsi_3'] = grouped.apply(\n",
" lambda x: pd.Series(talib.RSI(x['close'].values, timeperiod=3), index=x.index)\n",
" )\n",
" # df['rsi_6'] = grouped.apply(\n",
" # lambda x: pd.Series(talib.RSI(x['close'].values, timeperiod=6), index=x.index)\n",
" # )\n",
" # df['rsi_9'] = grouped.apply(\n",
" # lambda x: pd.Series(talib.RSI(x['close'].values, timeperiod=9), index=x.index)\n",
" # )\n",
"\n",
" # 计算 return_10 和 return_20\n",
" df['return_5'] = grouped['close'].apply(lambda x: x / x.shift(5) - 1)\n",
" # df['return_10'] = grouped['close'].apply(lambda x: x / x.shift(10) - 1)\n",
" df['return_20'] = grouped['close'].apply(lambda x: x / x.shift(20) - 1)\n",
"\n",
" # df['avg_close_5'] = grouped['close'].apply(lambda x: x.rolling(window=5).mean() / x)\n",
"\n",
" # 计算标准差指标\n",
" df['std_return_5'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=5).std())\n",
" # df['std_return_15'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=15).std())\n",
" # df['std_return_25'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=25).std())\n",
" df['std_return_90'] = grouped['close'].apply(lambda x: x.pct_change().rolling(window=90).std())\n",
" df['std_return_90_2'] = grouped['close'].apply(lambda x: x.shift(10).pct_change().rolling(window=90).std())\n",
"\n",
" # 计算 EMA 指标\n",
" df['_ema_5'] = grouped['close'].apply(\n",
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=5), index=x.index)\n",
" )\n",
" df['_ema_13'] = grouped['close'].apply(\n",
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=13), index=x.index)\n",
" )\n",
" df['_ema_20'] = grouped['close'].apply(\n",
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=20), index=x.index)\n",
" )\n",
" df['_ema_60'] = grouped['close'].apply(\n",
" lambda x: pd.Series(talib.EMA(x.values, timeperiod=60), index=x.index)\n",
" )\n",
"\n",
" # 计算 act_factor1, act_factor2, act_factor3, act_factor4\n",
" df['act_factor1'] = grouped['_ema_5'].apply(\n",
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 50\n",
" )\n",
" df['act_factor2'] = grouped['_ema_13'].apply(\n",
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 40\n",
" )\n",
" df['act_factor3'] = grouped['_ema_20'].apply(\n",
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 21\n",
" )\n",
" df['act_factor4'] = grouped['_ema_60'].apply(\n",
" lambda x: np.arctan((x / x.shift(1) - 1) * 100) * 57.3 / 10\n",
" )\n",
"\n",
" # 根据 trade_date 截面计算排名\n",
" df['rank_act_factor1'] = df.groupby('trade_date', group_keys=False)['act_factor1'].rank(ascending=False, pct=True)\n",
" df['rank_act_factor2'] = df.groupby('trade_date', group_keys=False)['act_factor2'].rank(ascending=False, pct=True)\n",
" df['rank_act_factor3'] = df.groupby('trade_date', group_keys=False)['act_factor3'].rank(ascending=False, pct=True)\n",
"\n",
" df['log(circ_mv)'] = np.log(df['circ_mv'])\n",
"\n",
" def rolling_covariance(x, y, window):\n",
" return x.rolling(window).cov(y)\n",
"\n",
" def delta(series, period):\n",
" return series.diff(period)\n",
"\n",
" def rank(series):\n",
" return series.rank(pct=True)\n",
"\n",
" def stddev(series, window):\n",
" return series.rolling(window).std()\n",
"\n",
" window_high_volume = 5\n",
" window_close_stddev = 20\n",
" period_delta = 5\n",
" df['cov'] = rolling_covariance(df['high'], df['vol'], window_high_volume)\n",
" df['delta_cov'] = delta(df['cov'], period_delta)\n",
" df['_rank_stddev'] = rank(stddev(df['close'], window_close_stddev))\n",
" df['alpha_22_improved'] = -1 * df['delta_cov'] * df['_rank_stddev']\n",
"\n",
" df['alpha_003'] = np.where(df['high'] != df['low'],\n",
" (df['close'] - df['open']) / (df['high'] - df['low']),\n",
" 0)\n",
"\n",
" df['alpha_007'] = grouped.apply(lambda x: x['close'].rolling(5).corr(x['vol'])).reset_index(level=0, drop=True)\n",
" df['alpha_007'] = df.groupby('trade_date', group_keys=False)['alpha_007'].rank(ascending=True, pct=True)\n",
"\n",
" df['alpha_013'] = grouped['close'].transform(lambda x: x.rolling(5).sum() - x.rolling(20).sum())\n",
" df['alpha_013'] = df.groupby('trade_date', group_keys=False)['alpha_013'].rank(ascending=True, pct=True)\n",
"\n",
" df['cat_up_limit'] = (df['close'] == df['up_limit']) # 是否涨停（1表示涨停，0表示未涨停）\n",
" df['cat_down_limit'] = (df['close'] == df['down_limit']) # 是否跌停（1表示跌停，0表示未跌停）\n",
" df['up_limit_count_10d'] = grouped['cat_up_limit'].rolling(window=10, min_periods=1).sum().reset_index(level=0,\n",
" drop=True)\n",
" df['down_limit_count_10d'] = grouped['cat_down_limit'].rolling(window=10, min_periods=1).sum().reset_index(level=0,\n",
