{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "79a7758178bafdd3", "metadata": { "jupyter": { "is_executing": true, "source_hidden": true } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "/mnt/d/PyProject/NewStock\n" ] } ], "source": [ "%load_ext autoreload\n", "%autoreload 2\n", "# %load_ext cudf.pandas\n", "\n", "import gc\n", "import os\n", "import sys\n", "sys.path.append('/mnt/d/PyProject/NewStock/')\n", "import sys\n", "sys.path.append('/mnt/d/PyProject/NewStock/main/')\n", "import sys\n", "sys.path.append('/mnt/d/PyProject/NewStock/train')\n", "import sys\n", "sys.path.append('/mnt/d/PyProject/NewStock')\n", "import sys\n", "sys.path.append('/mnt/d/PyProject/NewStock/main')\n", "import sys\n", "sys.path.append('/mnt/d/PyProject/NewStock/train/')\n", "print(os.getcwd())\n", "import pandas as pd\n", "from main.factor.factor import get_rolling_factor, get_simple_factor\n", "from main.utils.factor import read_industry_data\n", "from main.utils.factor_processor import calculate_score\n", "from main.utils.utils import read_and_merge_h5_data, merge_with_industry_data\n", "\n", "import warnings\n", "\n", "warnings.filterwarnings(\"ignore\")\n" ] }, { "cell_type": "code", "execution_count": 2, "id": "4a481c60", "metadata": {}, "outputs": [], "source": [ "# 设置使用核心\n", "import os\n", "os.environ[\"MODIN_CPUS\"] = \"4\"\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "a79cafb06a7e0e43", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.016626900Z", "start_time": "2025-04-03T12:46:06.998047Z" }, "scrolled": true }, "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", "\n", "RangeIndex: 9162612 entries, 0 to 9162611\n", "Data columns (total 33 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 amount float64 \n", " 8 pct_chg float64 \n", " 9 turnover_rate float64 \n", " 10 pe_ttm float64 \n", " 11 circ_mv float64 \n", " 12 total_mv float64 \n", " 13 volume_ratio float64 \n", " 14 is_st bool \n", " 15 up_limit float64 \n", " 16 down_limit float64 \n", " 17 buy_sm_vol float64 \n", " 18 sell_sm_vol float64 \n", " 19 buy_lg_vol float64 \n", " 20 sell_lg_vol float64 \n", " 21 buy_elg_vol float64 \n", " 22 sell_elg_vol float64 \n", " 23 net_mf_vol float64 \n", " 24 his_low float64 \n", " 25 his_high float64 \n", " 26 cost_5pct float64 \n", " 27 cost_15pct float64 \n", " 28 cost_50pct float64 \n", " 29 cost_85pct float64 \n", " 30 cost_95pct float64 \n", " 31 weight_avg float64 \n", " 32 winner_rate float64 \n", "dtypes: bool(1), datetime64[ns](1), float64(30), object(1)\n", "memory usage: 2.2+ GB\n", "None\n" ] } ], "source": [ "from main.utils.utils import read_and_merge_h5_data\n", "\n", "print('daily data')\n", "df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/daily_data.h5', key='daily_data',\n", " columns=['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol', 'amount', 'pct_chg'],\n", " df=None)\n", "\n", "print('daily basic')\n", "df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/daily_basic.h5', key='daily_basic',\n", " columns=['ts_code', 'trade_date', 'turnover_rate', 'pe_ttm', 'circ_mv', 'total_mv', 'volume_ratio',\n", " 'is_st'], df=df, join='inner')\n", "\n", "print('stk limit')\n", "df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/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('/mnt/d/PyProject/NewStock/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('/mnt/d/PyProject/NewStock/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())" ] }, { "cell_type": "code", "execution_count": 4, "id": "cac01788dac10678", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.020945600Z", "start_time": "2025-04-03T12:47:00.488715Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "industry\n" ] } ], "source": [ "print('industry')\n", "industry_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/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']])" ] }, { "cell_type": "code", "execution_count": 5, "id": "c4e9e1d31da6dba6", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.021492400Z", "start_time": "2025-04-03T12:47:10.541247Z" }, "jupyter": { "source_hidden": true } }, "outputs": [], "source": [ "from main.factor.factor import *\n", "\n", "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", " # df = sentiment_panic_greed_index(df)\n", " # df = sentiment_market_breadth_proxy(df)\n", " # df = sentiment_reversal_indicator(df)\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', \n", " 'RSI', 'MACD', 'Signal_line', 'MACD_hist', \n", " # 