{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "79a7758178bafdd3", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:32:04.258788Z", "start_time": "2025-04-10T13:32:03.855779Z" }, "jupyter": { "source_hidden": true } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "e:\\PyProject\\NewStock\\main\\train\n" ] } ], "source": [ "# %load_ext autoreload\n", "# %autoreload 2\n", "\n", "import gc\n", "import os\n", "import sys\n", "sys.path.append('../../')\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\")" ] }, { "cell_type": "code", "execution_count": 2, "id": "a79cafb06a7e0e43", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:32:50.139059Z", "start_time": "2025-04-10T13:32:04.267804Z" }, "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: 5123740 entries, 0 to 5123739\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: 1.2+ 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('../../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", "df = df[df['trade_date'] >= '2021-01-01']\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())" ] }, { "cell_type": "code", "execution_count": 3, "id": "cac01788dac10678", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:32:55.189416Z", "start_time": "2025-04-10T13:32:50.335162Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "industry\n" ] } ], "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']])" ] }, { "cell_type": "code", "execution_count": 4, "id": "c4e9e1d31da6dba6", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:32:55.289023Z", "start_time": "2025-04-10T13:32:55.203565Z" } }, "outputs": [], "source": [ "import talib\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", " 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" ] }, { "cell_type": "code", "execution_count": 5, "id": "53f86ddc0677a6d7", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:33:00.552850Z", "start_time": "2025-04-10T13:32:55.363645Z" }, "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", " 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" ] }, { "cell_type": "code", "execution_count": 6, "id": "dbe2fd8021b9417f", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:33:00.573680Z", "start_time": "2025-04-10T13:33:00.569106Z" } }, "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" ] } ], "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": 7, "id": "da6e43bd", "metadata": {}, "outputs": [], "source": [ "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", " epsilon = 1e-8\n", " df['lg_elg_net_buy_vol'] = df['buy_lg_vol'] + df['buy_elg_vol'] - df['sell_lg_vol'] - df['sell_elg_vol']\n", " # 检查 'volume' 列是否存在且有效\n", " df['flow_lg_elg_intensity'] = df['lg_elg_net_buy_vol'] / (df['vol'] + epsilon)\n", "\n", " # 2. 散户与主力背离度 (Retail vs Institutional Divergence)\n", " # 衡量小单净流入与（大单+超大单）净流入的差异或比率\n", " df['sm_net_buy_vol'] = df['buy_sm_vol'] - df['sell_sm_vol']\n", " df['flow_divergence_diff'] = df['sm_net_buy_vol'] - df['lg_elg_net_buy_vol']\n", " # 比率形式可能更稳定\n", " df['flow_divergence_ratio'] = df['sm_net_buy_vol'] / (\n", " df['lg_elg_net_buy_vol'] + np.sign(df['lg_elg_net_buy_vol']) * epsilon + epsilon) # 复杂处理避免0/0\n", "\n", " # 3. 资金流结构变动 (Flow Structure Change - Relative Strength of Large Flow)\n", " # 大单+超大单买入额占总买入额的比例的变化\n", " df['total_buy_vol'] = df['buy_sm_vol'] + df['buy_lg_vol'] + df['buy_elg_vol']\n", " df['lg_elg_buy_prop'] = (df['buy_lg_vol'] + df['buy_elg_vol']) / (df['total_buy_vol'] + epsilon)\n", " df['flow_struct_buy_change'] = grouped['lg_elg_buy_prop'].diff(1) # 1日变化\n", "\n", " # 4. 资金流加速度 (Flow Acceleration)\n", " # 净主力资金流的变化率（二阶导）\n", " df['lg_elg_net_buy_vol_change'] = grouped['lg_elg_net_buy_vol'].diff(1)\n", " df['flow_lg_elg_accel'] = grouped['lg_elg_net_buy_vol_change'].diff(1)\n", "\n", " # # 5. 极端资金流事件 (Categorical: Extreme Flow Event)\n", " # # 定义主力资金流强度是否处于其历史极端水平（例如，过去N天的90分位数以上或10分位数以下）\n", " # rolling_window = 20 # 可调整窗口期\n", "\n", " # # Step 1: Calculate the rolling quantiles separately\n", " # rolling_high = grouped['flow_lg_elg_intensity'].rolling(rolling_window, min_periods=1).quantile(0.9) # min_periods=1 保证窗口未满时也有输出\n", " # rolling_low = grouped['flow_lg_elg_intensity'].rolling(rolling_window, min_periods=1).quantile(0.1)\n", "\n", " # # Step 2: Assign the results to the DataFrame\n", " # # 确保 df 和 rolling_high/low 的索引是一致的\n", " # # 如果 df 的索引在此期间没有被修改过，这通常是安全的\n", " # df['flow_lg_elg_intensity_rolling_high'] = rolling_high\n", " # df['flow_lg_elg_intensity_rolling_low'] = rolling_low\n", "\n", " # # Step 3: Continue with the logic using the new columns\n", " # conditions_flow = [\n", " # df['flow_lg_elg_intensity'] > df['flow_lg_elg_intensity_rolling_high'],\n", " # df['flow_lg_elg_intensity'] < df['flow_lg_elg_intensity_rolling_low']\n", " # ]\n", " # choices_flow = [1, -1] # 1: 极端流入, -1: 极端流出\n", " # df['cat_extreme_flow'] = np.select(conditions_flow, choices_flow, default=0)\n", "\n", " # --- 筹码分布因子 ---\n", "\n", " # 6. 筹码集中度 (Chip Concentration)\n", " # 衡量筹码分布的紧密程度，例如 95% 与 5% 成本价的差距，相对于当前价格进行标准化\n", " # 检查 'close' 列是否存在且有效\n", " df['chip_concentration_range'] = (df['cost_95pct'] - df['cost_5pct']) / (df['close'] + epsilon)\n", "\n", " # 7. 筹码分布偏度 (Chip Distribution Skewness Proxy)\n", " # 比较中位数成本 (cost_50pct) 和加权平均成本 (weight_avg)\n", " # weight_avg > cost_50pct 暗示高成本区有较多筹码（右偏）\n", " df['chip_skewness'] = (df['weight_avg'] - df['cost_50pct']) / (df['cost_50pct'] + epsilon)\n", "\n", " # 8. 浮筹比例 (Floating Chips Proxy)\n", " # 衡量短期内（例如15%成本线以下）的筹码比例与总获利盘比例的关系\n", " # winner_rate 高但 cost_15pct 接近当前价，可能意味着大部分获利盘成本不高，易浮动\n", " # 这里简化为：获利盘比例 与 （当前价-15%成本价）/当前价 的乘积\n", " price_dist_cost15 = (df['close'] - df['cost_15pct']) / (df['close'] + epsilon)\n", " df['floating_chip_proxy'] = df['winner_rate'] * np.maximum(0, price_dist_cost15) # 只考虑价格高于15%成本线的情况\n", "\n", " # 9. 成本支撑强度变化 (Cost Support Strength Change)\n", " # 观察低位筹码成本（如 5% 或 15% 分位点）的变化率，看支撑位是上移还是下移\n", " df['cost_support_15pct_change'] = grouped['cost_15pct'].pct_change(1) * 100 # 百分比变化\n", "\n", " # 10. 获利盘压力/支撑区 (Categorical: Winner Rate Zone & Price Position)\n", " # 结合获利盘比例和当前价格相对于筹码成本的位置\n", " # 例如: 价格在 85% 成本线之上 & 获利盘 > 0.8 -> 高位派发风险区?\n", " # 价格在 15% 成本线之下 & 获利盘 < 0.2 -> 低位吸筹潜力区?\n", " conditions_winner = [\n", " (df['close'] > df['cost_85pct']) & (df['winner_rate'] > 0.8), # 高位 & 高获利盘\n", " (df['close'] < df['cost_15pct']) & (df['winner_rate'] < 0.2), # 低位 & 低获利盘\n", " (df['close'] > df['cost_50pct']) & (df['winner_rate'] > 0.5), # 中高位 & 多数获利\n", " (df['close'] < df['cost_50pct']) & (df['winner_rate'] < 0.5), # 中低位 & 多数亏损\n", " ]\n", " choices_winner = [1, 2, 3, 4] # 1:高风险区, 2:低潜力区, 3:中上获利区, 4:中下亏损区\n", " df['cat_winner_price_zone'] = np.select(conditions_winner, choices_winner, default=0) # 0: 其他\n", "\n", " # --- 结合因子 ---\n", "\n", " # 11. 主力行为与筹码结构一致性 (Flow-Chip Consistency)\n", " # 例如：主力净买入发生在价格接近下方筹码密集区（如 cost_15pct 到 cost_50pct）时\n", " price_near_low_support = (df['close'] > df['cost_15pct']) & (df['close'] < df['cost_50pct'])\n", " df['flow_chip_consistency'] = df['lg_elg_net_buy_vol'] * price_near_low_support.astype(int)\n", " # 可以进一步标准化或做成 categorical\n", "\n", " # 12. 获利了结压力/承接盘强度 (Profit-Taking Pressure vs Absorption)\n", " # 在高获利盘(winner_rate > 0.7)的情况下，观察主力资金是净流出（了结）还是净流入（高位换手/承接）\n", " high_winner_rate_flag = (df['winner_rate'] > 0.7).astype(int)\n", " df['profit_taking_vs_absorb'] = df['lg_elg_net_buy_vol'] * high_winner_rate_flag\n", " # 正值表示高获利盘下主力仍在买入（承接），负值表示主力在卖出（了结）\n", "\n", " # 清理临时列和可能产生的 NaN (可选，根据需要处理)\n", " cols_to_drop = ['lg_elg_net_buy_vol', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop',\n", " 'lg_elg_net_buy_vol_change', 'flow_lg_elg_intensity_rolling_high',\n", " 'flow_lg_elg_intensity_rolling_low']\n", " # df = df.drop(columns=cols_to_drop)\n", "\n", " window = 20\n", " df['_is_positive'] = (df['pct_chg'] > 0).astype(int)\n", " df['_is_negative'] = (df['pct_chg'] < 0).astype(int)\n", " df['cat_is_positive'] = (df['pct_chg'] > 0).astype(int)\n", "\n", " # 分离正负收益率 (用于计算各自的均值和平方均值)\n", " # 注意：这里我们保留原始收益率用于计算，而不是 clip 到 0\n", " df['_pos_returns'] = df['pct_chg'].where(df['pct_chg'] > 0, 0) # 非正设为0，便于求和\n", " df['_neg_returns'] = df['pct_chg'].where(df['pct_chg'] < 0, 0) # 非负设为0，便于求和\n", "\n", " # 计算收益率的平方 (用于计算 E[X^2])\n", " df['_pos_returns_sq'] = np.square(df['_pos_returns'])\n", " df['_neg_returns_sq'] = np.square(df['_neg_returns']) # 平方后负数变正\n", "\n", " # 4. 计算滚动统计量 (使用内置函数，速度较快)\n", " # 计算正收益日的统计量\n", " rolling_pos_count = grouped['_is_positive'].rolling(window, min_periods=max(1, window // 2)).sum()\n", " rolling_pos_sum = grouped['_pos_returns'].rolling(window, min_periods=max(1, window // 2)).sum()\n", " rolling_pos_sum_sq = grouped['_pos_returns_sq'].rolling(window, min_periods=max(1, window // 2)).sum()\n", "\n", " # 计算负收益日的统计量\n", " rolling_neg_count = grouped['_is_negative'].rolling(window, min_periods=max(1, window // 2)).sum()\n", " rolling_neg_sum = grouped['_neg_returns'].rolling(window, min_periods=max(1, window // 2)).sum()\n", " rolling_neg_sum_sq = grouped['_neg_returns_sq'].rolling(window, min_periods=max(1, window // 2)).sum()\n", "\n", " # 5. 