" drop=True)\n",
"\n",
" # 3. 最近连续涨跌停天数\n",
" def calculate_consecutive_limits(series):\n",
" \"\"\"\n",
" 计算连续涨停/跌停天数。\n",
" \"\"\"\n",
" consecutive_up = series * (series.groupby((series != series.shift()).cumsum()).cumcount() + 1)\n",
" consecutive_down = series * (series.groupby((series != series.shift()).cumsum()).cumcount() + 1)\n",
" return consecutive_up, consecutive_down\n",
"\n",
" # 连续涨停天数\n",
" df['consecutive_up_limit'] = grouped['cat_up_limit'].apply(\n",
" lambda x: calculate_consecutive_limits(x)[0]\n",
" ).reset_index(level=0, drop=True)\n",
"\n",
" df['vol_break'] = np.where((df['close'] > df['cost_85pct']) & (df['volume_ratio'] > 2), 1, 0)\n",
"\n",
" df['weight_roc5'] = grouped['weight_avg'].apply(lambda x: x.pct_change(5))\n",
"\n",
" def rolling_corr(group):\n",
" roc_close = group['close'].pct_change()\n",
" roc_weight = group['weight_avg'].pct_change()\n",
" return roc_close.rolling(10).corr(roc_weight)\n",
"\n",
" df['price_cost_divergence'] = grouped.apply(rolling_corr)\n",
"\n",
" df['smallcap_concentration'] = (1 / df['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['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['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": 37
},
{
"cell_type": "code",
"id": "53f86ddc0677a6d7",
"metadata": {
"jupyter": {
"source_hidden": true
},
"scrolled": true,
"ExecuteTime": {
"end_time": "2025-03-27T14:27:17.720085Z",
"start_time": "2025-03-27T14:27:10.615702Z"
}
},
"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": 38
},
{
"cell_type": "code",
"id": "dbe2fd8021b9417f",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:27:17.843735Z",
"start_time": "2025-03-27T14:27:17.837462Z"
}
},
"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": 39
},
{
"cell_type": "code",
"id": "85c3e3d0235ffffa",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:27:18.126281Z",
"start_time": "2025-03-27T14:27:17.932953Z"
}
},
"source": [
"print(df[df['is_st']][['ts_code', 'trade_date', 'is_st']])"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ts_code trade_date is_st\n",
"29 000037.SZ 2017-01-03 True\n",
"72 000408.SZ 2017-01-03 True\n",
"95 000504.SZ 2017-01-03 True\n",
"96 000505.SZ 2017-01-03 True\n",
"101 000511.SZ 2017-01-03 True\n",
"... ... ... ...\n",
"8449447 603869.SH 2025-03-21 True\n",
"8449452 603879.SH 2025-03-21 True\n",
"8449499 603959.SH 2025-03-21 True\n",
"8449881 688282.SH 2025-03-21 True\n",
"8449885 688287.SH 2025-03-21 True\n",
"\n",
"[192172 rows x 3 columns]\n"
]
}
],
"execution_count": 40
},
{
"cell_type": "code",
"id": "92d84ce15a562ec6",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:29:28.359109Z",
"start_time": "2025-03-27T14:27:18.133287Z"
}
},
"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.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: 5102787 entries, 0 to 5102786\n",
"Columns: 116 entries, ts_code to mv_momentum\n",
"dtypes: bool(12), datetime64[ns](2), float64(98), int32(1), int64(1), object(2)\n",
"memory usage: 4.0+ GB\n",
"None\n"
]
}
],
"execution_count": 41
},
{
"cell_type": "code",
"id": "b87b938028afa206",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:29:29.063060Z",
"start_time": "2025-03-27T14:29:29.044370Z"
}
},
"source": [
"from scipy.stats import ks_2samp, wasserstein_distance\n",
"from sklearn.metrics import roc_auc_score\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"\n",
"def remove_shifted_features(train_data, test_data, feature_columns, ks_threshold=0.05, wasserstein_threshold=0.1,\n",
" importance_threshold=0.05):\n",
" dropped_features = []\n",
"\n",
" # **统计数据漂移**\n",
" numeric_columns = train_data.select_dtypes(include=['float64', 'int64']).columns\n",
" numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
" for feature in numeric_columns:\n",
" ks_stat, p_value = ks_2samp(train_data[feature], test_data[feature])\n",
" wasserstein_dist = wasserstein_distance(train_data[feature], test_data[feature])\n",
"\n",
" if p_value < ks_threshold or wasserstein_dist > wasserstein_threshold:\n",
" dropped_features.append(feature)\n",
"\n",
" print(f\"检测到 {len(dropped_features)} 个可能漂移的特征: {dropped_features}\")\n",
"\n",
" # **应用阈值进行最终筛选**\n",
" filtered_features = [f for f in feature_columns if f not in dropped_features]\n",
"\n",
" return filtered_features, dropped_features\n",
"\n"
],
"outputs": [],
"execution_count": 42
},
{
"cell_type": "code",
"id": "f4f16d63ad18d1bc",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:29:29.468775Z",