'sentiment_panic_greed_index',\n", " '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 = '/mnt/d/PyProject/NewStock/data/index_data.h5'\n", "index_data = generate_index_indicators(h5_filename)\n", "index_data = index_data.dropna()\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "a735bc02ceb4d872", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.021998300Z", "start_time": "2025-04-03T12:47:10.751831Z" } }, "outputs": [], "source": [ "import talib\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 7, "id": "53f86ddc0677a6d7", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.021998300Z", "start_time": "2025-04-03T12:47:10.826179Z" }, "jupyter": { "source_hidden": true }, "scrolled": true }, "outputs": [], "source": [ "from main.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", "\n", " # cs_rank_intraday_range(industry_data)\n", " # cs_rank_close_pos_in_range(industry_data)\n", "\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('/mnt/d/PyProject/NewStock/data/sw_daily.h5')\n" ] }, { "cell_type": "code", "execution_count": 8, "id": "dbe2fd8021b9417f", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.055745300Z", "start_time": "2025-04-03T12:47:15.963327Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['ts_code', 'open', 'close', 'high', 'low', 'amount', 'circ_mv', 'total_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" ] } ], "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)" ] }, { "cell_type": "code", "execution_count": 9, "id": "85c3e3d0235ffffa", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.056256100Z", "start_time": "2025-04-03T12:47:15.990101Z" } }, "outputs": [], "source": [ "fina_indicator_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/fina_indicator.h5', key='fina_indicator',\n", " columns=['ts_code', 'ann_date', 'undist_profit_ps', 'ocfps', 'bps', 'roa', 'roe'],\n", " df=None)\n", "cashflow_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/cashflow.h5', key='cashflow',\n", " columns=['ts_code', 'ann_date', 'n_cashflow_act'],\n", " df=None)\n", "balancesheet_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/balancesheet.h5', key='balancesheet',\n", " columns=['ts_code', 'ann_date', 'money_cap', 'total_liab'],\n", " df=None)\n", "top_list_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/top_list.h5', key='top_list',\n", " columns=['ts_code', 'trade_date', 'reason'],\n", " df=None)\n", "\n", "top_list_df = top_list_df.sort_values(by='trade_date', ascending=False).drop_duplicates(subset=['ts_code', 'trade_date'], keep='first').sort_values(by='trade_date')\n", "\n", "stk_holdertrade_df = read_and_merge_h5_data('/mnt/d/PyProject/NewStock/data/stk_holdertrade.h5', key='stk_holdertrade',\n", " columns=['ts_code', 'ann_date', 'in_de', 'change_ratio', 'after_ratio'],\n", " df=None)" ] }, { "cell_type": "code", "execution_count": 10, "id": "92d84ce15a562ec6", "metadata": { "ExecuteTime": { "end_time": "2025-10-13T13:43:40.057271300Z", "start_time": "2025-04-03T12:47:16.121802Z" } }, "outputs": [], "source": [ "\n", "import numpy as np\n", "import polars as pl\n", "from main.factor.factor import *\n", "from main.factor.money_factor import *\n", "\n", "\n", "def filter_data(df):\n", " # df = df.groupby('trade_date').apply(lambda x: x.nlargest(1000, 'act_factor1'))\n", " df = df[df['trade_date'] <= '2025-06-01']\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'] >= '2019-01-01']\n", " if 'in_date' in df.columns:\n", " df = df.drop(columns=['in_date'])\n", " df = df.reset_index(drop=True)\n", " return df\n", "\n", "gc.collect()\n", "\n", "df = filter_data(df)\n", "df = df.sort_values(by=['ts_code', 'trade_date'])\n", "\n", "df = pl.from_dataframe(df)" ] }, { "cell_type": "code", "execution_count": null, "id": "a2b3d9e6", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Applying momentum factors: 0%| | 0/10 [00:00 \u001b[39m\u001b[32m4\u001b[39m df = \u001b[43mapply_momentum_factors\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 6\u001b[39m \u001b[38;5;28mprint\u001b[39m(df.columns)\n", "\u001b[36mFile \u001b[39m\u001b[32m/mnt/d/PyProject/NewStock/main/factor/polars_momentum_factors.py:408\u001b[39m, in \u001b[36mapply_momentum_factors\u001b[39m\u001b[34m(df, operators)\u001b[39m\n\u001b[32m 406\u001b[39m result_df = df\n\u001b[32m 407\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m operator \u001b[38;5;129;01min\u001b[39;00m tqdm(operators, desc=\u001b[33m\"\u001b[39m\u001b[33mApplying momentum factors\u001b[39m\u001b[33m\"\u001b[39m):\n\u001b[32m--> \u001b[39m\u001b[32m408\u001b[39m result_df = \u001b[43moperator\u001b[49m\u001b[43m.