计算方差和标准差\n", " pos_mean_sq = rolling_pos_sum_sq / rolling_pos_count\n", " pos_mean = rolling_pos_sum / rolling_pos_count\n", " pos_var = pos_mean_sq - np.square(pos_mean)\n", " pos_var = pos_var.where(rolling_pos_count >= 2, np.nan).clip(lower=0)\n", " upside_vol = np.sqrt(pos_var)\n", "\n", " neg_mean_sq = rolling_neg_sum_sq / rolling_neg_count\n", " neg_mean = rolling_neg_sum / rolling_neg_count # 注意 neg_mean 是负数\n", " neg_var = neg_mean_sq - np.square(neg_mean)\n", " neg_var = neg_var.where(rolling_neg_count >= 2, np.nan).clip(lower=0)\n", " downside_vol = np.sqrt(neg_var)\n", "\n", " # rolling 操作后结果带有 MultiIndex，需要去除股票代码层级以便合并\n", " df['upside_vol'] = upside_vol.reset_index(level=0, drop=True)\n", " df['downside_vol'] = downside_vol.reset_index(level=0, drop=True)\n", "\n", " df['vol_ratio'] = df['upside_vol'] / df['downside_vol']\n", " df['vol_ratio'] = df['vol_ratio'].replace([np.inf, -np.inf], np.nan).fillna(0) # 或 fillna(np.nan)\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'] = grouped['vol'].pct_change().rolling(window=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", " print(df.columns)\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", " window_high_volume = 5\n", " window_close_stddev = 20\n", " period_delta = 5\n", "\n", " # 计算每只股票的滚动协方差\n", " def calculate_rolling_cov(group):\n", " return group['high'].rolling(window_high_volume).cov(group['vol'])\n", "\n", " df['cov'] = grouped.apply(calculate_rolling_cov)\n", "\n", " # 计算每只股票的协方差差分\n", " def calculate_delta_cov(group):\n", " return group['cov'].diff(period_delta)\n", "\n", " df['delta_cov'] = grouped.apply(calculate_delta_cov)\n", "\n", " # 计算每只股票的滚动标准差\n", " def calculate_stddev_close(group):\n", " return group['close'].rolling(window_close_stddev).std()\n", "\n", " df['_stddev_close'] = grouped.apply(calculate_stddev_close)\n", " df['_rank_stddev'] = df.groupby('trade_date')['_stddev_close'].rank(pct=True)\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']))\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", " )\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 (使用 grouped)\n", " df['turnover_std'] = grouped['turnover_rate'].transform(lambda x: x.rolling(window=20).std())\n", " df['mv_volatility'] = grouped.apply(lambda x: x['turnover_std'] / x['log_circ_mv'])\n", "\n", " # 8. 市值成长性因子\n", " df['volume_growth'] = grouped['vol'].pct_change(periods=20)\n", " df['mv_growth'] = df['volume_growth'] / df['log_circ_mv']\n", "\n", " # AR 指标\n", " df[\"ar\"] = grouped.apply(\n", " lambda x: (x[\"high\"].div(x[\"open\"]).rolling(3).sum()) / (x[\"open\"].div(x[\"low\"]).rolling(3).sum()) * 100)\n", "\n", " # BR 指标\n", " df[\"pre_close\"] = grouped[\"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\"] = grouped.apply(lambda x: (x[\"br_up\"].rolling(3).sum()) / (x[\"br_down\"].rolling(3).sum()) * 100)\n", "\n", " # ARBR\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", " df.drop(\n", " columns=['_is_positive', '_is_negative', '_pos_returns', '_neg_returns', '_pos_returns_sq', '_neg_returns_sq'],\n", " 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_over_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_minus_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" ] }, { "cell_type": "code", "execution_count": 8, "id": "85c3e3d0235ffffa", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:34:15.568065Z", "start_time": "2025-04-10T13:33:00.592221Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Index(['ts_code', 'trade_date', 'open', 'close', 'high', 'low', 'vol',\n", " 'pct_chg', 'turnover_rate', 'pe_ttm', 'circ_mv', 'volume_ratio',\n", " 'is_st', 'up_limit', 'down_limit', 'buy_sm_vol', 'sell_sm_vol',\n", " 'buy_lg_vol', 'sell_lg_vol', 'buy_elg_vol', 'sell_elg_vol',\n", " 'net_mf_vol', 'his_low', 'his_high', 'cost_5pct', 'cost_15pct',\n", " 'cost_50pct', 'cost_85pct', 'cost_95pct', 'weight_avg', 'winner_rate',\n", " 'l2_code', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity',\n", " 'sm_net_buy_vol', 'flow_divergence_diff', 'flow_divergence_ratio',\n", " 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change',\n", " 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel',\n", " 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy',\n", " 'cost_support_15pct_change', 'cat_winner_price_zone',\n", " 'flow_chip_consistency', 'profit_taking_vs_absorb', '_is_positive',\n", " '_is_negative', 'cat_is_positive', '_pos_returns', '_neg_returns',\n", " '_pos_returns_sq', '_neg_returns_sq', 'upside_vol', 'downside_vol',\n", " 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate',\n", " 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike',\n", " 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike',\n", " 'vol_std_5', 'atr_14', 'atr_6', 'obv'],\n", " dtype='object')\n", "\n", "Index: 3148690 entries, 0 to 3148689\n", "Columns: 136 entries, ts_code to mv_momentum\n", "dtypes: bool(12), datetime64[ns](1), float64(117), int32(3), int64(1), object(2)\n", "memory usage: 2.9+ GB\n", "None\n" ] } ], "source": [ "import numpy as np\n", "\n", "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", " 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", "\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())" ] }, { "cell_type": "code", "execution_count": 9, "id": "f4f16d63ad18d1bc", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T13:34:15.976910Z", "start_time": "2025-04-10T13:34:15.967986Z" }, "jupyter": { "source_hidden": true } }, "outputs": [], "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" ] }, { "cell_type": "code", "execution_count": 35, "id": "40e6b68a91b30c79", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:45:38.780120Z", "start_time": "2025-04-10T14:45:38.545898Z" } }, "outputs": [], "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,\n", " log=True, val_data=None):\n", " dropped_features = []\n", "\n", " if val_data is None:\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", " else:\n", " train_data_split = train_data\n", " val_data_split = val_data\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", " if p_value < ks_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", "\n", "\n", "def time_series_quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99, window=60):\n", " df = df.copy()\n", " # 确保按股票和时间排序\n", " df = df.sort_values(['ts_code', 'trade_date'])\n", " grouped = df.groupby('ts_code')\n", " for col in features:\n", " # 对每个股票的时间序列计算滚动分位数\n", " rolling_lower = grouped[col].rolling(window=window, min_periods=window // 2).quantile(lower_quantile)\n", " rolling_upper = grouped[col].rolling(window=window, min_periods=window // 2).quantile(upper_quantile)\n", " # rolling结果带有多重索引，需要对齐\n", " rolling_lower = rolling_lower.reset_index(level=0, drop=True)\n", " rolling_upper = rolling_upper.reset_index(level=0, drop=True)\n", " # 应用 clip\n", " df[col] = np.clip(df[col], rolling_lower, rolling_upper)\n", " return df\n", "\n", "\n", "def cross_sectional_quantile_filter(df, features, lower_quantile=0.01, upper_quantile=0.99):\n", " df = df.copy()\n", " grouped = df.groupby('trade_date')\n", " for col in features:\n", " # 计算每日截面的分位数边界\n", " lower_bound = grouped[col].transform(lambda x: x.quantile(lower_quantile))\n", " upper_bound = grouped[col].transform(lambda x: x.quantile(upper_quantile))\n", " # 应用 clip\n", " df[col] = np.clip(df[col], lower_bound, upper_bound)\n", " return df\n", "\n", "def select_top_features_by_rankic(df: pd.DataFrame, feature_columns: list, n: int, target_column: str = 'future_return') -> list:\n", " \"\"\"\n", " 计算给定特征与目标列的 RankIC，并返回 RankIC 绝对值最高的 n 个特征。\n", "\n", " Args:\n", " df: 包含特征列和目标列的 Pandas DataFrame。\n", " feature_columns: 包含所有待评估特征列名的列表。\n", " n: 希望选取的 RankIC 绝对值最高的特征数量。\n", " target_column: 目标列的名称，用于计算 RankIC。默认为 'future_return'。\n", "\n", " Returns:\n", " 包含 RankIC 绝对值最高的 n 个特征列名的列表。\n", " \"\"\"\n", " numeric_columns = df.select_dtypes(include=['float64', 'int64']).columns\n", " numeric_columns = [col for col in numeric_columns if col in feature_columns]\n", " if target_column not in df.columns:\n", " raise ValueError(f\"目标列 '{target_column}' 不存在于 DataFrame 中。\")\n", "\n", " rankic_scores = {}\n", " for feature in numeric_columns:\n", " if feature not in df.columns:\n", " print(f\"警告: 特征列 '{feature}' 不存在于 DataFrame 中，已跳过。\")\n", " continue\n", "\n", " # 计算特征与目标列的 RankIC (斯皮尔曼相关系数)\n", " # dropna() 是为了处理缺失值，确保相关性计算不失败\n", " valid_data = df[[feature, target_column]].dropna()\n", " if len(valid_data) > 1: # 确保有足够的数据点进行相关性计算\n", " # 计算斯皮尔曼相关性\n", " correlation = valid_data[feature].corr(valid_data[target_column], method='spearman')\n", " rankic_scores[feature] = abs(correlation) # 使用绝对值来衡量相关性强度\n", " else:\n", " rankic_scores[feature] = 0 # 数据不足，RankIC设为0或跳过\n", "\n", " # 将 RankIC 分数转换为 Series 便于排序\n", " rankic_series = pd.Series(rankic_scores)\n", "\n", " # 按 RankIC 绝对值降序排序，选取前 n 个特征\n", " # handle case where n might be larger than available features\n", " n_actual = min(n, len(rankic_series))\n", " top_features = rankic_series.sort_values(ascending=False).head(n_actual).index.tolist()\n", " top_features = [col for col in feature_columns if col in top_features or col not in numeric_columns]\n", " return top_features" ] }, { "cell_type": "code", "execution_count": 11, "id": "1c46817a-b5dd-4bec-8bb4-e6e80bfd9d66", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:38:09.383969Z", "start_time": "2025-04-10T14:38:09.381447Z" } }, "outputs": [], "source": [ "# print(test_data.head()[['act_factor1', 'act_factor2', 'ts_code', 'trade_date']])" ] }, { "cell_type": "code", "execution_count": 12, "id": "da2bb202843d9275", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:38:09.436214Z", "start_time": "2025-04-10T14:38:09.426468Z" }, "jupyter": { "source_hidden": true } }, "outputs": [], "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", " # 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", " # 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", " if validation_days > 0:\n", " X_val = val_data_split[feature_columns]\n", " y_val = val_data_split['label']\n", " val_groups = val_data_split.groupby('trade_date').size().tolist()\n", " val_dataset = lgb.Dataset(\n", " X_val, label=y_val, group=val_groups,\n", " categorical_feature=categorical_feature\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", " else:\n", " model = lgb.train(\n", " params, train_dataset, num_boost_round=num_boost_round, 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, None" ] }, { "cell_type": "code", "execution_count": 13, "id": "ff19e3f1e051a489", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:50:14.928322Z", "start_time": "2025-04-10T14:48:29.721868Z" } }, "outputs": [], "source": [ "\n", "days = 5\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_return'] = df.groupby('ts_code')['pct_chg'].