"start_time": "2025-03-27T14:29:29.452331Z"
}
},
"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": 43
},
{
"cell_type": "code",
"id": "40e6b68a91b30c79",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T14:29:31.276518Z",
"start_time": "2025-03-27T14:29:29.638999Z"
}
},
"source": [
"import pandas as pd\n",
"\n",
"\n",
"def remove_outliers_label_percentile(label: pd.Series, lower_percentile: float = 0.01, upper_percentile: float = 0.99,\n",
" log=True):\n",
" if not (0 <= lower_percentile < upper_percentile <= 1):\n",
" raise ValueError(\"Percentile values must satisfy 0 <= lower_percentile < upper_percentile <= 1.\")\n",
"\n",
" # Calculate lower and upper bounds based on percentiles\n",
" lower_bound = label.quantile(lower_percentile)\n",
" upper_bound = label.quantile(upper_percentile)\n",
"\n",
" # Filter out values outside the bounds\n",
" filtered_label = label[(label >= lower_bound) & (label <= upper_bound)]\n",
"\n",
" # Print the number of removed outliers\n",
" if log:\n",
" print(f\"Removed {len(label) - len(filtered_label)} outliers.\")\n",
" return filtered_label\n",
"\n",
"\n",
"def calculate_risk_adjusted_target(df, days=5):\n",
" df = df.sort_values(by=['ts_code', 'trade_date'])\n",
"\n",
" df['future_close'] = df.groupby('ts_code')['close'].shift(-days)\n",
" df['future_open'] = df.groupby('ts_code')['open'].shift(-1)\n",
" df['future_return'] = (df['future_close'] - df['future_open']) / df['future_open']\n",
"\n",
" df['future_volatility'] = df.groupby('ts_code')['future_return'].rolling(days, min_periods=1).std().reset_index(\n",
" level=0, drop=True)\n",
" sharpe_ratio = df['future_return'] * df['future_volatility']\n",
" sharpe_ratio.replace([np.inf, -np.inf], np.nan, inplace=True)\n",
"\n",
" return sharpe_ratio\n",
"\n",
"\n",
"def calculate_score(df, days=5, lambda_param=1.0):\n",
" def calculate_max_drawdown(prices):\n",
" peak = prices.iloc[0] # 初始化峰值\n",
" max_drawdown = 0 # 初始化最大回撤\n",
"\n",
" for price in prices:\n",
" if price > peak:\n",
" peak = price # 更新峰值\n",
" else:\n",
" drawdown = (peak - price) / peak # 计算当前回撤\n",
" max_drawdown = max(max_drawdown, drawdown) # 更新最大回撤\n",
"\n",
" return max_drawdown\n",
"\n",
" def compute_stock_score(stock_df):\n",
" stock_df = stock_df.sort_values(by=['trade_date'])\n",
" future_return = stock_df['future_return']\n",
" volatility = stock_df['close'].pct_change().rolling(days).std().shift(-days)\n",
" max_drawdown = stock_df['close'].rolling(days).apply(calculate_max_drawdown, raw=False).shift(-days)\n",
" score = future_return - lambda_param * max_drawdown\n",
"\n",
" return score\n",
"\n",
" scores = df.groupby('ts_code').apply(lambda x: compute_stock_score(x))\n",
" scores = scores.reset_index(level=0, drop=True)\n",
"\n",
" return scores\n",
"\n",
"\n",
"def remove_highly_correlated_features(df, feature_columns, threshold=0.9):\n",
" numeric_features = df[feature_columns].select_dtypes(include=[np.number]).columns.tolist()\n",
" if not numeric_features:\n",
" raise ValueError(\"No numeric features found in the provided data.\")\n",
"\n",
" corr_matrix = df[numeric_features].corr().abs()\n",
" upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool))\n",
" to_drop = [column for column in upper.columns if any(upper[column] > threshold)]\n",
" remaining_features = [col for col in feature_columns if col not in to_drop\n",
" or 'act' in col or 'af' in col]\n",
" return remaining_features\n",
"\n",
"import pandas as pd\n",
"from sklearn.preprocessing import StandardScaler\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",
"import numpy as np\n",
"import pandas as pd\n",
"import statsmodels.api as sm\n",
"\n",
"def mad_filter(df, features, n=3):\n",
" \"\"\" 使用中位数绝对偏差（MAD）去极值 \"\"\"\n",
" df = df.copy()\n",
" for col in features:\n",
" median = df[col].median()\n",
" mad = np.median(np.abs(df[col] - median))\n",
" upper = median + n * mad\n",
" lower = median - n * mad\n",
" df[col] = np.clip(df[col], lower, upper) # 截断极值\n",
" return df\n",
"\n",
"from concurrent.futures import ProcessPoolExecutor\n",
"\n",
"def neutralize_manual(df, features, industry_col, mkt_cap_col):\n",
" \"\"\" 手动实现简单回归以提升速度 \"\"\"\n",
"\n",
" for col in features:\n",
" residuals = []\n",
" for _, group in df.groupby(industry_col):\n",
" if len(group) > 1:\n",
" x = np.log(group[mkt_cap_col]) # 市值对数\n",
" y = group[col] # 因子值\n",
" beta = np.cov(y, x)[0, 1] / np.var(x) # 计算斜率\n",