\u001b[49m\u001b[43mapply\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresult_df\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 410\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m result_df\n", "\u001b[36mFile \u001b[39m\u001b[32m/mnt/d/PyProject/NewStock/main/factor/operator_framework.py:58\u001b[39m, in \u001b[36mBaseOperator.apply\u001b[39m\u001b[34m(self, df, return_type, **kwargs)\u001b[39m\n\u001b[32m 55\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33m缺少必需列：\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.required_columns\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m)\n\u001b[32m 57\u001b[39m long_table = \u001b[38;5;28mself\u001b[39m._sectional_roll(df, **kwargs) \u001b[38;5;66;03m# ① 滚动\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m58\u001b[39m merged = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_merge_factor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlong_table\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# ② 合并\u001b[39;00m\n\u001b[32m 59\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m merged \u001b[38;5;28;01mif\u001b[39;00m return_type == \u001b[33m'\u001b[39m\u001b[33mdf\u001b[39m\u001b[33m'\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m merged[\u001b[38;5;28mself\u001b[39m.get_factor_name()]\n", "\u001b[36mFile \u001b[39m\u001b[32m/mnt/d/PyProject/NewStock/main/factor/operator_framework.py:76\u001b[39m, in \u001b[36mBaseOperator._merge_factor\u001b[39m\u001b[34m(self, original, factor_table)\u001b[39m\n\u001b[32m 74\u001b[39m \u001b[38;5;250m\u001b[39m\u001b[33;03m\"\"\"按 [ts_code, trade_date] 左联，原地追加因子列\"\"\"\u001b[39;00m\n\u001b[32m 75\u001b[39m factor_name = \u001b[38;5;28mself\u001b[39m.get_factor_name()\n\u001b[32m---> \u001b[39m\u001b[32m76\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43moriginal\u001b[49m\u001b[43m.\u001b[49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfactor_table\u001b[49m\u001b[43m.\u001b[49m\u001b[43mselect\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mts_code\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mtrade_date\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfactor_name\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 77\u001b[39m \u001b[43m \u001b[49m\u001b[43mon\u001b[49m\u001b[43m=\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mts_code\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mtrade_date\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 78\u001b[39m \u001b[43m \u001b[49m\u001b[43mhow\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mleft\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/polars/_utils/deprecation.py:128\u001b[39m, in \u001b[36mdeprecate_renamed_parameter..decorate..wrapper\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 123\u001b[39m \u001b[38;5;129m@wraps\u001b[39m(function)\n\u001b[32m 124\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mwrapper\u001b[39m(*args: P.args, **kwargs: P.kwargs) -> T:\n\u001b[32m 125\u001b[39m _rename_keyword_argument(\n\u001b[32m 126\u001b[39m old_name, new_name, kwargs, function.\u001b[34m__qualname__\u001b[39m, version\n\u001b[32m 127\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m128\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/polars/dataframe/frame.py:7842\u001b[39m, in \u001b[36mDataFrame.join\u001b[39m\u001b[34m(self, other, on, how, left_on, right_on, suffix, validate, nulls_equal, coalesce, maintain_order)\u001b[39m\n\u001b[32m 7824\u001b[39m require_same_type(\u001b[38;5;28mself\u001b[39m, other)\n\u001b[32m 7826\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mpolars\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mlazyframe\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mopt_flags\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m QueryOptFlags\n\u001b[32m 7828\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m (\n\u001b[32m 7829\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mlazy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 7830\u001b[39m \u001b[43m \u001b[49m\u001b[43m.\u001b[49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m 7831\u001b[39m \u001b[43m \u001b[49m\u001b[43mother\u001b[49m\u001b[43m=\u001b[49m\u001b[43mother\u001b[49m\u001b[43m.