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=days, 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", "# )" ] }, { "cell_type": "code", "execution_count": 57, "id": "27dba27b2e108316", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:50:24.097167Z", "start_time": "2025-04-10T14:50:15.128276Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "2025-04-09 00:00:00\n" ] } ], "source": [ "def select_pre_zt_stocks_dynamic(stock_df):\n", " def select_stocks(group):\n", " max_stocks = 1500\n", " return group.nsmallest(max_stocks, 'log_circ_mv')\n", "\n", " stock_df = stock_df.groupby('trade_date', group_keys=False).apply(select_stocks)\n", " return stock_df\n", "\n", "\n", "pdf = select_pre_zt_stocks_dynamic(df[(df['trade_date'] >= '2022-01-01') & (df['trade_date'] <= '2029-04-07')])\n", "print(pdf['trade_date'].max())\n", "\n", "# pdf['label'] = pdf.groupby('trade_date', group_keys=False)['future_score'].transform(\n", "# lambda x: pd.qcut(x, q=20, labels=False, duplicates='drop')\n", "# )" ] }, { "cell_type": "code", "execution_count": 58, "id": "ca96fb81e17c4a90", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:50:25.416842Z", "start_time": "2025-04-10T14:50:24.111269Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['vol', 'pct_chg', 'turnover_rate', 'volume_ratio', 'winner_rate', 'lg_elg_net_buy_vol', 'flow_lg_elg_intensity', 'sm_net_buy_vol', 'total_buy_vol', 'lg_elg_buy_prop', 'flow_struct_buy_change', 'lg_elg_net_buy_vol_change', 'flow_lg_elg_accel', 'chip_concentration_range', 'chip_skewness', 'floating_chip_proxy', 'cost_support_15pct_change', 'cat_winner_price_zone', 'flow_chip_consistency', 'profit_taking_vs_absorb', 'cat_is_positive', 'upside_vol', 'downside_vol', 'vol_ratio', 'return_skew', 'return_kurtosis', 'volume_change_rate', 'cat_volume_breakout', 'turnover_deviation', 'cat_turnover_spike', 'avg_volume_ratio', 'cat_volume_ratio_breakout', 'vol_spike', 'vol_std_5', 'atr_14', 'atr_6', 'obv', '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', 'log_circ_mv', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_003', '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', 'volume_growth', 'mv_growth', 'arbr', 'momentum_factor', 'resonance_factor', 'log_close', 'cat_vol_spike', 'up', 'down', 'obv_maobv_6', 'std_return_5_over_std_return_90', 'std_return_90_minus_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_turnover_ratio', 'mv_adjusted_volume', 'mv_weighted_turnover', 'nonlinear_mv_volume', 'mv_volume_ratio', 'mv_momentum', 'industry_obv', 'industry_return_5', 'industry_return_20', 'industry__ema_5', 'industry__ema_13', 'industry__ema_20', 'industry__ema_60', '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" ] } ], "source": [ "pdf = pdf.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\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", "# feature_columns = [col for col in feature_columns if col not in ['ts_code', 'trade_date', 'vol_std_5', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_007', 'consecutive_up_limit', 'mv_volatility', 'volume_growth', 'mv_growth', 'arbr']]\n", "\n", "print(feature_columns)\n", "numeric_columns = pdf.select_dtypes(include=['float64', 'int64']).columns\n", "numeric_columns = [col for col in numeric_columns if col in feature_columns]\n", "\n", "\n", "# filter_index = pdf['future_volatility'].between(pdf['future_volatility'].quantile(0.01),\n", "# pdf['future_volatility'].quantile(0.99)) | filter_index" ] }, { "cell_type": "code", "execution_count": 59, "id": "81d4570663ae21d7", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:52:09.850326Z", "start_time": "2025-04-10T14:50:25.514971Z" } }, "outputs": [], "source": [ "\n", "# pdf = time_series_quantile_filter(pdf, numeric_columns)\n", "pdf = cross_sectional_quantile_filter(pdf, numeric_columns)\n", "pdf = cross_sectional_standardization(pdf, numeric_columns)\n", "\n", "pdf = pdf.sort_values(by=['ts_code', 'trade_date'])\n", "filter_index = pdf['future_return'].between(pdf['future_return'].quantile(0.01),\n", " pdf['future_return'].quantile(0.99))" ] }, { "cell_type": "code", "execution_count": 60, "id": "92428d543f4727ad", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:52:10.203284Z", "start_time": "2025-04-10T14:52:09.941361Z" } }, "outputs": [ { "data": { "text/plain": [ "14" ] }, "execution_count": 60, "metadata": {}, "output_type": "execute_result" } ], "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()" ] }, { "cell_type": "code", "execution_count": 61, "id": "8f134d435f71e9e2", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T15:08:28.458002Z", "start_time": "2025-04-10T15:08:28.217183Z" } }, "outputs": [], "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, params=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 + 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[max(0, start - days + 1): start + train_days - days + 1]\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[df['trade_date'].isin(train_dates)]\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", " # val_data=df[filter_index & (df['trade_date'] ==\n", " # unique_dates[start + train_days - days + 1])])\n", " feature_columns = feature_columns_origin\n", " # feature_columns = select_top_features_by_rankic(train_data, feature_columns, n=50)\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", " test_data = test_data.dropna(subset=feature_columns)\n", " test_data = test_data.reset_index(drop=True)\n", " print(\n", " f\"train_data最大日期: {train_data['trade_date'].max().strftime('%Y-%m-%d')}, 训练天数{train_data['trade_date'].nunique()}\")\n", " print(f\"test_data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", " params['label_gain'] = label_gain\n", "\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", " # 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", " # params['feature_contri'] = feature_contri\n", " try:\n", " model, _, _ = train_light_model(train_data.dropna(subset=['label']),\n", " 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=36, validation_days=validation_days,\n", " print_feature_importance=False, use_pca=False)\n", " except Exception as e:\n", " print(e)\n", " print(train_data['label'].unique().tolist())\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", " # score_df['score'] = score_df['log_circ_mv']\n", " top_stock_ = score_df.nlargest(1, columns='score').reset_index(level=0)\n", " final_selection = top_stock_\n", " # final_selection = final_selection.sort_values(['log_circ_mv']).head(1)\n", " predictions_list.append(final_selection[['trade_date', 'score', 'ts_code']])\n", "\n", " final_predictions = pd.concat(predictions_list, ignore_index=True)\n", " return final_predictions\n", "\n" ] }, { "cell_type": "code", "execution_count": 62, "id": "63235069-dc59-48fb-961a-e80373e41a61", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T15:15:47.062878Z", "start_time": "2025-04-10T15:11:48.632695Z" }, "editable": true, "scrolled": true, "slideshow": { "slide_type": "" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "finish\n", "train_data最大日期: 2022-01-11, 训练天数5\n", "test_data最大日期: 2022-01-18\n", "划分后的训练集大小: 6946, 验证集大小: 1391\n", "train_data最大日期: 2022-01-12, 训练天数5\n", "test_data最大日期: 2022-01-19\n", "划分后的训练集大小: 6946, 验证集大小: 1390\n", "train_data最大日期: 2022-01-13, 训练天数5\n", "test_data最大日期: 2022-01-20\n", "划分后的训练集大小: 6943, 验证集大小: 1387\n", "train_data最大日期: 2022-01-14, 训练天数5\n", "test_data最大日期: 2022-01-21\n", "划分后的训练集大小: 6932, 验证集大小: 1377\n", "train_data最大日期: 2022-01-17, 训练天数5\n", "test_data最大日期: 2022-01-24\n", "划分后的训练集大小: 6931, 验证集大小: 1386\n", "train_data最大日期: 2022-01-18, 训练天数5\n", "test_data最大日期: 2022-01-25\n", "划分后的训练集大小: 6928, 验证集大小: 1388\n", "train_data最大日期: 2022-01-19, 训练天数5\n", "test_data最大日期: 2022-01-26\n", "划分后的训练集大小: 6915, 验证集大小: 1377\n", "train_data最大日期: 2022-01-20, 训练天数5\n", "test_data最大日期: 2022-01-27\n", "划分后的训练集大小: 6894, 验证集大小: 1366\n", "train_data最大日期: 2022-01-21, 训练天数5\n", "test_data最大日期: 2022-01-28\n", "划分后的训练集大小: 6904, 验证集大小: 1387\n", "train_data最大日期: 2022-01-24, 训练天数5\n", "test_data最大日期: 2022-02-07\n", "划分后的训练集大小: 6910, 验证集大小: 1392\n", "train_data最大日期: 2022-01-25, 训练天数5\n", "test_data最大日期: 2022-02-08\n", "划分后的训练集大小: 6918, 验证集大小: 1396\n", "train_data最大日期: 2022-01-26, 训练天数5\n", "test_data最大日期: 2022-02-09\n", "划分后的训练集大小: 6939, 验证集大小: 1398\n", "train_data最大日期: 2022-01-27, 训练天数5\n", "test_data最大日期: 2022-02-10\n", "划分后的训练集大小: 6949, 验证集大小: 1376\n", "train_data最大日期: 2022-01-28, 训练天数5\n", "test_data最大日期: 2022-02-11\n", "划分后的训练集大小: 6950, 验证集大小: 1388\n", "train_data最大日期: 2022-02-07, 训练天数5\n", "test_data最大日期: 2022-02-14\n", "划分后的训练集大小: 6947, 验证集大小: 1389\n", "train_data最大日期: 2022-02-08, 训练天数5\n", "test_data最大日期: 2022-02-15\n", "划分后的训练集大小: 6940, 验证集大小: 1389\n", "train_data最大日期: 2022-02-09, 训练天数5\n", "test_data最大日期: 2022-02-16\n", "划分后的训练集大小: 6933, 验证集大小: 1391\n", "train_data最大日期: 2022-02-10, 训练天数5\n", "test_data最大日期: 2022-02-17\n", "划分后的训练集大小: 6960, 验证集大小: 1403\n", "train_data最大日期: 2022-02-11, 训练天数5\n", "test_data最大日期: 2022-02-18\n", "划分后的训练集大小: 6978, 验证集大小: 1406\n", "train_data最大日期: 2022-02-14, 训练天数5\n", "test_data最大日期: 2022-02-21\n", "划分后的训练集大小: 6991, 验证集大小: 1402\n", "train_data最大日期: 2022-02-15, 训练天数5\n", "test_data最大日期: 2022-02-22\n", "划分后的训练集大小: 6997, 验证集大小: 1395\n", "train_data最大日期: 2022-02-16, 训练天数5\n", "test_data最大日期: 2022-02-23\n", "划分后的训练集大小: 7003, 验证集大小: 1397\n", "train_data最大日期: 2022-02-17, 训练天数5\n", "test_data最大日期: 2022-02-24\n", "划分后的训练集大小: 7001, 验证集大小: 1401\n", "train_data最大日期: 2022-02-18, 训练天数5\n", "test_data最大日期: 2022-02-25\n", "划分后的训练集大小: 6996, 验证集大小: 1401\n", "train_data最大日期: 2022-02-21, 训练天数5\n", "test_data最大日期: 2022-02-28\n", "划分后的训练集大小: 6990, 验证集大小: 1396\n", "train_data最大日期: 