" alpha = np.mean(y) - beta * np.mean(x) # 计算截距\n",
" resid = y - (alpha + beta * x) # 计算残差\n",
" residuals.extend(resid)\n",
" else:\n",
" residuals.extend(group[col]) # 样本不足时保留原值\n",
"\n",
" df[col] = residuals\n",
"\n",
" return df\n",
"\n",
"\n",
"import gc\n",
"\n",
"gc.collect()"
],
"outputs": [
{
"data": {
"text/plain": [
"0"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"execution_count": 44
},
{
"cell_type": "code",
"id": "47c12bb34062ae7a",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T15:01:53.894366Z",
"start_time": "2025-03-27T14:59:19.610939Z"
}
},
"source": [
"days = 2\n",
"validation_days = 120\n",
"\n",
"import gc\n",
"\n",
"gc.collect()\n",
"\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')['future_return']\n",
" .transform(lambda x: x.rolling(days).std())\n",
")\n",
"\n",
"df['future_score'] = (\n",
" 0.7 * df['future_return'] +\n",
" 0.3 * df['future_volatility']\n",
")\n",
"\n",
"filter_index = df['future_return'].between(df['future_return'].quantile(0.01), df['future_return'].quantile(0.99))\n",
"filter_index = df['future_volatility'].between(df['future_volatility'].quantile(0.01),\n",
" df['future_volatility'].quantile(0.99)) | filter_index\n",
"\n",
"# df['label'] = df.groupby('trade_date', group_keys=False)['future_volatility'].transform(\n",
"# lambda x: pd.qcut(x, q=30, labels=False, duplicates='drop')\n",
"# )\n",
"\n",
"df['label'] = df.groupby('trade_date', group_keys=False)['future_score'].transform(\n",
" lambda x: pd.qcut(x, q=50, labels=False, duplicates='drop')\n",
")\n",
"\n",
"\n",
"# df['1_score'] = df.groupby('ts_code', group_keys=False)['future_score'].shift(days)\n",
"# df['2_score'] = df.groupby('ts_code', group_keys=False)['future_score'].shift(1 + days)\n",
"# df['3_score'] = df.groupby('ts_code', group_keys=False)['future_score'].shift(3 + days - 1)\n",
"\n",
"def symmetric_log_transform(values):\n",
" return np.sign(values) * np.log1p(np.abs(values))\n",
"\n",
"\n",
"train_data = df[filter_index & (df['trade_date'] <= '2023-01-01') & (df['trade_date'] >= '2000-01-01')]\n",
"test_data = df[filter_index & (df['trade_date'] >= '2023-01-01')]\n",
"\n",
"\n",
"def select_pre_zt_stocks_dynamic(stock_df):\n",
" # 排序数据\n",
" stock_df = stock_df.sort_values(by=['trade_date', 'ts_code'])\n",
"\n",
" # avg_vol_3 = stock_df.groupby('ts_code')['vol'].rolling(window=3).mean().reset_index(level=0, drop=True)\n",
" # avg_vol_5 = stock_df.groupby('ts_code')['vol'].rolling(window=5).mean().shift(3).reset_index(level=0, drop=True)\n",
"\n",
" # stock_df = stock_df[\n",
" # (stock_df['cat_up_limit'] == 1) |\n",
" # (stock_df['vol'] > vol_spike_multiplier * stock_df['vol_spike'])\n",
" # ]\n",
" # cd1 = stock_df[\"close\"] > stock_df[\"close\"].shift(1)\n",
"\n",
" # cd2 = stock_df[\"close\"] > stock_df[\"close\"].rolling(window=10).mean()\n",
" #\n",
" # cd3 = (avg_vol_3 > avg_vol_5 * 2)\n",
" #\n",
" # cd4 = stock_df['gap_next_open'] < 0\n",
"\n",
" # stock_df = stock_df[(cd2 & cd4) | cd3]\n",
" stock_df = stock_df.groupby('trade_date', group_keys=False).apply(\n",
" lambda x: x.nlargest(1000, 'return_20')\n",
" )\n",
"\n",
" return stock_df\n",
"\n",
"\n",
"# train_data = select_pre_zt_stocks_dynamic(train_data)\n",
"# test_data = select_pre_zt_stocks_dynamic(test_data)\n",
"\n",
"train_data, _ = get_simple_factor(train_data)\n",
"test_data, _ = get_simple_factor(test_data)\n",
"\n",
"# train_data['label'] = train_data.groupby('trade_date', group_keys=False)['future_score'].transform(\n",
"# lambda x: pd.qcut(x, q=50, labels=False, duplicates='drop')\n",
"# )\n",
"# test_data['label'] = test_data.groupby('trade_date', group_keys=False)['future_score'].transform(\n",
"# lambda x: pd.qcut(x, q=50, labels=False, duplicates='drop')\n",
"# )\n",
"\n",
"industry_df = industry_df.sort_values(by=['trade_date'])\n",
"index_data = index_data.sort_values(by=['trade_date'])\n",
"\n",
"train_data = train_data.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n",
"# train_data = train_data.merge(index_data, on='trade_date', how='left')\n",
"test_data = test_data.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n",
"# test_data = test_data.merge(index_data, on='trade_date', how='left')\n",
"\n",
"train_data, test_data = train_data.replace([np.inf, -np.inf], np.nan), test_data.replace([np.inf, -np.inf], np.nan)\n",
"\n",
"# feature_columns_new = feature_columns[:]\n",
"# train_data, _ = create_deviation_within_dates(train_data, feature_columns)\n",