\u001b[49m\u001b[43mlazy\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7832\u001b[39m \u001b[43m \u001b[49m\u001b[43mleft_on\u001b[49m\u001b[43m=\u001b[49m\u001b[43mleft_on\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7833\u001b[39m \u001b[43m \u001b[49m\u001b[43mright_on\u001b[49m\u001b[43m=\u001b[49m\u001b[43mright_on\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7834\u001b[39m \u001b[43m \u001b[49m\u001b[43mon\u001b[49m\u001b[43m=\u001b[49m\u001b[43mon\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7835\u001b[39m \u001b[43m \u001b[49m\u001b[43mhow\u001b[49m\u001b[43m=\u001b[49m\u001b[43mhow\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7836\u001b[39m \u001b[43m \u001b[49m\u001b[43msuffix\u001b[49m\u001b[43m=\u001b[49m\u001b[43msuffix\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7837\u001b[39m \u001b[43m \u001b[49m\u001b[43mvalidate\u001b[49m\u001b[43m=\u001b[49m\u001b[43mvalidate\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7838\u001b[39m \u001b[43m \u001b[49m\u001b[43mnulls_equal\u001b[49m\u001b[43m=\u001b[49m\u001b[43mnulls_equal\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7839\u001b[39m \u001b[43m \u001b[49m\u001b[43mcoalesce\u001b[49m\u001b[43m=\u001b[49m\u001b[43mcoalesce\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7840\u001b[39m \u001b[43m \u001b[49m\u001b[43mmaintain_order\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmaintain_order\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m 7841\u001b[39m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m-> \u001b[39m\u001b[32m7842\u001b[39m \u001b[43m \u001b[49m\u001b[43m.\u001b[49m\u001b[43mcollect\u001b[49m\u001b[43m(\u001b[49m\u001b[43moptimizations\u001b[49m\u001b[43m=\u001b[49m\u001b[43mQueryOptFlags\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_eager\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 7843\u001b[39m )\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/polars/_utils/deprecation.py:97\u001b[39m, in \u001b[36mdeprecate_streaming_parameter..decorate..wrapper\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 93\u001b[39m kwargs[\u001b[33m\"\u001b[39m\u001b[33mengine\u001b[39m\u001b[33m\"\u001b[39m] = \u001b[33m\"\u001b[39m\u001b[33min-memory\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 95\u001b[39m \u001b[38;5;28;01mdel\u001b[39;00m kwargs[\u001b[33m\"\u001b[39m\u001b[33mstreaming\u001b[39m\u001b[33m\"\u001b[39m]\n\u001b[32m---> \u001b[39m\u001b[32m97\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/polars/lazyframe/opt_flags.py:331\u001b[39m, in \u001b[36mforward_old_opt_flags..decorate..wrapper\u001b[39m\u001b[34m(*args, **kwargs)\u001b[39m\n\u001b[32m 328\u001b[39m optflags = cb(optflags, kwargs.pop(key)) \u001b[38;5;66;03m# type: ignore[no-untyped-call,unused-ignore]\u001b[39;00m\n\u001b[32m 330\u001b[39m kwargs[\u001b[33m\"\u001b[39m\u001b[33moptimizations\u001b[39m\u001b[33m\"\u001b[39m] = optflags\n\u001b[32m--> \u001b[39m\u001b[32m331\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/miniconda3/envs/stock/lib/python3.13/site-packages/polars/lazyframe/frame.py:2300\u001b[39m, in \u001b[36mLazyFrame.collect\u001b[39m\u001b[34m(self, type_coercion, predicate_pushdown, projection_pushdown, simplify_expression, slice_pushdown, comm_subplan_elim, comm_subexpr_elim, cluster_with_columns, collapse_joins, no_optimization, engine, background, optimizations, **_kwargs)\u001b[39m\n\u001b[32m 2298\u001b[39m \u001b[38;5;66;03m# Only for testing purposes\u001b[39;00m\n\u001b[32m 2299\u001b[39m callback = _kwargs.get(\u001b[33m\"\u001b[39m\u001b[33mpost_opt_callback\u001b[39m\u001b[33m\"\u001b[39m, callback)\n\u001b[32m-> \u001b[39m\u001b[32m2300\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m wrap_df(\u001b[43mldf\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcollect\u001b[49m\u001b[43m(\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallback\u001b[49m\u001b[43m)\u001b[49m)\n", "\u001b[31mDuplicateError\u001b[39m: column with name 'price_minus_deduction_price_10_right' already exists\n\nYou may want to try:\n- renaming the column prior to joining\n- using the `suffix` parameter to specify a suffix different to the default one ('_right')" ] } ], "source": [ "from main.factor.polars_momentum_factors import apply_momentum_factors\n", "\n", "\n", "df = apply_momentum_factors(df)\n", "\n", "print(df)" ] } ], "metadata": { "kernelspec": { "display_name": "stock", "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": "3.13.2" } }, "nbformat": 4, "nbformat_minor": 5 }