2022-02-22, 训练天数5\n", "test_data最大日期: 2022-03-01\n", "划分后的训练集大小: 6989, 验证集大小: 1394\n", "train_data最大日期: 2022-02-23, 训练天数5\n", "test_data最大日期: 2022-03-02\n", "划分后的训练集大小: 6996, 验证集大小: 1404\n", "train_data最大日期: 2022-02-24, 训练天数5\n", "test_data最大日期: 2022-03-03\n", "划分后的训练集大小: 6987, 验证集大小: 1392\n", "train_data最大日期: 2022-02-25, 训练天数5\n", "test_data最大日期: 2022-03-04\n", "划分后的训练集大小: 6989, 验证集大小: 1403\n", "train_data最大日期: 2022-02-28, 训练天数5\n", "test_data最大日期: 2022-03-07\n", "划分后的训练集大小: 6988, 验证集大小: 1395\n", "train_data最大日期: 2022-03-01, 训练天数5\n", "test_data最大日期: 2022-03-08\n", "划分后的训练集大小: 6993, 验证集大小: 1399\n", "train_data最大日期: 2022-03-02, 训练天数5\n", "test_data最大日期: 2022-03-09\n", "划分后的训练集大小: 6985, 验证集大小: 1396\n", "train_data最大日期: 2022-03-03, 训练天数5\n", "test_data最大日期: 2022-03-10\n", "划分后的训练集大小: 6979, 验证集大小: 1386\n", "train_data最大日期: 2022-03-04, 训练天数5\n", "test_data最大日期: 2022-03-11\n", "划分后的训练集大小: 6976, 验证集大小: 1400\n", "train_data最大日期: 2022-03-07, 训练天数5\n", "test_data最大日期: 2022-03-14\n", "划分后的训练集大小: 6976, 验证集大小: 1395\n", "train_data最大日期: 2022-03-08, 训练天数5\n", "test_data最大日期: 2022-03-15\n", "划分后的训练集大小: 6964, 验证集大小: 1387\n", "train_data最大日期: 2022-03-09, 训练天数5\n", "test_data最大日期: 2022-03-16\n", "划分后的训练集大小: 6963, 验证集大小: 1395\n", "train_data最大日期: 2022-03-10, 训练天数5\n", "test_data最大日期: 2022-03-17\n", "划分后的训练集大小: 6978, 验证集大小: 1401\n", "train_data最大日期: 2022-03-11, 训练天数5\n", "test_data最大日期: 2022-03-18\n", "划分后的训练集大小: 6987, 验证集大小: 1409\n", "train_data最大日期: 2022-03-14, 训练天数5\n", "test_data最大日期: 2022-03-21\n", "划分后的训练集大小: 6996, 验证集大小: 1404\n", "train_data最大日期: 2022-03-15, 训练天数5\n", "test_data最大日期: 2022-03-22\n", "划分后的训练集大小: 6994, 验证集大小: 1385\n", "train_data最大日期: 2022-03-16, 训练天数5\n", "test_data最大日期: 2022-03-23\n", "划分后的训练集大小: 7002, 验证集大小: 1403\n", "train_data最大日期: 2022-03-17, 训练天数5\n", "test_data最大日期: 2022-03-24\n", "划分后的训练集大小: 7005, 验证集大小: 1404\n", "train_data最大日期: 2022-03-18, 训练天数5\n", "test_data最大日期: 2022-03-25\n", "划分后的训练集大小: 6999, 验证集大小: 1403\n", "train_data最大日期: 2022-03-21, 训练天数5\n", "test_data最大日期: 2022-03-28\n", "划分后的训练集大小: 6992, 验证集大小: 1397\n", "train_data最大日期: 2022-03-22, 训练天数5\n", "test_data最大日期: 2022-03-29\n", "划分后的训练集大小: 7018, 验证集大小: 1411\n", "train_data最大日期: 2022-03-23, 训练天数5\n", "test_data最大日期: 2022-03-30\n", "划分后的训练集大小: 7022, 验证集大小: 1407\n", "train_data最大日期: 2022-03-24, 训练天数5\n", "test_data最大日期: 2022-03-31\n", "划分后的训练集大小: 7024, 验证集大小: 1406\n", "train_data最大日期: 2022-03-25, 训练天数5\n", "test_data最大日期: 2022-04-01\n", "划分后的训练集大小: 7015, 验证集大小: 1394\n", "train_data最大日期: 2022-03-28, 训练天数5\n", "test_data最大日期: 2022-04-06\n", "划分后的训练集大小: 7018, 验证集大小: 1400\n", "train_data最大日期: 2022-03-29, 训练天数5\n", "test_data最大日期: 2022-04-07\n", "划分后的训练集大小: 7016, 验证集大小: 1409\n", "train_data最大日期: 2022-03-30, 训练天数5\n", "test_data最大日期: 2022-04-08\n", "划分后的训练集大小: 7011, 验证集大小: 1402\n", "train_data最大日期: 2022-03-31, 训练天数5\n", "test_data最大日期: 2022-04-11\n", "划分后的训练集大小: 7009, 验证集大小: 1404\n", "train_data最大日期: 2022-04-01, 训练天数5\n", "test_data最大日期: 2022-04-12\n", "划分后的训练集大小: 7017, 验证集大小: 1402\n", "train_data最大日期: 2022-04-06, 训练天数5\n", "test_data最大日期: 2022-04-13\n", "划分后的训练集大小: 7001, 验证集大小: 1384\n", "train_data最大日期: 2022-04-07, 训练天数5\n", "test_data最大日期: 2022-04-14\n", "划分后的训练集大小: 6992, 验证集大小: 1400\n", "train_data最大日期: 2022-04-08, 训练天数5\n", "test_data最大日期: 2022-04-15\n", "划分后的训练集大小: 6989, 验证集大小: 1399\n", "train_data最大日期: 2022-04-11, 训练天数5\n", "test_data最大日期: 2022-04-18\n", "划分后的训练集大小: 6985, 验证集大小: 1400\n", "train_data最大日期: 2022-04-12, 训练天数5\n", "test_data最大日期: 2022-04-19\n", "划分后的训练集大小: 6981, 验证集大小: 1398\n", "train_data最大日期: 2022-04-13, 训练天数5\n", "test_data最大日期: 2022-04-20\n", "划分后的训练集大小: 6998, 验证集大小: 1401\n", "train_data最大日期: 2022-04-14, 训练天数5\n", "test_data最大日期: 2022-04-21\n", "划分后的训练集大小: 6987, 验证集大小: 1389\n", "train_data最大日期: 2022-04-15, 训练天数5\n", "test_data最大日期: 2022-04-22\n", "划分后的训练集大小: 6985, 验证集大小: 1397\n", "train_data最大日期: 2022-04-18, 训练天数5\n", "test_data最大日期: 2022-04-25\n", "划分后的训练集大小: 6821, 验证集大小: 1236\n", "train_data最大日期: 2022-04-19, 训练天数5\n", "test_data最大日期: 2022-04-26\n", "划分后的训练集大小: 6232, 验证集大小: 809\n", "train_data最大日期: 2022-04-20, 训练天数5\n", "test_data最大日期: 2022-04-27\n", "划分后的训练集大小: 5968, 验证集大小: 1137\n", "train_data最大日期: 2022-04-21, 训练天数5\n", "test_data最大日期: 2022-04-28\n", "划分后的训练集大小: 5774, 验证集大小: 1195\n", "train_data最大日期: 2022-04-22, 训练天数5\n", "test_data最大日期: 2022-04-29\n", "划分后的训练集大小: 5727, 验证集大小: 1350\n", "train_data最大日期: 2022-04-25, 训练天数5\n", "test_data最大日期: 2022-05-05\n", "划分后的训练集大小: 5877, 验证集大小: 1386\n", "train_data最大日期: 2022-04-26, 训练天数5\n", "test_data最大日期: 2022-05-06\n", "划分后的训练集大小: 6423, 验证集大小: 1355\n", "train_data最大日期: 2022-04-27, 训练天数5\n", "test_data最大日期: 2022-05-09\n", "划分后的训练集大小: 6661, 验证集大小: 1375\n", "train_data最大日期: 2022-04-28, 训练天数5\n", "test_data最大日期: 2022-05-10\n", "划分后的训练集大小: 6830, 验证集大小: 1364\n", "train_data最大日期: 2022-04-29, 训练天数5\n", "test_data最大日期: 2022-05-11\n", "划分后的训练集大小: 6869, 验证集大小: 1389\n", "train_data最大日期: 2022-05-05, 训练天数5\n", "test_data最大日期: 2022-05-12\n", "划分后的训练集大小: 6886, 验证集大小: 1403\n", "train_data最大日期: 2022-05-06, 训练天数5\n", "test_data最大日期: 2022-05-13\n", "划分后的训练集大小: 6929, 验证集大小: 1398\n", "train_data最大日期: 2022-05-09, 训练天数5\n", "test_data最大日期: 2022-05-16\n", "划分后的训练集大小: 6959, 验证集大小: 1405\n", "train_data最大日期: 2022-05-10, 训练天数5\n", "test_data最大日期: 2022-05-17\n", "划分后的训练集大小: 7000, 验证集大小: 1405\n", "train_data最大日期: 2022-05-11, 训练天数5\n", "test_data最大日期: 2022-05-18\n", "划分后的训练集大小: 7006, 验证集大小: 1395\n", "train_data最大日期: 2022-05-12, 训练天数5\n", "test_data最大日期: 2022-05-19\n", "划分后的训练集大小: 7002, 验证集大小: 1399\n", "train_data最大日期: 2022-05-13, 训练天数5\n", "test_data最大日期: 2022-05-20\n", "划分后的训练集大小: 7005, 验证集大小: 1401\n", "train_data最大日期: 2022-05-16, 训练天数5\n", "test_data最大日期: 2022-05-23\n", "划分后的训练集大小: 6995, 验证集大小: 1395\n", "train_data最大日期: 2022-05-17, 训练天数5\n", "test_data最大日期: 2022-05-24\n", "划分后的训练集大小: 6984, 验证集大小: 1394\n", "train_data最大日期: 2022-05-18, 训练天数5\n", "test_data最大日期: 2022-05-25\n", "划分后的训练集大小: 6975, 验证集大小: 1386\n", "train_data最大日期: 2022-05-19, 训练天数5\n", "test_data最大日期: 2022-05-26\n", "划分后的训练集大小: 6980, 验证集大小: 1404\n", "train_data最大日期: 2022-05-20, 训练天数5\n", "test_data最大日期: 2022-05-27\n", "划分后的训练集大小: 6978, 验证集大小: 1399\n", "train_data最大日期: 2022-05-23, 训练天数5\n", "test_data最大日期: 2022-05-30\n", "划分后的训练集大小: 6984, 验证集大小: 1401\n", "train_data最大日期: 2022-05-24, 训练天数5\n", "test_data最大日期: 2022-05-31\n", "划分后的训练集大小: 6987, 验证集大小: 1397\n", "train_data最大日期: 2022-05-25, 训练天数5\n", "test_data最大日期: 2022-06-01\n", "划分后的训练集大小: 6999, 验证集大小: 1398\n", "train_data最大日期: 2022-05-26, 训练天数5\n", "test_data最大日期: 2022-06-02\n", "划分后的训练集大小: 6989, 验证集大小: 1394\n", "train_data最大日期: 2022-05-27, 训练天数5\n", "test_data最大日期: 2022-06-06\n", "划分后的训练集大小: 6991, 验证集大小: 1401\n", "train_data最大日期: 2022-05-30, 训练天数5\n", "test_data最大日期: 2022-06-07\n", "划分后的训练集大小: 6990, 验证集大小: 1400\n", "train_data最大日期: 2022-05-31, 训练天数5\n", "test_data最大日期: 2022-06-08\n", "划分后的训练集大小: 6992, 验证集大小: 1399\n", "train_data最大日期: 2022-06-01, 训练天数5\n", "test_data最大日期: 2022-06-09\n", "划分后的训练集大小: 6992, 验证集大小: 1398\n", "train_data最大日期: 2022-06-02, 训练天数5\n", "test_data最大日期: 2022-06-10\n", "划分后的训练集大小: 6997, 验证集大小: 1399\n", "train_data最大日期: 2022-06-06, 训练天数5\n", "test_data最大日期: 2022-06-13\n", "划分后的训练集大小: 6990, 验证集大小: 1394\n", "train_data最大日期: 2022-06-07, 训练天数5\n", "test_data最大日期: 2022-06-14\n", "划分后的训练集大小: 6980, 验证集大小: 1390\n", "train_data最大日期: 2022-06-08, 训练天数5\n", "test_data最大日期: 2022-06-15\n", "划分后的训练集大小: 6974, 验证集大小: 1393\n", "train_data最大日期: 2022-06-09, 训练天数5\n", "test_data最大日期: 2022-06-16\n", "划分后的训练集大小: 6964, 验证集大小: 1388\n", "train_data最大日期: 2022-06-10, 训练天数5\n", "test_data最大日期: 2022-06-17\n", "划分后的训练集大小: 6953, 验证集大小: 1388\n", "train_data最大日期: 2022-06-13, 训练天数5\n", "test_data最大日期: 2022-06-20\n", "划分后的训练集大小: 6945, 验证集大小: 1386\n", "train_data最大日期: 2022-06-14, 训练天数5\n", "test_data最大日期: 2022-06-21\n", "划分后的训练集大小: 6948, 验证集大小: 1393\n", "train_data最大日期: 2022-06-15, 训练天数5\n", "test_data最大日期: 2022-06-22\n", "划分后的训练集大小: 6942, 验证集大小: 1387\n", "train_data最大日期: 2022-06-16, 训练天数5\n", "test_data最大日期: 2022-06-23\n", "划分后的训练集大小: 6940, 验证集大小: 1386\n", "train_data最大日期: 2022-06-17, 训练天数5\n", "test_data最大日期: 2022-06-24\n", "划分后的训练集大小: 6940, 验证集大小: 1388\n", "train_data最大日期: 2022-06-20, 训练天数5\n", "test_data最大日期: 2022-06-27\n", "划分后的训练集大小: 6942, 验证集大小: 1388\n", "train_data最大日期: 2022-06-21, 训练天数5\n", "test_data最大日期: 2022-06-28\n", "划分后的训练集大小: 6933, 验证集大小: 1384\n", "train_data最大日期: 2022-06-22, 训练天数5\n", "test_data最大日期: 2022-06-29\n", "划分后的训练集大小: 6934, 验证集大小: 1388\n", "train_data最大日期: 2022-06-23, 训练天数5\n", "test_data最大日期: 2022-06-30\n", "划分后的训练集大小: 6923, 验证集大小: 1375\n", "train_data最大日期: 2022-06-24, 训练天数5\n", "test_data最大日期: 2022-07-01\n", "划分后的训练集大小: 6932, 验证集大小: 1397\n", "train_data最大日期: 2022-06-27, 训练天数5\n", "test_data最大日期: 2022-07-04\n", "划分后的训练集大小: 6944, 验证集大小: 1400\n", "train_data最大日期: 2022-06-28, 训练天数5\n", "test_data最大日期: 2022-07-05\n", "划分后的训练集大小: 6953, 验证集大小: 1393\n", "train_data最大日期: 2022-06-29, 训练天数5\n", "test_data最大日期: 2022-07-06\n", "划分后的训练集大小: 6963, 验证集大小: 1398\n", "train_data最大日期: 2022-06-30, 训练天数5\n", "test_data最大日期: 2022-07-07\n", "划分后的训练集大小: 6991, 验证集大小: 1403\n", "train_data最大日期: 2022-07-01, 训练天数5\n", "test_data最大日期: 2022-07-08\n", "划分后的训练集大小: 6995, 验证集大小: 1401\n", "train_data最大日期: 2022-07-04, 训练天数5\n", "test_data最大日期: 2022-07-11\n", "划分后的训练集大小: 7001, 验证集大小: 1406\n", "train_data最大日期: 2022-07-05, 训练天数5\n", "test_data最大日期: 2022-07-12\n", "划分后的训练集大小: 7014, 验证集大小: 1406\n", "train_data最大日期: 2022-07-06, 训练天数5\n", "test_data最大日期: 2022-07-13\n", "划分后的训练集大小: 7021, 验证集大小: 1405\n", "train_data最大日期: 2022-07-07, 训练天数5\n", "test_data最大日期: 2022-07-14\n", "划分后的训练集大小: 7028, 验证集大小: 1410\n", "train_data最大日期: 2022-07-08, 训练天数5\n", "test_data最大日期: 2022-07-15\n", "划分后的训练集大小: 7035, 验证集大小: 1408\n", "train_data最大日期: 2022-07-11, 训练天数5\n", "test_data最大日期: 2022-07-18\n", "划分后的训练集大小: 7037, 验证集大小: 1408\n", "train_data最大日期: 2022-07-12, 训练天数5\n", "test_data最大日期: 2022-07-19\n", "划分后的训练集大小: 7023, 