"# test_data, _ = create_deviation_within_dates(test_data, feature_columns)\n",
"\n",
"feature_columns = [col for col in train_data.columns if col in train_data.columns]\n",
"feature_columns = [col for col in feature_columns if col not in ['trade_date',\n",
" 'ts_code',\n",
" 'label']]\n",
"feature_columns = [col for col in feature_columns if 'future' not in col]\n",
"feature_columns = [col for col in feature_columns if 'label' not in col]\n",
"feature_columns = [col for col in feature_columns if 'score' not in col]\n",
"feature_columns = [col for col in feature_columns if 'gen' not in col]\n",
"feature_columns = [col for col in feature_columns if 'cat_l2_code' not in col]\n",
"feature_columns = [col for col in feature_columns if col not in origin_columns]\n",
"feature_columns = [col for col in feature_columns if not col.startswith('_')]\n",
"print(f'feature_columns size: {len(feature_columns)}')\n",
"\n",
"numeric_columns = train_data.select_dtypes(include=['float64', 'int64']).columns\n",
"numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
"print('去极值')\n",
"train_data = mad_filter(train_data, feature_columns) # 去极值\n",
"# print('中性化')\n",
"# train_data = neutralize_manual(train_data, numeric_columns, industry_col='cat_l2_code', mkt_cap_col='log(circ_mv)') # 中性化\n",
"print('去极值')\n",
"test_data = mad_filter(test_data, feature_columns) # 去极值\n",
"# print('中性化')\n",
"# test_data = neutralize_manual(test_data, numeric_columns, industry_col='cat_l2_code', mkt_cap_col='log(circ_mv)')\n",
"\n",
"feature_columns, _ = remove_shifted_features(train_data[train_data['label'] == train_data['label'].max()],\n",
" test_data[test_data['label'] == test_data['label'].max()],\n",
" feature_columns)\n",
"\n",
"feature_columns = remove_highly_correlated_features(train_data[train_data['label'] == train_data['label'].max()],\n",
" feature_columns)\n",
"keep_columns = [col for col in train_data.columns if\n",
" col in feature_columns or col in ['ts_code', 'trade_date', 'label', 'future_return',\n",
" 'future_score', 'future_volatility']]\n",
"# train_data = train_data[keep_columns]\n",
"print(f'feature_columns: {feature_columns}')\n",
"\n",
"train_data = train_data.dropna(subset=feature_columns)\n",
"train_data = train_data.dropna(subset=['label'])\n",
"train_data = train_data.reset_index(drop=True)\n",
"\n",
"# print(test_data.tail())\n",
"test_data = test_data.dropna(subset=feature_columns)\n",
"# test_data = test_data.dropna(subset=['label'])\n",
"test_data = test_data.reset_index(drop=True)\n",
"\n",
"print(len(train_data))\n",
"print(f\"最小日期: {train_data['trade_date'].min().strftime('%Y-%m-%d')}\")\n",
"print(f\"最大日期: {train_data['trade_date'].max().strftime('%Y-%m-%d')}\")\n",
"print(len(test_data))\n",
"print(f\"最小日期: {test_data['trade_date'].min().strftime('%Y-%m-%d')}\")\n",
"print(f\"最大日期: {test_data['trade_date'].max().strftime('%Y-%m-%d')}\")\n",
"\n",
"cat_columns = [col for col in feature_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",
"\n",
"\n",
"# feature_columns_new.remove('cat_l2_code')"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"feature_columns size: 106\n",
"去极值\n",
"去极值\n",
"检测到 17 个可能漂移的特征: ['vol', 'pct_chg', 'turnover_rate', 'vol_std_5', 'obv', 'log(circ_mv)', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', 'log_close', 'up', 'down', 'mv_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume']\n",
"feature_columns: ['pe_ttm', 'volume_ratio', 'winner_rate', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'atr_14', 'maobv_6', 'rsi_3', 'return_5', 'return_20', 'std_return_5', 'std_return_90', 'std_return_90_2', 'act_factor1', 'act_factor2', 'act_factor3', 'act_factor4', 'rank_act_factor1', 'rank_act_factor2', 'rank_act_factor3', 'alpha_007', 'alpha_013', 'cat_up_limit', 'cat_down_limit', 'up_limit_count_10d', 'down_limit_count_10d', 'consecutive_up_limit', 'vol_break', 'weight_roc5', 'smallcap_concentration', 'cost_stability', 'high_cost_break_days', 'liquidity_risk', 'turnover_std', 'mv_volatility', 'volume_growth', 'mv_growth', 'arbr', 'momentum_factor', 'resonance_factor', 'cat_vol_spike', 'obv-maobv_6', 'std_return_5 / std_return_90', 'std_return_90 - std_return_90_2', 'cat_af2', 'cat_af3', 'cat_af4', 'act_factor5', 'act_factor6', 'active_buy_volume_large', 'active_buy_volume_big', 'active_buy_volume_small', 'buy_lg_vol_minus_sell_lg_vol', 'buy_elg_vol_minus_sell_elg_vol', 'ctrl_strength', 'low_cost_dev', 'asymmetry', 'lock_factor', 'cat_vol_break', 'cost_atr_adj', 'cat_golden_resonance', 'mv_momentum', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry_act_factor1', 'industry_act_factor2', 'industry_act_factor3', 'industry_act_factor4', 'industry_act_factor5', 'industry_act_factor6', 'industry_rank_act_factor1', 'industry_rank_act_factor2', 'industry_rank_act_factor3', 'industry_return_5_percentile', 'industry_return_20_percentile']\n",