验证集大小: 1392\n", "train_data最大日期: 2022-07-13, 训练天数5\n", "test_data最大日期: 2022-07-20\n", "划分后的训练集大小: 7009, 验证集大小: 1391\n", "train_data最大日期: 2022-07-14, 训练天数5\n", "test_data最大日期: 2022-07-21\n", "划分后的训练集大小: 6999, 验证集大小: 1400\n", "train_data最大日期: 2022-07-15, 训练天数5\n", "test_data最大日期: 2022-07-22\n", "划分后的训练集大小: 6986, 验证集大小: 1395\n", "train_data最大日期: 2022-07-18, 训练天数5\n", "test_data最大日期: 2022-07-25\n", "划分后的训练集大小: 6988, 验证集大小: 1410\n", "train_data最大日期: 2022-07-19, 训练天数5\n", "test_data最大日期: 2022-07-26\n", "划分后的训练集大小: 7009, 验证集大小: 1413\n", "train_data最大日期: 2022-07-20, 训练天数5\n", "test_data最大日期: 2022-07-27\n", "划分后的训练集大小: 7029, 验证集大小: 1411\n", "train_data最大日期: 2022-07-21, 训练天数5\n", "test_data最大日期: 2022-07-28\n", "划分后的训练集大小: 7038, 验证集大小: 1409\n", "train_data最大日期: 2022-07-22, 训练天数5\n", "test_data最大日期: 2022-07-29\n", "划分后的训练集大小: 7054, 验证集大小: 1411\n", "train_data最大日期: 2022-07-25, 训练天数5\n", "test_data最大日期: 2022-08-01\n", "划分后的训练集大小: 7049, 验证集大小: 1405\n", "train_data最大日期: 2022-07-26, 训练天数5\n", "test_data最大日期: 2022-08-02\n", "划分后的训练集大小: 7040, 验证集大小: 1404\n", "train_data最大日期: 2022-07-27, 训练天数5\n", "test_data最大日期: 2022-08-03\n", "划分后的训练集大小: 7031, 验证集大小: 1402\n", "train_data最大日期: 2022-07-28, 训练天数5\n", "test_data最大日期: 2022-08-04\n", "划分后的训练集大小: 7029, 验证集大小: 1407\n", "train_data最大日期: 2022-07-29, 训练天数5\n", "test_data最大日期: 2022-08-05\n", "划分后的训练集大小: 7019, 验证集大小: 1401\n", "train_data最大日期: 2022-08-01, 训练天数5\n", "test_data最大日期: 2022-08-08\n", "划分后的训练集大小: 7025, 验证集大小: 1411\n", "train_data最大日期: 2022-08-02, 训练天数5\n", "test_data最大日期: 2022-08-09\n", "划分后的训练集大小: 7025, 验证集大小: 1404\n", "train_data最大日期: 2022-08-03, 训练天数5\n", "test_data最大日期: 2022-08-10\n", "划分后的训练集大小: 7027, 验证集大小: 1404\n", "train_data最大日期: 2022-08-04, 训练天数5\n", "test_data最大日期: 2022-08-11\n", "划分后的训练集大小: 7027, 验证集大小: 1407\n", "train_data最大日期: 2022-08-05, 训练天数5\n", "test_data最大日期: 2022-08-12\n", "划分后的训练集大小: 7031, 验证集大小: 1405\n", "train_data最大日期: 2022-08-08, 训练天数5\n", "test_data最大日期: 2022-08-15\n", "划分后的训练集大小: 7026, 验证集大小: 1406\n", "train_data最大日期: 2022-08-09, 训练天数5\n", "test_data最大日期: 2022-08-16\n", "划分后的训练集大小: 7028, 验证集大小: 1406\n", "train_data最大日期: 2022-08-10, 训练天数5\n", "test_data最大日期: 2022-08-17\n", "划分后的训练集大小: 7035, 验证集大小: 1411\n", "train_data最大日期: 2022-08-11, 训练天数5\n", "test_data最大日期: 2022-08-18\n", "划分后的训练集大小: 7032, 验证集大小: 1404\n", "train_data最大日期: 2022-08-12, 训练天数5\n", "test_data最大日期: 2022-08-19\n", "划分后的训练集大小: 7032, 验证集大小: 1405\n", "train_data最大日期: 2022-08-15, 训练天数5\n", "test_data最大日期: 2022-08-22\n", "划分后的训练集大小: 7035, 验证集大小: 1409\n", "train_data最大日期: 2022-08-16, 训练天数5\n", "test_data最大日期: 2022-08-23\n", "划分后的训练集大小: 7036, 验证集大小: 1407\n", "train_data最大日期: 2022-08-17, 训练天数5\n", "test_data最大日期: 2022-08-24\n", "划分后的训练集大小: 7036, 验证集大小: 1411\n", "train_data最大日期: 2022-08-18, 训练天数5\n", "test_data最大日期: 2022-08-25\n", "划分后的训练集大小: 7027, 验证集大小: 1395\n", "train_data最大日期: 2022-08-19, 训练天数5\n", "test_data最大日期: 2022-08-26\n", "划分后的训练集大小: 7025, 验证集大小: 1403\n", "train_data最大日期: 2022-08-22, 训练天数5\n", "test_data最大日期: 2022-08-29\n", "划分后的训练集大小: 7025, 验证集大小: 1409\n", "train_data最大日期: 2022-08-23, 训练天数5\n", "test_data最大日期: 2022-08-30\n", "划分后的训练集大小: 7011, 验证集大小: 1393\n", "train_data最大日期: 2022-08-24, 训练天数5\n", "test_data最大日期: 2022-08-31\n", "划分后的训练集大小: 6984, 验证集大小: 1384\n", "train_data最大日期: 2022-08-25, 训练天数5\n", "test_data最大日期: 2022-09-01\n", "划分后的训练集大小: 6971, 验证集大小: 1382\n", "train_data最大日期: 2022-08-26, 训练天数5\n", "test_data最大日期: 2022-09-02\n", "划分后的训练集大小: 6977, 验证集大小: 1409\n", "train_data最大日期: 2022-08-29, 训练天数5\n", "test_data最大日期: 2022-09-05\n", "划分后的训练集大小: 6970, 验证集大小: 1402\n", "train_data最大日期: 2022-08-30, 训练天数5\n", "test_data最大日期: 2022-09-06\n", "划分后的训练集大小: 6982, 验证集大小: 1405\n", "train_data最大日期: 2022-08-31, 训练天数5\n", "test_data最大日期: 2022-09-07\n", "划分后的训练集大小: 7000, 验证集大小: 1402\n", "train_data最大日期: 2022-09-01, 训练天数5\n", "test_data最大日期: 2022-09-08\n", "划分后的训练集大小: 7020, 验证集大小: 1402\n", "train_data最大日期: 2022-09-02, 训练天数5\n", "test_data最大日期: 2022-09-09\n", "划分后的训练集大小: 7021, 验证集大小: 1410\n", "train_data最大日期: 2022-09-05, 训练天数5\n", "test_data最大日期: 2022-09-13\n", "划分后的训练集大小: 7027, 验证集大小: 1408\n", "train_data最大日期: 2022-09-06, 训练天数5\n", "test_data最大日期: 2022-09-14\n", "划分后的训练集大小: 7019, 验证集大小: 1397\n", "train_data最大日期: 2022-09-07, 训练天数5\n", "test_data最大日期: 2022-09-15\n", "划分后的训练集大小: 7008, 验证集大小: 1391\n", "train_data最大日期: 2022-09-08, 训练天数5\n", "test_data最大日期: 2022-09-16\n", "划分后的训练集大小: 7000, 验证集大小: 1394\n", "train_data最大日期: 2022-09-09, 训练天数5\n", "test_data最大日期: 2022-09-19\n", "划分后的训练集大小: 6991, 验证集大小: 1401\n", "train_data最大日期: 2022-09-13, 训练天数5\n", "test_data最大日期: 2022-09-20\n", "划分后的训练集大小: 6989, 验证集大小: 1406\n", "train_data最大日期: 2022-09-14, 训练天数5\n", "test_data最大日期: 2022-09-21\n", "划分后的训练集大小: 6998, 验证集大小: 1406\n", "train_data最大日期: 2022-09-15, 训练天数5\n", "test_data最大日期: 2022-09-22\n", "划分后的训练集大小: 7014, 验证集大小: 1407\n", "train_data最大日期: 2022-09-16, 训练天数5\n", "test_data最大日期: 2022-09-23\n", "划分后的训练集大小: 7028, 验证集大小: 1408\n", "train_data最大日期: 2022-09-19, 训练天数5\n", "test_data最大日期: 2022-09-26\n", "划分后的训练集大小: 7031, 验证集大小: 1404\n", "train_data最大日期: 2022-09-20, 训练天数5\n", "test_data最大日期: 2022-09-27\n", "划分后的训练集大小: 7029, 验证集大小: 1404\n", "train_data最大日期: 2022-09-21, 训练天数5\n", "test_data最大日期: 2022-09-28\n", "划分后的训练集大小: 7014, 验证集大小: 1391\n", "train_data最大日期: 2022-09-22, 训练天数5\n", "test_data最大日期: 2022-09-29\n", "划分后的训练集大小: 6996, 验证集大小: 1389\n", "train_data最大日期: 2022-09-23, 训练天数5\n", "test_data最大日期: 2022-09-30\n", "划分后的训练集大小: 6980, 验证集大小: 1392\n", "train_data最大日期: 2022-09-26, 训练天数5\n", "test_data最大日期: 2022-10-10\n", "划分后的训练集大小: 6952, 验证集大小: 1376\n", "train_data最大日期: 2022-09-27, 训练天数5\n", "test_data最大日期: 2022-10-11\n", "划分后的训练集大小: 6921, 验证集大小: 1373\n", "train_data最大日期: 2022-09-28, 训练天数5\n", "test_data最大日期: 2022-10-12\n", "划分后的训练集大小: 6919, 验证集大小: 1389\n", "train_data最大日期: 2022-09-29, 训练天数5\n", "test_data最大日期: 2022-10-13\n", "划分后的训练集大小: 6925, 验证集大小: 1395\n", "train_data最大日期: 2022-09-30, 训练天数5\n", "test_data最大日期: 2022-10-14\n", "划分后的训练集大小: 6930, 验证集大小: 1397\n", "train_data最大日期: 2022-10-10, 训练天数5\n", "test_data最大日期: 2022-10-17\n", "划分后的训练集大小: 6936, 验证集大小: 1382\n", "train_data最大日期: 2022-10-11, 训练天数5\n", "test_data最大日期: 2022-10-18\n", "划分后的训练集大小: 6946, 验证集大小: 1383\n", "train_data最大日期: 2022-10-12, 训练天数5\n", "test_data最大日期: 2022-10-19\n", "划分后的训练集大小: 6946, 验证集大小: 1389\n", "train_data最大日期: 2022-10-13, 训练天数5\n", "test_data最大日期: 2022-10-20\n", "划分后的训练集大小: 6947, 验证集大小: 1396\n", "train_data最大日期: 2022-10-14, 训练天数5\n", "test_data最大日期: 2022-10-21\n", "划分后的训练集大小: 6956, 验证集大小: 1406\n", "train_data最大日期: 2022-10-17, 训练天数5\n", "test_data最大日期: 2022-10-24\n", "划分后的训练集大小: 6977, 验证集大小: 1403\n", "train_data最大日期: 2022-10-18, 训练天数5\n", "test_data最大日期: 2022-10-25\n", "划分后的训练集大小: 6986, 验证集大小: 1392\n", "train_data最大日期: 2022-10-19, 训练天数5\n", "test_data最大日期: 2022-10-26\n", "划分后的训练集大小: 6998, 验证集大小: 1401\n", "train_data最大日期: 2022-10-20, 训练天数5\n", "test_data最大日期: 2022-10-27\n", "划分后的训练集大小: 7009, 验证集大小: 1407\n", "train_data最大日期: 2022-10-21, 训练天数5\n", "test_data最大日期: 2022-10-28\n", "划分后的训练集大小: 7002, 验证集大小: 1399\n", "train_data最大日期: 2022-10-24, 训练天数5\n", "test_data最大日期: 2022-10-31\n", "划分后的训练集大小: 7001, 验证集大小: 1402\n", "train_data最大日期: 2022-10-25, 训练天数5\n", "test_data最大日期: 2022-11-01\n", "划分后的训练集大小: 7007, 验证集大小: 1398\n", "train_data最大日期: 2022-10-26, 训练天数5\n", "test_data最大日期: 2022-11-02\n", "划分后的训练集大小: 7004, 验证集大小: 1398\n", "train_data最大日期: 2022-10-27, 训练天数5\n", "test_data最大日期: 2022-11-03\n", "划分后的训练集大小: 6999, 验证集大小: 1402\n", "train_data最大日期: 2022-10-28, 训练天数5\n", "test_data最大日期: 2022-11-04\n", "划分后的训练集大小: 7000, 验证集大小: 1400\n", "train_data最大日期: 2022-10-31, 训练天数5\n", "test_data最大日期: 2022-11-07\n", "划分后的训练集大小: 6995, 验证集大小: 1397\n", "train_data最大日期: 2022-11-01, 训练天数5\n", "test_data最大日期: 2022-11-08\n", "划分后的训练集大小: 6996, 验证集大小: 1399\n", "train_data最大日期: 2022-11-02, 训练天数5\n", "test_data最大日期: 2022-11-09\n", "划分后的训练集大小: 6984, 验证集大小: 1386\n", "train_data最大日期: 2022-11-03, 训练天数5\n", "test_data最大日期: 2022-11-10\n", "划分后的训练集大小: 6974, 验证集大小: 1392\n", "train_data最大日期: 2022-11-04, 训练天数5\n", "test_data最大日期: 2022-11-11\n", "划分后的训练集大小: 6971, 验证集大小: 1397\n", "train_data最大日期: 2022-11-07, 训练天数5\n", "test_data最大日期: 2022-11-14\n", "划分后的训练集大小: 6968, 验证集大小: 1394\n", "train_data最大日期: 2022-11-08, 训练天数5\n", "test_data最大日期: 2022-11-15\n", "划分后的训练集大小: 6962, 验证集大小: 1393\n", "train_data最大日期: 2022-11-09, 训练天数5\n", "test_data最大日期: 2022-11-16\n", "划分后的训练集大小: 6982, 验证集大小: 1406\n", "train_data最大日期: 2022-11-10, 训练天数5\n", "test_data最大日期: 2022-11-17\n", "划分后的训练集大小: 6992, 验证集大小: 1402\n", "train_data最大日期: 2022-11-11, 训练天数5\n", "test_data最大日期: 2022-11-18\n", "划分后的训练集大小: 6992, 验证集大小: 1397\n", "train_data最大日期: 2022-11-14, 训练天数5\n", "test_data最大日期: 2022-11-21\n", "划分后的训练集大小: 7001, 验证集大小: 1403\n", "train_data最大日期: 2022-11-15, 训练天数5\n", "test_data最大日期: 2022-11-22\n", "划分后的训练集大小: 7006, 验证集大小: 1398\n", "train_data最大日期: 2022-11-16, 训练天数5\n", "test_data最大日期: 2022-11-23\n", "划分后的训练集大小: 7002, 验证集大小: 1402\n", "train_data最大日期: 2022-11-17, 训练天数5\n", "test_data最大日期: 2022-11-24\n", "划分后的训练集大小: 7003, 验证集大小: 1403\n", "train_data最大日期: 2022-11-18, 训练天数5\n", "test_data最大日期: 2022-11-25\n", "划分后的训练集大小: 7013, 验证集大小: 1407\n", "train_data最大日期: 2022-11-21, 训练天数5\n", "test_data最大日期: 2022-11-28\n", "划分后的训练集大小: 7015, 验证集大小: 1405\n", "train_data最大日期: 2022-11-22, 训练天数5\n", "test_data最大日期: 2022-11-29\n", "划分后的训练集大小: 7020, 验证集大小: 1403\n", "train_data最大日期: 2022-11-23, 训练天数5\n", "test_data最大日期: 2022-11-30\n", "划分后的训练集大小: 7014, 验证集大小: 1396\n", "train_data最大日期: 2022-11-24, 训练天数5\n", "test_data最大日期: 2022-12-01\n", "划分后的训练集大小: 7013, 验证集大小: 1402\n", "train_data最大日期: 2022-11-25, 训练天数5\n", "test_data最大日期: 2022-12-02\n", "划分后的训练集大小: 7001, 验证集大小: 1395\n", "train_data最大日期: 2022-11-28, 训练天数5\n", "test_data最大日期: 2022-12-05\n", "划分后的训练集大小: 6998, 验证集大小: 1402\n", "train_data最大日期: 2022-11-29, 训练天数5\n", "test_data最大日期: 2022-12-06\n", "划分后的训练集大小: 7002, 验证集大小: 1407\n", "train_data最大日期: 2022-11-30, 训练天数5\n", "test_data最大日期: 