"2539543\n",
"最小日期: 2018-06-04\n",
"最大日期: 2022-12-30\n",
"1232105\n",
"最小日期: 2023-01-03\n",
"最大日期: 2025-03-19\n"
]
}
],
"execution_count": 72
},
{
"cell_type": "code",
"id": "8f134d435f71e9e2",
"metadata": {
"jupyter": {
"source_hidden": true
},
"ExecuteTime": {
"end_time": "2025-03-27T15:01:54.350330Z",
"start_time": "2025-03-27T15:01:54.264148Z"
}
},
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"import lightgbm as lgb\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.decomposition import PCA\n",
"\n",
"\n",
"def train_light_model(train_data_df, params, feature_columns, callbacks, evals,\n",
" print_feature_importance=True, num_boost_round=100,\n",
" validation_days=180, use_pca=False, split_date=None): # 新增参数：validation_days\n",
" # 确保数据按时间排序\n",
" train_data_df = train_data_df.sort_values(by='trade_date')\n",
"\n",
" numeric_columns = train_data_df.select_dtypes(include=['float64', 'int64']).columns\n",
" numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
" # X_train.loc[:, numeric_columns] = scaler.fit_transform(X_train[numeric_columns])\n",
" # X_val.loc[:, numeric_columns] = scaler.transform(X_val[numeric_columns])\n",
" train_data_df = cross_sectional_standardization(train_data_df, numeric_columns)\n",
"\n",
" # 去除标签为空的样本\n",
" train_data_df = train_data_df.dropna(subset=['label'])\n",
" print('原始训练集大小: ', len(train_data_df))\n",
"\n",
" # 按时间顺序划分训练集和验证集\n",
" if split_date is None:\n",
" all_dates = train_data_df['trade_date'].unique() # 获取所有唯一的 trade_date\n",
" split_date = all_dates[-validation_days] # 划分点为倒数第 validation_days 天\n",
" train_data_split = train_data_df[train_data_df['trade_date'] < split_date] # 训练集\n",
" val_data_split = train_data_df[train_data_df['trade_date'] >= split_date] # 验证集\n",
"\n",
" # 打印划分结果\n",
" print(f\"划分后的训练集大小: {len(train_data_split)}, 验证集大小: {len(val_data_split)}\")\n",
"\n",
" # 提取特征和标签\n",
" X_train = train_data_split[feature_columns]\n",
" y_train = train_data_split['label']\n",
"\n",
" X_val = val_data_split[feature_columns]\n",
" y_val = val_data_split['label']\n",
"\n",
" # 标准化数值特征\n",
" scaler = StandardScaler()\n",
"\n",
"\n",
" # 计算每个 trade_date 内的样本数（LTR 需要 group 信息）\n",
" train_groups = train_data_split.groupby('trade_date').size().tolist()\n",
" val_groups = val_data_split.groupby('trade_date').size().tolist()\n",
"\n",
" # 处理类别特征\n",
" categorical_feature = [col for col in feature_columns if 'cat' in col]\n",
"\n",
" pca = None\n",
" if use_pca:\n",
" pca = PCA(n_components=0.95) # 或指定 n_components=固定值（如 10）\n",
" numeric_features = [col for col in feature_columns if col not in categorical_feature]\n",
" numeric_pca = pca.fit_transform(X_train[numeric_features])\n",
" X_train = pd.concat([pd.DataFrame(numeric_pca, index=X_train.index), X_train[categorical_feature]], axis=1)\n",
"\n",
" numeric_pca = pca.transform(X_val[numeric_features])\n",
" X_val = pd.concat([pd.DataFrame(numeric_pca, index=X_val.index), X_val[categorical_feature]], axis=1)\n",
"\n",
" # 计算权重（基于时间）\n",
" # trade_date = train_data_split['trade_date'] # 交易日期\n",
" # weights = (trade_date - trade_date.min()).dt.days / (trade_date.max() - trade_date.min()).days + 1\n",
" # weights = train_data_split.groupby('trade_date')['std_return_5'].transform(\n",
" # lambda x: x / x.mean()\n",
" # )\n",
" ud = sorted(train_data_split[\"trade_date\"].unique().tolist())\n",
" date_weights = {date: weight * weight for date, weight in zip(ud, np.linspace(1, 10, len(ud)))}\n",
" params['weight'] = train_data_split[\"trade_date\"].map(date_weights).tolist()\n",
"\n",
" print('feature_columns size: ', len(X_train.columns.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\n",
"\n",
"\n",
"from catboost import CatBoostRanker, Pool\n",
"import numpy as np\n",
"\n",
"\n",
"def train_catboost(train_data_df, test_data_df, feature_columns, params=None, plot=False):\n",
" X_train = train_data_df[feature_columns]\n",
" y_train = train_data_df['label']\n",
"\n",
" X_val = test_data_df[feature_columns]\n",
" y_val = test_data_df['label']\n",
"\n",
" scaler = StandardScaler()\n",