2022-12-07\n", "划分后的训练集大小: 7017, 验证集大小: 1411\n", "train_data最大日期: 2022-12-01, 训练天数5\n", "test_data最大日期: 2022-12-08\n", "划分后的训练集大小: 7019, 验证集大小: 1404\n", "train_data最大日期: 2022-12-02, 训练天数5\n", "test_data最大日期: 2022-12-09\n", "划分后的训练集大小: 7034, 验证集大小: 1410\n", "train_data最大日期: 2022-12-05, 训练天数5\n", "test_data最大日期: 2022-12-12\n", "划分后的训练集大小: 7029, 验证集大小: 1397\n", "train_data最大日期: 2022-12-06, 训练天数5\n", "test_data最大日期: 2022-12-13\n", "划分后的训练集大小: 7026, 验证集大小: 1404\n", "train_data最大日期: 2022-12-07, 训练天数5\n", "test_data最大日期: 2022-12-14\n", "划分后的训练集大小: 7020, 验证集大小: 1405\n", "train_data最大日期: 2022-12-08, 训练天数5\n", "test_data最大日期: 2022-12-15\n", "划分后的训练集大小: 7020, 验证集大小: 1404\n", "train_data最大日期: 2022-12-09, 训练天数5\n", "test_data最大日期: 2022-12-16\n", "划分后的训练集大小: 7014, 验证集大小: 1404\n", "train_data最大日期: 2022-12-12, 训练天数5\n", "test_data最大日期: 2022-12-19\n", "划分后的训练集大小: 7016, 验证集大小: 1399\n", "train_data最大日期: 2022-12-13, 训练天数5\n", "test_data最大日期: 2022-12-20\n", "划分后的训练集大小: 7018, 验证集大小: 1406\n", "train_data最大日期: 2022-12-14, 训练天数5\n", "test_data最大日期: 2022-12-21\n", "划分后的训练集大小: 7020, 验证集大小: 1407\n", "train_data最大日期: 2022-12-15, 训练天数5\n", "test_data最大日期: 2022-12-22\n", "划分后的训练集大小: 7018, 验证集大小: 1402\n", "train_data最大日期: 2022-12-16, 训练天数5\n", "test_data最大日期: 2022-12-23\n", "划分后的训练集大小: 7019, 验证集大小: 1405\n", "train_data最大日期: 2022-12-19, 训练天数5\n", "test_data最大日期: 2022-12-26\n", "划分后的训练集大小: 7029, 验证集大小: 1409\n", "train_data最大日期: 2022-12-20, 训练天数5\n", "test_data最大日期: 2022-12-27\n", "划分后的训练集大小: 7030, 验证集大小: 1407\n", "train_data最大日期: 2022-12-21, 训练天数5\n", "test_data最大日期: 2022-12-28\n", "划分后的训练集大小: 7027, 验证集大小: 1404\n", "train_data最大日期: 2022-12-22, 训练天数5\n", "test_data最大日期: 2022-12-29\n", "划分后的训练集大小: 7034, 验证集大小: 1409\n", "train_data最大日期: 2022-12-23, 训练天数5\n", "test_data最大日期: 2022-12-30\n", "划分后的训练集大小: 7035, 验证集大小: 1406\n", "train_data最大日期: 2022-12-26, 训练天数5\n", "test_data最大日期: 2023-01-03\n", "划分后的训练集大小: 7034, 验证集大小: 1408\n", "train_data最大日期: 2022-12-27, 训练天数5\n", "test_data最大日期: 2023-01-04\n", "划分后的训练集大小: 7037, 验证集大小: 1410\n", "train_data最大日期: 2022-12-28, 训练天数5\n", "test_data最大日期: 2023-01-05\n", "划分后的训练集大小: 7037, 验证集大小: 1404\n", "train_data最大日期: 2022-12-29, 训练天数5\n", "test_data最大日期: 2023-01-06\n", "划分后的训练集大小: 7037, 验证集大小: 1409\n", "train_data最大日期: 2022-12-30, 训练天数5\n", "test_data最大日期: 2023-01-09\n", "划分后的训练集大小: 7043, 验证集大小: 1412\n", "train_data最大日期: 2023-01-03, 训练天数5\n", "test_data最大日期: 2023-01-10\n", "划分后的训练集大小: 7048, 验证集大小: 1413\n", "train_data最大日期: 2023-01-04, 训练天数5\n", "test_data最大日期: 2023-01-11\n", "划分后的训练集大小: 7042, 验证集大小: 1404\n", "train_data最大日期: 2023-01-05, 训练天数5\n", "test_data最大日期: 2023-01-12\n", "划分后的训练集大小: 7051, 验证集大小: 1413\n", "train_data最大日期: 2023-01-06, 训练天数5\n", "test_data最大日期: 2023-01-13\n", "划分后的训练集大小: 7058, 验证集大小: 1416\n", "train_data最大日期: 2023-01-09, 训练天数5\n", "test_data最大日期: 2023-01-16\n", "划分后的训练集大小: 7055, 验证集大小: 1409\n", "train_data最大日期: 2023-01-10, 训练天数5\n", "test_data最大日期: 2023-01-17\n", "划分后的训练集大小: 7048, 验证集大小: 1406\n", "train_data最大日期: 2023-01-11, 训练天数5\n", "test_data最大日期: 2023-01-18\n", "划分后的训练集大小: 7055, 验证集大小: 1411\n", "train_data最大日期: 2023-01-12, 训练天数5\n", "test_data最大日期: 2023-01-19\n", "划分后的训练集大小: 7054, 验证集大小: 1412\n", "train_data最大日期: 2023-01-13, 训练天数5\n", "test_data最大日期: 2023-01-20\n", "划分后的训练集大小: 7050, 验证集大小: 1412\n", "train_data最大日期: 2023-01-16, 训练天数5\n", "test_data最大日期: 2023-01-30\n", "划分后的训练集大小: 7052, 验证集大小: 1411\n", "train_data最大日期: 2023-01-17, 训练天数5\n", "test_data最大日期: 2023-01-31\n", "划分后的训练集大小: 7058, 验证集大小: 1412\n", "train_data最大日期: 2023-01-18, 训练天数5\n", "test_data最大日期: 2023-02-01\n", "划分后的训练集大小: 7053, 验证集大小: 1406\n", "train_data最大日期: 2023-01-19, 训练天数5\n", "test_data最大日期: 2023-02-02\n", "划分后的训练集大小: 7047, 验证集大小: 1406\n", "train_data最大日期: 2023-01-20, 训练天数5\n", "test_data最大日期: 2023-02-03\n", "划分后的训练集大小: 7045, 验证集大小: 1410\n", "train_data最大日期: 2023-01-30, 训练天数5\n", "test_data最大日期: 2023-02-06\n", "划分后的训练集大小: 7039, 验证集大小: 1405\n", "train_data最大日期: 2023-01-31, 训练天数5\n", "test_data最大日期: 2023-02-07\n", "划分后的训练集大小: 7030, 验证集大小: 1403\n", "train_data最大日期: 2023-02-01, 训练天数5\n", "test_data最大日期: 2023-02-08\n", "划分后的训练集大小: 7025, 验证集大小: 1401\n", "train_data最大日期: 2023-02-02, 训练天数5\n", "test_data最大日期: 2023-02-09\n", "划分后的训练集大小: 7028, 验证集大小: 1409\n", "train_data最大日期: 2023-02-03, 训练天数5\n", "test_data最大日期: 2023-02-10\n", "划分后的训练集大小: 7036, 验证集大小: 1418\n", "train_data最大日期: 2023-02-06, 训练天数5\n", "test_data最大日期: 2023-02-13\n", "划分后的训练集大小: 7053, 验证集大小: 1422\n", "train_data最大日期: 2023-02-07, 训练天数5\n", "test_data最大日期: 2023-02-14\n", "划分后的训练集大小: 7072, 验证集大小: 1422\n", "train_data最大日期: 2023-02-08, 训练天数5\n", "test_data最大日期: 2023-02-15\n", "划分后的训练集大小: 7091, 验证集大小: 1420\n", "train_data最大日期: 2023-02-09, 训练天数5\n", "test_data最大日期: 2023-02-16\n", "划分后的训练集大小: 7104, 验证集大小: 1422\n", "train_data最大日期: 2023-02-10, 训练天数5\n", "test_data最大日期: 2023-02-17\n", "划分后的训练集大小: 7108, 验证集大小: 1422\n", "train_data最大日期: 2023-02-13, 训练天数5\n", "test_data最大日期: 2023-02-20\n", "划分后的训练集大小: 7111, 验证集大小: 1425\n", "train_data最大日期: 2023-02-14, 训练天数5\n", "test_data最大日期: 2023-02-21\n", "划分后的训练集大小: 7109, 验证集大小: 1420\n", "train_data最大日期: 2023-02-15, 训练天数5\n", "test_data最大日期: 2023-02-22\n", "划分后的训练集大小: 7112, 验证集大小: 1423\n", "train_data最大日期: 2023-02-16, 训练天数5\n", "test_data最大日期: 2023-02-23\n", "划分后的训练集大小: 7109, 验证集大小: 1419\n", "train_data最大日期: 2023-02-17, 训练天数5\n", "test_data最大日期: 2023-02-24\n", "划分后的训练集大小: 7105, 验证集大小: 1418\n", "train_data最大日期: 2023-02-20, 训练天数5\n", "test_data最大日期: 2023-02-27\n", "划分后的训练集大小: 7100, 验证集大小: 1420\n", "train_data最大日期: 2023-02-21, 训练天数5\n", "test_data最大日期: 2023-02-28\n", "划分后的训练集大小: 7101, 验证集大小: 1421\n", "train_data最大日期: 2023-02-22, 训练天数5\n", "test_data最大日期: 2023-03-01\n", "划分后的训练集大小: 7096, 验证集大小: 1418\n", "train_data最大日期: 2023-02-23, 训练天数5\n", "test_data最大日期: 2023-03-02\n", "划分后的训练集大小: 7096, 验证集大小: 1419\n", "train_data最大日期: 2023-02-24, 训练天数5\n", "test_data最大日期: 2023-03-03\n", "划分后的训练集大小: 7098, 验证集大小: 1420\n", "train_data最大日期: 2023-02-27, 训练天数5\n", "test_data最大日期: 2023-03-06\n", "划分后的训练集大小: 7097, 验证集大小: 1419\n", "train_data最大日期: 2023-02-28, 训练天数5\n", "test_data最大日期: 2023-03-07\n", "划分后的训练集大小: 7093, 验证集大小: 1417\n", "train_data最大日期: 2023-03-01, 训练天数5\n", "test_data最大日期: 2023-03-08\n", "划分后的训练集大小: 7094, 验证集大小: 1419\n", "train_data最大日期: 2023-03-02, 训练天数5\n", "test_data最大日期: 2023-03-09\n", "划分后的训练集大小: 7089, 验证集大小: 1414\n", "train_data最大日期: 2023-03-03, 训练天数5\n", "test_data最大日期: 2023-03-10\n", "划分后的训练集大小: 7083, 验证集大小: 1414\n", "train_data最大日期: 2023-03-06, 训练天数5\n", "test_data最大日期: 2023-03-13\n", "划分后的训练集大小: 7080, 验证集大小: 1416\n", "train_data最大日期: 2023-03-07, 训练天数5\n", "test_data最大日期: 2023-03-14\n", "划分后的训练集大小: 7074, 验证集大小: 1411\n", "train_data最大日期: 2023-03-08, 训练天数5\n", "test_data最大日期: 2023-03-15\n", "划分后的训练集大小: 7065, 验证集大小: 1410\n", "train_data最大日期: 2023-03-09, 训练天数5\n", "test_data最大日期: 2023-03-16\n", "划分后的训练集大小: 7063, 验证集大小: 1412\n", "train_data最大日期: 2023-03-10, 训练天数5\n", "test_data最大日期: 2023-03-17\n", "划分后的训练集大小: 7060, 验证集大小: 1411\n", "train_data最大日期: 2023-03-13, 训练天数5\n", "test_data最大日期: 2023-03-20\n", "划分后的训练集大小: 7057, 验证集大小: 1413\n", "train_data最大日期: 2023-03-14, 训练天数5\n", "test_data最大日期: 2023-03-21\n", "划分后的训练集大小: 7060, 验证集大小: 1414\n", "train_data最大日期: 2023-03-15, 训练天数5\n", "test_data最大日期: 2023-03-22\n", "划分后的训练集大小: 7061, 验证集大小: 1411\n", "train_data最大日期: 2023-03-16, 训练天数5\n", "test_data最大日期: 2023-03-23\n", "划分后的训练集大小: 7055, 验证集大小: 1406\n", "train_data最大日期: 2023-03-17, 训练天数5\n", "test_data最大日期: 2023-03-24\n", "划分后的训练集大小: 7055, 验证集大小: 1411\n", "train_data最大日期: 2023-03-20, 训练天数5\n", "test_data最大日期: 2023-03-27\n", "划分后的训练集大小: 7056, 验证集大小: 1414\n", "train_data最大日期: 2023-03-21, 训练天数5\n", "test_data最大日期: 2023-03-28\n", "划分后的训练集大小: 7052, 验证集大小: 1410\n", "train_data最大日期: 2023-03-22, 训练天数5\n", "test_data最大日期: 2023-03-29\n", "划分后的训练集大小: 7059, 验证集大小: 1418\n", "train_data最大日期: 2023-03-23, 训练天数5\n", "test_data最大日期: 2023-03-30\n", "划分后的训练集大小: 7072, 验证集大小: 1419\n", "train_data最大日期: 2023-03-24, 训练天数5\n", "test_data最大日期: 2023-03-31\n", "划分后的训练集大小: 7078, 验证集大小: 1417\n", "train_data最大日期: 2023-03-27, 训练天数5\n", "test_data最大日期: 2023-04-03\n", "划分后的训练集大小: 7081, 验证集大小: 1417\n", "train_data最大日期: 2023-03-28, 训练天数5\n", "test_data最大日期: 2023-04-04\n", "划分后的训练集大小: 7088, 验证集大小: 1417\n", "train_data最大日期: 2023-03-29, 训练天数5\n", "test_data最大日期: 2023-04-06\n", "划分后的训练集大小: 7085, 验证集大小: 1415\n", "train_data最大日期: 2023-03-30, 训练天数5\n", "test_data最大日期: 2023-04-07\n", "划分后的训练集大小: 7083, 验证集大小: 1417\n", "train_data最大日期: 2023-03-31, 训练天数5\n", "test_data最大日期: 2023-04-10\n", "划分后的训练集大小: 7082, 验证集大小: 1416\n", "train_data最大日期: 2023-04-03, 训练天数5\n", "test_data最大日期: 2023-04-11\n", "划分后的训练集大小: 7081, 验证集大小: 1416\n", "train_data最大日期: 2023-04-04, 训练天数5\n", "test_data最大日期: 2023-04-12\n", "划分后的训练集大小: 7076, 验证集大小: 1412\n", "train_data最大日期: 2023-04-06, 训练天数5\n", "test_data最大日期: 2023-04-13\n", "划分后的训练集大小: 7075, 验证集大小: 1414\n", "train_data最大日期: 2023-04-07, 训练天数5\n", "test_data最大日期: 2023-04-14\n", "划分后的训练集大小: 7076, 验证集大小: 1418\n", "train_data最大日期: 2023-04-10, 训练天数5\n", "test_data最大日期: 2023-04-17\n", "划分后的训练集大小: 7067, 验证集大小: 1407\n", "train_data最大日期: 2023-04-11, 训练天数5\n", "test_data最大日期: 2023-04-18\n", "划分后的训练集大小: 7062, 验证集大小: 1411\n", "train_data最大日期: 2023-04-12, 训练天数5\n", "test_data最大日期: 2023-04-19\n", "划分后的训练集大小: 7061, 验证集大小: 1411\n", "train_data最大日期: 2023-04-13, 训练天数5\n", "test_data最大日期: 2023-04-20\n", "划分后的训练集大小: 7052, 验证集大小: 1405\n", "train_data最大日期: 2023-04-14, 训练天数5\n", "test_data最大日期: 2023-04-21\n", "划分后的训练集大小: 7038, 验证集大小: 1404\n", "train_data最大日期: 2023-04-17, 训练天数5\n", "test_data最大日期: 2023-04-24\n", "划分后的训练集大小: 7036, 验证集大小: 1405\n", "train_data最大日期: 2023-04-18, 训练天数5\n", "test_data最大日期: 2023-04-25\n", "划分后的训练集大小: 7027, 验证集大小: 1402\n", "train_data最大日期: 2023-04-19, 训练天数5\n", "test_data最大日期: 2023-04-26\n", "划分后的训练集大小: 7016, 验证集大小: 1400\n", "train_data最大日期: 2023-04-20, 训练天数5\n", "test_data最大日期: 2023-04-27\n", "划分后的训练集大小: 7005, 验证集大小: 1394\n", "train_data最大日期: 2023-04-21, 训练天数5\n", "test_data最大日期: 2023-04-28\n", "划分后的训练集大小: 6996, 验证集大小: 1395\n", "train_data最大日期: 2023-04-24, 训练天数5\n", "test_data最大日期: 2023-05-04\n", "划分后的训练集大小: 6980, 验证集大小: 1389\n", "train_data最大日期: 2023-04-25, 训练天数5\n", "test_data最大日期: 2023-05-05\n", "划分后的训练集大小: 6968, 验证集大小: 1390\n", "train_data最大日期: 2023-04-26, 训练天数5\n", "test_data最大日期: 2023-05-08\n", "划分后的训练集大小: 6957, 验证集大小: 1389\n", "train_data最大日期: 2023-04-27, 训练天数5\n", "test_data最大日期: 2023-05-09\n", "划分后的训练集大小: 6963, 验证集大小: 1400\n", "train_data最大日期: 2023-04-28, 训练天数5\n", "test_data最大日期: 2023-05-10\n", "划分后的训练集大小: 6972, 验证集大小: 1404\n", "train_data最大日期: 2023-05-04, 训练天数5\n", "test_data最大日期: 2023-05-11\n", "划分后的训练集大小: 7010, 验证集大小: 1427\n", "train_data最大日期: 2023-05-05, 训练天数5\n", "test_data最大日期: 2023-05-12\n", "划分后的训练集大小: 7051, 验证集大小: 1431\n", "train_data最大日期: 2023-05-08, 训练天数5\n", "test_data最大日期: 2023-05-15\n", "划分后的训练集大小: 7095, 验证集大小: 1433\n", "train_data最大日期: 2023-05-09, 训练天数5\n", "test_data最大日期: 2023-05-16\n", "划分后的训练集大小: 7129, 验证集大小: 1434\n", "train_data最大日期: 2023-05-10, 训练天数5\n", "test_data最大日期: 2023-05-17\n", "划分后的训练集大小: 7161, 验证集大小: 1436\n", "train_data最大日期: 2023-05-11, 训练天数5\n", "test_data最大日期: 2023-05-18\n", "划分后的训练集大小: 7167, 验证集大小: 1433\n", "train_data最大日期: 2023-05-12, 训练天数5\n", "test_data最大日期: 2023-05-19\n", "划分后的训练集大小: 7166, 验证集大小: 1430\n", "train_data最大日期: 2023-05-15, 训练天数5\n", "test_data最大日期: 2023-05-22\n", "划分后的训练集大小: 7163, 验证集大小: 1430\n", "train_data最大日期: 2023-05-16, 训练天数5\n", "test_data最大日期: 2023-05-23\n", "划分后的训练集大小: 7158, 验证集大小: 1429\n", "train_data最大日期: 2023-05-17, 训练天数5\n", "test_data最大日期: 2023-05-24\n", "划分后的训练集大小: 7153, 验证集大小: 1431\n", "train_data最大日期: 2023-05-18, 训练天数5\n", "test_data最大日期: 2023-05-25\n", "划分后的训练集大小: 7149, 验证集大小: 1429\n", "train_data最大日期: 2023-05-19, 训练天数5\n", "test_data最大日期: 2023-05-26\n", "划分后的训练集大小: 7150, 验证集大小: 1431\n", "train_data最大日期: 2023-05-22, 训练天数5\n", "test_data最大日期: 2023-05-29\n", "划分后的训练集大小: 7150, 验证集大小: 1430\n", "train_data最大日期: 2023-05-23, 训练天数5\n", "test_data最大日期: 2023-05-30\n", "划分后的训练集大小: 7146, 验证集大小: 1425\n", "train_data最大日期: 2023-05-24, 训练天数5\n", "test_data最大日期: 2023-05-31\n", "划分后的训练集大小: 7142, 验证集大小: 1427\n", "train_data最大日期: 2023-05-25, 训练天数5\n", "test_data最大日期: 2023-06-01\n", "划分后的训练集大小: 7136, 验证集大小: 1423\n", "train_data最大日期: 2023-05-26, 训练天数5\n", "test_data最大日期: 2023-06-02\n", "划分后的训练集大小: 7133, 验证集大小: 1428\n", "train_data最大日期: 2023-05-29, 训练天数5\n", "test_data最大日期: 2023-06-05\n", "划分后的训练集大小: 7128, 验证集大小: 1425\n", "train_data最大日期: 2023-05-30, 训练天数5\n", "test_data最大日期: 2023-06-06\n", "划分后的训练集大小: 7127, 验证集大小: 1424\n", "train_data最大日期: 2023-05-31, 训练天数5\n", "test_data最大日期: 2023-06-07\n", "划分后的训练集大小: 7118, 验证集大小: 1418\n", "train_data最大日期: 2023-06-01, 训练天数5\n", "test_data最大日期: 2023-06-08\n", "划分后的训练集大小: 7112, 验证集大小: 1417\n", "train_data最大日期: 2023-06-02, 训练天数5\n", "test_data最大日期: 2023-06-09\n", "划分后的训练集大小: 7105, 验证集大小: 1421\n", "train_data最大日期: 2023-06-05, 训练天数5\n", "test_data最大日期: 2023-06-12\n", "划分后的训练集大小: 7099, 验证集大小: 1419\n", "train_data最大日期: 2023-06-06, 训练天数5\n", "test_data最大日期: 2023-06-13\n", "划分后的训练集大小: 7099, 验证集大小: 1424\n", "train_data最大日期: 2023-06-07, 训练天数5\n", "test_data最大日期: 2023-06-14\n", "划分后的训练集大小: 7102, 验证集大小: 1421\n", "train_data最大日期: 2023-06-08, 训练天数5\n", "test_data最大日期: 2023-06-15\n", "划分后的训练集大小: 7113, 验证集大小: 1428\n", "train_data最大日期: 2023-06-09, 训练天数5\n", "test_data最大日期: 2023-06-16\n", "划分后的训练集大小: 7118, 验证集大小: 1426\n", "train_data最大日期: 2023-06-12, 训练天数5\n", "test_data最大日期: 2023-06-19\n", "划分后的训练集大小: 7125, 验证集大小: 1426\n", "train_data最大日期: 2023-06-13, 训练天数5\n", "test_data最大日期: 2023-06-20\n", "划分后的训练集大小: 7122, 验证集大小: 1421\n", "train_data最大日期: 2023-06-14, 训练天数5\n", "test_data最大日期: 2023-06-21\n", "划分后的训练集大小: 7117, 验证集大小: 1416\n", "train_data最大日期: 2023-06-15, 训练天数5\n", "test_data最大日期: 2023-06-26\n", "划分后的训练集大小: 7109, 验证集大小: 1420\n", "train_data最大日期: 2023-06-16, 训练天数5\n", "test_data最大日期: 2023-06-27\n", "划分后的训练集大小: 7101, 验证集大小: 1418\n", "train_data最大日期: 2023-06-19, 训练天数5\n", "test_data最大日期: 2023-06-28\n", "划分后的训练集大小: 7094, 验证集大小: 1419\n", "train_data最大日期: 2023-06-20, 训练天数5\n", "test_data最大日期: 2023-06-29\n", "划分后的训练集大小: 7092, 验证集大小: 1419\n", "train_data最大日期: 2023-06-21, 训练天数5\n", "test_data最大日期: 2023-06-30\n", "划分后的训练集大小: 7100, 验证集大小: 1424\n", "train_data最大日期: 2023-06-26, 训练天数5\n", "test_data最大日期: 2023-07-03\n", "划分后的训练集大小: 7101, 验证集大小: 1421\n", "train_data最大日期: 2023-06-27, 训练天数5\n", "test_data最大日期: 2023-07-04\n", "划分后的训练集大小: 7106, 验证集大小: 1423\n", "train_data最大日期: 2023-06-28, 训练天数5\n", "test_data最大日期: 2023-07-05\n", "划分后的训练集大小: 7115, 验证集大小: 1428\n", "train_data最大日期: 2023-06-29, 训练天数5\n", "test_data最大日期: 2023-07-06\n", "划分后的训练集大小: 7124, 验证集大小: 1428\n", "train_data最大日期: 2023-06-30, 训练天数5\n", "test_data最大日期: 2023-07-07\n", "划分后的训练集大小: 7127, 验证集大小: 1427\n", "train_data最大日期: 2023-07-03, 训练天数5\n", "test_data最大日期: 2023-07-10\n", "划分后的训练集大小: 7133, 验证集大小: 1427\n", "train_data最大日期: 2023-07-04, 训练天数5\n", "test_data最大日期: 2023-07-11\n", "划分后的训练集大小: 7134, 验证集大小: 1424\n", "train_data最大日期: 2023-07-05, 训练天数5\n", "test_data最大日期: 2023-07-12\n", "划分后的训练集大小: 7130, 验证集大小: 1424\n", "train_data最大日期: 2023-07-06, 训练天数5\n", "test_data最大日期: 2023-07-13\n", "划分后的训练集大小: 7132, 验证集大小: 1430\n", "train_data最大日期: 2023-07-07, 训练天数5\n", "test_data最大日期: 2023-07-14\n", "划分后的训练集大小: 7136, 验证集大小: 1431\n", "train_data最大日期: 2023-07-10, 训练天数5\n", "test_data最大日期: 2023-07-17\n", "划分后的训练集大小: 7139, 验证集大小: 1430\n", "train_data最大日期: 2023-07-11, 训练天数5\n", "test_data最大日期: 2023-07-18\n", "划分后的训练集大小: 7146, 验证集大小: 1431\n", "train_data最大日期: 2023-07-12, 训练天数5\n", "test_data最大日期: 2023-07-19\n", "划分后的训练集大小: 7157, 验证集大小: 1435\n", "train_data最大日期: 2023-07-13, 训练天数5\n", "test_data最大日期: 2023-07-20\n", "划分后的训练集大小: 7161, 验证集大小: 1434\n", "train_data最大日期: 2023-07-14, 训练天数5\n", "test_data最大日期: 2023-07-21\n", "划分后的训练集大小: 7164, 验证集大小: 1434\n", "train_data最大日期: 2023-07-17, 训练天数5\n", "test_data最大日期: 2023-07-24\n", "划分后的训练集大小: 7167, 验证集大小: 1433\n", "train_data最大日期: 2023-07-18, 训练天数5\n", "test_data最大日期: 2023-07-25\n", "划分后的训练集大小: 7166, 验证集大小: 1430\n", "train_data最大日期: 2023-07-19, 训练天数5\n", "test_data最大日期: 2023-07-26\n", "划分后的训练集大小: 7161, 验证集大小: 1430\n", "train_data最大日期: 2023-07-20, 训练天数5\n", "test_data最大日期: 2023-07-27\n", "划分后的训练集大小: 7163, 验证集大小: 1436\n", "train_data最大日期: 2023-07-21, 训练天数5\n", "test_data最大日期: 2023-07-28\n", "划分后的训练集大小: 7168, 验证集大小: 1439\n", "train_data最大日期: 2023-07-24, 训练天数5\n", "test_data最大日期: 2023-07-31\n", "划分后的训练集大小: 7172, 验证集大小: 1437\n", "train_data最大日期: 2023-07-25, 训练天数5\n", "test_data最大日期: 2023-08-01\n", "划分后的训练集大小: 7180, 验证集大小: 1438\n", "train_data最大日期: 2023-07-26, 训练天数5\n", "test_data最大日期: 2023-08-02\n", "划分后的训练集大小: 7188, 验证集大小: 1438\n", "train_data最大日期: 2023-07-27, 训练天数5\n", "test_data最大日期: 2023-08-03\n", "划分后的训练集大小: 7189, 验证集大小: 1437\n", "train_data最大日期: 2023-07-28, 训练天数5\n", "test_data最大日期: 2023-08-04\n", "划分后的训练集大小: 7188, 验证集大小: 1438\n", "train_data最大日期: 2023-07-31, 训练天数5\n", "test_data最大日期: 2023-08-07\n", "划分后的训练集大小: 7192, 验证集大小: 1441\n", "train_data最大日期: 2023-08-01, 训练天数5\n", "test_data最大日期: 2023-08-08\n", "划分后的训练集大小: 7189, 验证集大小: 1435\n", "train_data最大日期: 2023-08-02, 训练天数5\n", "test_data最大日期: 2023-08-09\n", "划分后的训练集大小: 7192, 验证集大小: 1441\n", "train_data最大日期: 2023-08-03, 训练天数5\n", "test_data最大日期: 2023-08-10\n", "划分后的训练集大小: 7196, 验证集大小: 1441\n", "train_data最大日期: 2023-08-04, 训练天数5\n", "test_data最大日期: 2023-08-11\n", "划分后的训练集大小: 7204, 验证集大小: 1446\n", "train_data最大日期: 2023-08-07, 训练天数5\n", "test_data最大日期: 2023-08-14\n", "划分后的训练集大小: 7206, 验证集大小: 1443\n", "train_data最大日期: 2023-08-08, 训练天数5\n", "test_data最大日期: 2023-08-15\n", "划分后的训练集大小: 7218, 验证集大小: 1447\n", "train_data最大日期: 2023-08-09, 训练天数5\n", "test_data最大日期: 2023-08-16\n", "划分后的训练集大小: 7227, 验证集大小: 1450\n", "train_data最大日期: 2023-08-10, 训练天数5\n", "test_data最大日期: 2023-08-17\n", "划分后的训练集大小: 7237, 验证集大小: 1451\n", "train_data最大日期: 2023-08-11, 训练天数5\n", "test_data最大日期: 2023-08-18\n", "划分后的训练集大小: 7240, 验证集大小: 1449\n", "train_data最大日期: 2023-08-14, 训练天数5\n", "test_data最大日期: 2023-08-21\n", "划分后的训练集大小: 7248, 验证集大小: 1451\n", "train_data最大日期: 2023-08-15, 训练天数5\n", "test_data最大日期: 2023-08-22\n", "划分后的训练集大小: 7247, 验证集大小: 1446\n", "train_data最大日期: 2023-08-16, 训练天数5\n", "test_data最大日期: 2023-08-23\n", "划分后的训练集大小: 7244, 验证集大小: 1447\n", "train_data最大日期: 2023-08-17, 训练天数5\n", "test_data最大日期: 2023-08-24\n", "划分后的训练集大小: 7239, 验证集大小: 1446\n", "train_data最大日期: 2023-08-18, 训练天数5\n", "test_data最大日期: 2023-08-25\n", "划分后的训练集大小: 7231, 验证集大小: 1441\n", "train_data最大日期: 2023-08-21, 训练天数5\n", "test_data最大日期: 2023-08-28\n", "划分后的训练集大小: 7226, 验证集大小: 1446\n", "train_data最大日期: 2023-08-22, 训练天数5\n", "test_data最大日期: 2023-08-29\n", "划分后的训练集大小: 7230, 验证集大小: 1450\n", "train_data最大日期: 2023-08-23, 训练天数5\n", "test_data最大日期: 2023-08-30\n", "划分后的训练集大小: 7234, 验证集大小: 1451\n", "train_data最大日期: 2023-08-24, 训练天数5\n", "test_data最大日期: 2023-08-31\n", "划分后的训练集大小: 7239, 验证集大小: 1451\n", "train_data最大日期: 2023-08-25, 训练天数5\n", "test_data最大日期: 2023-09-01\n", "划分后的训练集大小: 7248, 验证集大小: 1450\n", "train_data最大日期: 2023-08-28, 训练天数5\n", "test_data最大日期: 2023-09-04\n", "划分后的训练集大小: 7248, 验证集大小: 1446\n", "train_data最大日期: 2023-08-29, 训练天数5\n", "test_data最大日期: 2023-09-05\n", "划分后的训练集大小: 7240, 验证集大小: 1442\n", "train_data最大日期: 2023-08-30, 训练天数5\n", "test_data最大日期: 2023-09-06\n", "划分后的训练集大小: 7208, 验证集大小: 1419\n", "train_data最大日期: 2023-08-31, 训练天数5\n", "test_data最大日期: 2023-09-07\n", "划分后的训练集大小: 7208, 验证集大小: 1451\n", "train_data最大日期: 2023-09-01, 训练天数5\n", "test_data最大日期: 2023-09-08\n", "划分后的训练集大小: 7203, 验证集大小: 1445\n", "train_data最大日期: 2023-09-04, 训练天数5\n", "test_data最大日期: 2023-09-11\n", "划分后的训练集大小: 7212, 验证集大小: 1455\n", "train_data最大日期: 2023-09-05, 训练天数5\n", "test_data最大日期: 2023-09-12\n", "划分后的训练集大小: 7226, 验证集大小: 1456\n", "train_data最大日期: 2023-09-06, 训练天数5\n", "test_data最大日期: 2023-09-13\n", "划分后的训练集大小: 7262, 验证集大小: 1455\n", "train_data最大日期: 2023-09-07, 训练天数5\n", "test_data最大日期: 2023-09-14\n", "划分后的训练集大小: 7267, 