" numeric_columns = X_train.select_dtypes(include=['float64', 'int64']).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",
"\n",
" group_train = train_data_df['trade_date'].factorize()[0]\n",
" group_val = test_data_df['trade_date'].factorize()[0]\n",
"\n",
" cat_features = [i for i, col in enumerate(feature_columns) if col.startswith('cat')]\n",
" print(f'cat_features: {cat_features}')\n",
"\n",
" train_pool = Pool(\n",
" data=X_train,\n",
" label=y_train,\n",
" group_id=group_train,\n",
" cat_features=cat_features\n",
" )\n",
"\n",
" val_pool = Pool(\n",
" data=X_val,\n",
" label=y_val,\n",
" group_id=group_val,\n",
" cat_features=cat_features\n",
" )\n",
"\n",
" # CatBoost 排序学习模型\n",
" model = CatBoostRanker(**params)\n",
" model.fit(train_pool, eval_set=val_pool, plot=plot, use_best_model=True)\n",
"\n",
" return model, scaler\n"
],
"outputs": [],
"execution_count": 73
},
{
"cell_type": "code",
"id": "c6eb5cd4-e714-420a-ac48-39af3e11ee81",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T15:05:04.709244Z",
"start_time": "2025-03-27T15:01:54.503922Z"
}
},
"source": [
"print('train data size: ', len(train_data))\n",
"\n",
"label_gain = list(range(len(train_data['label'].unique())))\n",
"label_gain = [gain * gain for gain in label_gain]\n",
"light_params = {\n",
" 'label_gain': label_gain,\n",
" 'objective': 'lambdarank',\n",
" 'metric': 'lambdarank',\n",
" 'learning_rate': 0.1,\n",
" 'num_leaves': 1024,\n",
" 'min_data_in_leaf': 128,\n",
" 'max_depth': 16,\n",
" 'max_bin': 1024,\n",
" 'feature_fraction': 0.7,\n",
" 'bagging_fraction': 1,\n",
" 'bagging_freq': 5,\n",
" 'lambda_l1': 1,\n",
" 'lambda_l2': 1,\n",
" # 'boosting': 'dart',\n",
" 'verbosity': -1,\n",
" 'extra_trees': True,\n",
" 'max_position': 5,\n",
" 'ndcg_at': 1,\n",
" 'seed': 7\n",
"}\n",
"evals = {}\n",
"\n",
"gc.collect()\n",
"\n",
"use_pca = False\n",
"feature_contri = [2 if feat.startswith('act_factor') else 1 for feat in feature_columns]\n",
"light_params['feature_contri'] = feature_contri\n",
"print(f'feature_contri: {feature_contri}')\n",
"model, scaler, pca = train_light_model(train_data.dropna(subset=['label']),\n",
" light_params, feature_columns,\n",
" [lgb.log_evaluation(period=100),\n",
" lgb.callback.record_evaluation(evals),\n",
" lgb.early_stopping(50, first_metric_only=True)\n",
" ], evals,\n",
" num_boost_round=1000, validation_days=120,\n",
" print_feature_importance=True, use_pca=use_pca)\n",
"\n",
"print('train data size: ', len(train_data))"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"train data size: 2539543\n",
"feature_contri: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]\n",
"原始训练集大小: 2539543\n",
"划分后的训练集大小: 2258414, 验证集大小: 281129\n",
"feature_columns size: 84\n",
"Training until validation scores don't improve for 50 rounds\n",
"[100]\ttrain's ndcg@1: 0.793308\tvalid's ndcg@1: 0.572619\n",
"Early stopping, best iteration is:\n",
"[59]\ttrain's ndcg@1: 0.754956\tvalid's ndcg@1: 0.624334\n",
"Evaluated only: ndcg@1\n"
]
},
{
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "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
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "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
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"train data size: 2539543\n"
]
}
],
"execution_count": 74
},
{
"cell_type": "code",
"id": "1a248706-e58a-406f-9268-6dce3de2d863",
"metadata": {
"jupyter": {
"source_hidden": true
},
"ExecuteTime": {
"end_time": "2025-03-27T15:05:05.002439Z",
"start_time": "2025-03-27T15:05:04.994562Z"
}
},
"source": [
"\n",
"\n",
"# catboost_params = {\n",
"# 'loss_function': 'QuerySoftMax',\n",
"# 'eval_metric': 'QuerySoftMax',\n",
"# # 'custom_metric': ['AverageGain:top=10'],\n",
"\n",
"# 'iterations': 5000,\n",
"# 'learning_rate': 0.01,\n",
"# 'depth': 10,\n",
"# 'grow_policy': 'Lossguide',\n",
"# # 'max_leaves': 64,\n",
"# # 'min_data_in_leaf': 50,\n",
"\n",
"# # 'l2_leaf_reg': 5,\n",
"# # 'random_strength': 2.0,\n",
"# # 'bagging_temperature': 1.2,\n",
"# # 'subsample': 0.8,\n",
"\n",
"# 'early_stopping_rounds': 100,\n",
"# 'task_type': 'GPU',\n",
"# 'verbose': 500,\n",
"\n",
"# 'one_hot_max_size': 64\n",
"# }\n",
"\n",
"# gc.collect()\n",
"\n",
"# feature_weights = {col: 2.0 if 'act_factor' in col\n",
"# # or 'af' in col\n",
"# or 'limit' in col\n",
"# else 1.0\n",
"# for col in feature_columns_new}\n",
"# catboost_params['feature_weights'] = feature_weights\n",
"\n",
"# # model, scaler = train_catboost(train_data, test_data.dropna(subset=['label']), feature_columns_new, catboost_params, plot=True)"
],
"outputs": [],
"execution_count": 75
},
{
"cell_type": "code",
"id": "5d1522a7538db91b",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T15:05:48.344702Z",
"start_time": "2025-03-27T15:05:05.075376Z"
}
},
"source": [
"# train_data = train_data.sort_values(by='trade_date')\n",
"# all_dates = train_data['trade_date'].unique() # 获取所有唯一的 trade_date\n",
"# split_date = all_dates[-120] # 划分点为倒数第 validation_days 天\n",
"# print(split_date)\n",
"# print(all_dates)\n",
"# val_data_split = train_data[train_data['trade_date'] >= split_date] # 验证集\n",
"\n",
"score_df = test_data\n",
"numeric_columns = score_df.select_dtypes(include=['float64', 'int64']).columns\n",
"numeric_columns = [col for col in numeric_columns if col in feature_columns]\n",
"# score_df.loc[:, numeric_columns] = scaler.transform(score_df[numeric_columns])\n",
"score_df = cross_sectional_standardization(score_df, numeric_columns)\n",
"\n",
"if use_pca and pca is not None:\n",
" categorical_feature = [col for col in feature_columns if 'cat' in col]\n",
" numeric_features = [col for col in feature_columns if col not in categorical_feature]\n",
" numeric_pca = pca.transform(score_df[numeric_features])\n",
" score_df = pd.concat([pd.DataFrame(numeric_pca), score_df[categorical_feature],\n",
" score_df[['trade_date', 'ts_code', 'future_return', 'future_score', 'label']]], axis=1)\n",
" score_df['score'] = model.predict(score_df[[col for col in score_df.columns if\n",
" col not in ['trade_date', 'ts_code', 'future_return', 'future_score',\n",
" 'label']]])\n",
"else:\n",
" score_df['score'] = model.predict(score_df[feature_columns])\n",
"# train_data['score'] = catboost_model.predict(train_data[feature_columns])\n",
"score_df = score_df.loc[score_df.groupby('trade_date')['score'].idxmax()]\n",
"# score_df = score_df[score_df['score'] > 0]\n",
"score_df[['trade_date', 'score', 'ts_code']].to_csv('predictions_test.tsv', index=False)\n",
"print(score_df['label'].mean())\n",
"print(score_df[['trade_date', 'ts_code', 'future_return', 'future_score', 'label']].head(10))"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"34.45215759849906\n",
" trade_date ts_code future_return future_score label\n",
"1018787 2023-01-03 603232.SH -0.048337 0.009385 25.0\n",
"861926 2023-01-04 601155.SH 0.011962 0.027340 43.0\n",
"56178 2023-01-05 000596.SZ 0.006810 0.025770 42.0\n",
"919818 2023-01-06 601865.SH -0.016155 0.009868 36.0\n",
"986371 2023-01-09 603129.SH 0.005034 0.028874 47.0\n",
"270858 2023-01-10 002238.SZ 0.137958 0.110154 49.0\n",
"254244 2023-01-11 002188.SZ -0.014411 0.009928 33.0\n",
"315695 2023-01-12 002368.SZ 0.064003 0.047429 47.0\n",
"1076977 2023-01-13 603530.SH -0.033076 0.001755 17.0\n",
"179564 2023-01-16 001339.SZ -0.045814 -0.015564 3.0\n"
]
}
],
"execution_count": 76
},
{
"cell_type": "code",
"id": "d86af99d15cb3bdd",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T15:05:48.949443Z",
"start_time": "2025-03-27T15:05:48.354713Z"
}
},
"source": [
"print(df[(df['ts_code'] == '603577.SH') & (df['trade_date'] >= '2018-06-04')][\n",
" ['trade_date', 'ts_code', 'close', 'open', 'future_return']])"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" trade_date ts_code close open future_return\n",
"255411 2018-06-04 603577.SH 24.57 23.98 -0.044408\n",
"257982 2018-06-05 603577.SH 23.45 24.32 -0.037819\n",
"260550 2018-06-06 603577.SH 23.24 22.74 -0.052262\n",
"263114 2018-06-07 603577.SH 21.88 22.77 -0.028451\n",
"265676 2018-06-08 603577.SH 21.58 21.44 -0.002314\n",
"... ... ... ... ... ...\n",
"5090093 2025-03-17 603577.SH 20.05 20.20 0.011958\n",
"5093183 2025-03-18 603577.SH 20.27 20.07 0.015294\n",
"5096269 2025-03-19 603577.SH 20.31 20.27 0.017725\n",
"5099355 2025-03-20 603577.SH 20.58 20.31 NaN\n",
"5102442 2025-03-21 603577.SH 20.67 20.56 NaN\n",
"\n",
"[1650 rows x 5 columns]\n"
]
}
],
"execution_count": 77
},
{
"cell_type": "code",
"id": "ef9d068e-67f7-412c-bbd8-cdee7492dbc9",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-27T15:05:49.093930Z",
"start_time": "2025-03-27T15:05:49.014773Z"
}
},
"source": [
"print(train_data[\"future_score\"].corr(train_data[\"label\"]))\n",
"print(test_data[\"future_score\"].corr(test_data[\"label\"]))\n"
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.7431901412574308\n",
"0.6963809182594688\n"
]
}
],
"execution_count": 78
}
],
"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
}
Reference in New Issue Copy Permalink