验证集大小: 1456\n", "train_data最大日期: 2023-09-08, 训练天数5\n", "test_data最大日期: 2023-09-15\n", "划分后的训练集大小: 7273, 验证集大小: 1451\n", "train_data最大日期: 2023-09-11, 训练天数5\n", "test_data最大日期: 2023-09-18\n", "划分后的训练集大小: 7271, 验证集大小: 1453\n", "train_data最大日期: 2023-09-12, 训练天数5\n", "test_data最大日期: 2023-09-19\n", "划分后的训练集大小: 7269, 验证集大小: 1454\n", "train_data最大日期: 2023-09-13, 训练天数5\n", "test_data最大日期: 2023-09-20\n", "划分后的训练集大小: 7269, 验证集大小: 1455\n", "train_data最大日期: 2023-09-14, 训练天数5\n", "test_data最大日期: 2023-09-21\n", "划分后的训练集大小: 7275, 验证集大小: 1462\n", "train_data最大日期: 2023-09-15, 训练天数5\n", "test_data最大日期: 2023-09-22\n", "划分后的训练集大小: 7278, 验证集大小: 1454\n", "train_data最大日期: 2023-09-18, 训练天数5\n", "test_data最大日期: 2023-09-25\n", "划分后的训练集大小: 7281, 验证集大小: 1456\n", "train_data最大日期: 2023-09-19, 训练天数5\n", "test_data最大日期: 2023-09-26\n", "划分后的训练集大小: 7284, 验证集大小: 1457\n", "train_data最大日期: 2023-09-20, 训练天数5\n", "test_data最大日期: 2023-09-27\n", "划分后的训练集大小: 7287, 验证集大小: 1458\n", "train_data最大日期: 2023-09-21, 训练天数5\n", "test_data最大日期: 2023-09-28\n", "划分后的训练集大小: 7279, 验证集大小: 1454\n", "train_data最大日期: 2023-09-22, 训练天数5\n", "test_data最大日期: 2023-10-09\n", "划分后的训练集大小: 7279, 验证集大小: 1454\n", "train_data最大日期: 2023-09-25, 训练天数5\n", "test_data最大日期: 2023-10-10\n", "划分后的训练集大小: 7275, 验证集大小: 1452\n", "train_data最大日期: 2023-09-26, 训练天数5\n", "test_data最大日期: 2023-10-11\n", "划分后的训练集大小: 7267, 验证集大小: 1449\n", "train_data最大日期: 2023-09-27, 训练天数5\n", "test_data最大日期: 2023-10-12\n", "划分后的训练集大小: 7259, 验证集大小: 1450\n", "train_data最大日期: 2023-09-28, 训练天数5\n", "test_data最大日期: 2023-10-13\n", "划分后的训练集大小: 7259, 验证集大小: 1454\n", "train_data最大日期: 2023-10-09, 训练天数5\n", "test_data最大日期: 2023-10-16\n", "划分后的训练集大小: 7260, 验证集大小: 1455\n", "train_data最大日期: 2023-10-10, 训练天数5\n", "test_data最大日期: 2023-10-17\n", "划分后的训练集大小: 7260, 验证集大小: 1452\n", "train_data最大日期: 2023-10-11, 训练天数5\n", "test_data最大日期: 2023-10-18\n", "划分后的训练集大小: 7269, 验证集大小: 1458\n", "train_data最大日期: 2023-10-12, 训练天数5\n", "test_data最大日期: 2023-10-19\n", "划分后的训练集大小: 7270, 验证集大小: 1451\n", "train_data最大日期: 2023-10-13, 训练天数5\n", "test_data最大日期: 2023-10-20\n", "划分后的训练集大小: 7268, 验证集大小: 1452\n", "train_data最大日期: 2023-10-16, 训练天数5\n", "test_data最大日期: 2023-10-23\n", "划分后的训练集大小: 7259, 验证集大小: 1446\n", "train_data最大日期: 2023-10-17, 训练天数5\n", "test_data最大日期: 2023-10-24\n", "划分后的训练集大小: 7257, 验证集大小: 1450\n", "train_data最大日期: 2023-10-18, 训练天数5\n", "test_data最大日期: 2023-10-25\n", "划分后的训练集大小: 7246, 验证集大小: 1447\n", "train_data最大日期: 2023-10-19, 训练天数5\n", "test_data最大日期: 2023-10-26\n", "划分后的训练集大小: 7244, 验证集大小: 1449\n", "train_data最大日期: 2023-10-20, 训练天数5\n", "test_data最大日期: 2023-10-27\n", "划分后的训练集大小: 7239, 验证集大小: 1447\n", "train_data最大日期: 2023-10-23, 训练天数5\n", "test_data最大日期: 2023-10-30\n", "划分后的训练集大小: 7245, 验证集大小: 1452\n", "train_data最大日期: 2023-10-24, 训练天数5\n", "test_data最大日期: 2023-10-31\n", "划分后的训练集大小: 7251, 验证集大小: 1456\n", "train_data最大日期: 2023-10-25, 训练天数5\n", "test_data最大日期: 2023-11-01\n", "划分后的训练集大小: 7257, 验证集大小: 1453\n", "train_data最大日期: 2023-10-26, 训练天数5\n", "test_data最大日期: 2023-11-02\n", "划分后的训练集大小: 7258, 验证集大小: 1450\n", "train_data最大日期: 2023-10-27, 训练天数5\n", "test_data最大日期: 2023-11-03\n", "划分后的训练集大小: 7261, 验证集大小: 1450\n", "train_data最大日期: 2023-10-30, 训练天数5\n", "test_data最大日期: 2023-11-06\n", "划分后的训练集大小: 7264, 验证集大小: 1455\n", "train_data最大日期: 2023-10-31, 训练天数5\n", "test_data最大日期: 2023-11-07\n", "划分后的训练集大小: 7258, 验证集大小: 1450\n", "train_data最大日期: 2023-11-01, 训练天数5\n", "test_data最大日期: 2023-11-08\n", "划分后的训练集大小: 7253, 验证集大小: 1448\n", "train_data最大日期: 2023-11-02, 训练天数5\n", "test_data最大日期: 2023-11-09\n", "划分后的训练集大小: 7251, 验证集大小: 1448\n", "train_data最大日期: 2023-11-03, 训练天数5\n", "test_data最大日期: 2023-11-10\n", "划分后的训练集大小: 7256, 验证集大小: 1455\n", "train_data最大日期: 2023-11-06, 训练天数5\n", "test_data最大日期: 2023-11-13\n", "划分后的训练集大小: 7254, 验证集大小: 1453\n", "train_data最大日期: 2023-11-07, 训练天数5\n", "test_data最大日期: 2023-11-14\n", "划分后的训练集大小: 7240, 验证集大小: 1436\n", "train_data最大日期: 2023-11-08, 训练天数5\n", "test_data最大日期: 2023-11-15\n", "划分后的训练集大小: 7229, 验证集大小: 1437\n", "train_data最大日期: 2023-11-09, 训练天数5\n", "test_data最大日期: 2023-11-16\n", "划分后的训练集大小: 7228, 验证集大小: 1447\n", "train_data最大日期: 2023-11-10, 训练天数5\n", "test_data最大日期: 2023-11-17\n", "划分后的训练集大小: 7221, 验证集大小: 1448\n", "train_data最大日期: 2023-11-13, 训练天数5\n", "test_data最大日期: 2023-11-20\n", "划分后的训练集大小: 7211, 验证集大小: 1443\n", "train_data最大日期: 2023-11-14, 训练天数5\n", "test_data最大日期: 2023-11-21\n", "划分后的训练集大小: 7218, 验证集大小: 1443\n", "train_data最大日期: 2023-11-15, 训练天数5\n", "test_data最大日期: 2023-11-22\n", "划分后的训练集大小: 7215, 验证集大小: 1434\n", "train_data最大日期: 2023-11-16, 训练天数5\n", "test_data最大日期: 2023-11-23\n", "划分后的训练集大小: 7212, 验证集大小: 1444\n", "train_data最大日期: 2023-11-17, 训练天数5\n", "test_data最大日期: 2023-11-24\n", "划分后的训练集大小: 7212, 验证集大小: 1448\n", "train_data最大日期: 2023-11-20, 训练天数5\n", "test_data最大日期: 2023-11-27\n", "划分后的训练集大小: 7215, 验证集大小: 1446\n", "train_data最大日期: 2023-11-21, 训练天数5\n", "test_data最大日期: 2023-11-28\n", "划分后的训练集大小: 7213, 验证集大小: 1441\n", "train_data最大日期: 2023-11-22, 训练天数5\n", "test_data最大日期: 2023-11-29\n", "划分后的训练集大小: 7216, 验证集大小: 1437\n", "train_data最大日期: 2023-11-23, 训练天数5\n", "test_data最大日期: 2023-11-30\n", "划分后的训练集大小: 7220, 验证集大小: 1448\n", "train_data最大日期: 2023-11-24, 训练天数5\n", "test_data最大日期: 2023-12-01\n", "划分后的训练集大小: 7222, 验证集大小: 1450\n", "train_data最大日期: 2023-11-27, 训练天数5\n", "test_data最大日期: 2023-12-04\n", "划分后的训练集大小: 7217, 验证集大小: 1441\n", "train_data最大日期: 2023-11-28, 训练天数5\n", "test_data最大日期: 2023-12-05\n", "划分后的训练集大小: 7222, 验证集大小: 1446\n", "train_data最大日期: 2023-11-29, 训练天数5\n", "test_data最大日期: 2023-12-06\n", "划分后的训练集大小: 7229, 验证集大小: 1444\n", "train_data最大日期: 2023-11-30, 训练天数5\n", "test_data最大日期: 2023-12-07\n", "划分后的训练集大小: 7222, 验证集大小: 1441\n", "train_data最大日期: 2023-12-01, 训练天数5\n", "test_data最大日期: 2023-12-08\n", "划分后的训练集大小: 7222, 验证集大小: 1450\n", "train_data最大日期: 2023-12-04, 训练天数5\n", "test_data最大日期: 2023-12-11\n", "划分后的训练集大小: 7229, 验证集大小: 1448\n", "train_data最大日期: 2023-12-05, 训练天数5\n", "test_data最大日期: 2023-12-12\n", "划分后的训练集大小: 7224, 验证集大小: 1441\n", "train_data最大日期: 2023-12-06, 训练天数5\n", "test_data最大日期: 2023-12-13\n", "划分后的训练集大小: 7217, 验证集大小: 1437\n", "train_data最大日期: 2023-12-07, 训练天数5\n", "test_data最大日期: 2023-12-14\n", "划分后的训练集大小: 7219, 验证集大小: 1443\n", "train_data最大日期: 2023-12-08, 训练天数5\n", "test_data最大日期: 2023-12-15\n", "划分后的训练集大小: 7206, 验证集大小: 1437\n", "train_data最大日期: 2023-12-11, 训练天数5\n", "test_data最大日期: 2023-12-18\n", "划分后的训练集大小: 7194, 验证集大小: 1436\n", "train_data最大日期: 2023-12-12, 训练天数5\n", "test_data最大日期: 2023-12-19\n", "划分后的训练集大小: 7199, 验证集大小: 1446\n", "train_data最大日期: 2023-12-13, 训练天数5\n", "test_data最大日期: 2023-12-20\n", "划分后的训练集大小: 7202, 验证集大小: 1440\n", "train_data最大日期: 2023-12-14, 训练天数5\n", "test_data最大日期: 2023-12-21\n", "划分后的训练集大小: 7195, 验证集大小: 1436\n", "train_data最大日期: 2023-12-15, 训练天数5\n", "test_data最大日期: 2023-12-22\n", "划分后的训练集大小: 7189, 验证集大小: 1431\n", "train_data最大日期: 2023-12-18, 训练天数5\n", "test_data最大日期: 2023-12-25\n", "划分后的训练集大小: 7185, 验证集大小: 1432\n", "train_data最大日期: 2023-12-19, 训练天数5\n", "test_data最大日期: 2023-12-26\n", "划分后的训练集大小: 7170, 验证集大小: 1431\n", "train_data最大日期: 2023-12-20, 训练天数5\n", "test_data最大日期: 2023-12-27\n", "划分后的训练集大小: 7165, 验证集大小: 1435\n", "train_data最大日期: 2023-12-21, 训练天数5\n", "test_data最大日期: 2023-12-28\n", "划分后的训练集大小: 7168, 验证集大小: 1439\n", "train_data最大日期: 2023-12-22, 训练天数5\n", "test_data最大日期: 2023-12-29\n", "划分后的训练集大小: 7180, 验证集大小: 1443\n", "train_data最大日期: 2023-12-25, 训练天数5\n", "test_data最大日期: 2024-01-02\n", "划分后的训练集大小: 7182, 验证集大小: 1434\n", "train_data最大日期: 2023-12-26, 训练天数5\n", "test_data最大日期: 2024-01-03\n", "划分后的训练集大小: 7179, 验证集大小: 1428\n", "train_data最大日期: 2023-12-27, 训练天数5\n", "test_data最大日期: 2024-01-04\n", "划分后的训练集大小: 7179, 验证集大小: 1435\n", "train_data最大日期: 2023-12-28, 训练天数5\n", "test_data最大日期: 2024-01-05\n", "划分后的训练集大小: 7184, 验证集大小: 1444\n", "train_data最大日期: 2023-12-29, 训练天数5\n", "test_data最大日期: 2024-01-08\n", "划分后的训练集大小: 7177, 验证集大小: 1436\n", "train_data最大日期: 2024-01-02, 训练天数5\n", "test_data最大日期: 2024-01-09\n", "划分后的训练集大小: 7184, 验证集大小: 1441\n", "train_data最大日期: 2024-01-03, 训练天数5\n", "test_data最大日期: 2024-01-10\n", "划分后的训练集大小: 7194, 验证集大小: 1438\n", "train_data最大日期: 2024-01-04, 训练天数5\n", "test_data最大日期: 2024-01-11\n", "划分后的训练集大小: 7198, 验证集大小: 1439\n", "train_data最大日期: 2024-01-05, 训练天数5\n", "test_data最大日期: 2024-01-12\n", "划分后的训练集大小: 7197, 验证集大小: 1443\n", "train_data最大日期: 2024-01-08, 训练天数5\n", "test_data最大日期: 2024-01-15\n", "划分后的训练集大小: 7200, 验证集大小: 1439\n", "train_data最大日期: 2024-01-09, 训练天数5\n", "test_data最大日期: 2024-01-16\n", "划分后的训练集大小: 7197, 验证集大小: 1438\n", "train_data最大日期: 2024-01-10, 训练天数5\n", "test_data最大日期: 2024-01-17\n", "划分后的训练集大小: 7201, 验证集大小: 1442\n", "train_data最大日期: 2024-01-11, 训练天数5\n", "test_data最大日期: 2024-01-18\n", "划分后的训练集大小: 7199, 验证集大小: 1437\n", "train_data最大日期: 2024-01-12, 训练天数5\n", "test_data最大日期: 2024-01-19\n", "划分后的训练集大小: 7192, 验证集大小: 1436\n", "train_data最大日期: 2024-01-15, 训练天数5\n", "test_data最大日期: 2024-01-22\n", "划分后的训练集大小: 7141, 验证集大小: 1388\n", "train_data最大日期: 2024-01-16, 训练天数5\n", "test_data最大日期: 2024-01-23\n", "划分后的训练集大小: 7085, 验证集大小: 1382\n", "train_data最大日期: 2024-01-17, 训练天数5\n", "test_data最大日期: 2024-01-24\n", "划分后的训练集大小: 7075, 验证集大小: 1432\n", "train_data最大日期: 2024-01-18, 训练天数5\n", "test_data最大日期: 2024-01-25\n", "划分后的训练集大小: 7072, 验证集大小: 1434\n", "train_data最大日期: 2024-01-19, 训练天数5\n", "test_data最大日期: 2024-01-26\n", "划分后的训练集大小: 7067, 验证集大小: 1431\n", "train_data最大日期: 2024-01-22, 训练天数5\n", "test_data最大日期: 2024-01-29\n", "划分后的训练集大小: 7110, 验证集大小: 1431\n", "train_data最大日期: 2024-01-23, 训练天数5\n", "test_data最大日期: 2024-01-30\n", "划分后的训练集大小: 7162, 验证集大小: 1434\n", "train_data最大日期: 2024-01-24, 训练天数5\n", "test_data最大日期: 2024-01-31\n", "划分后的训练集大小: 7128, 验证集大小: 1398\n", "train_data最大日期: 2024-01-25, 训练天数5\n", "test_data最大日期: 2024-02-01\n", "划分后的训练集大小: 6927, 验证集大小: 1233\n", "train_data最大日期: 2024-01-26, 训练天数5\n", "test_data最大日期: 2024-02-02\n", "划分后的训练集大小: 6116, 验证集大小: 620\n", "train_data最大日期: 2024-01-29, 训练天数5\n", "test_data最大日期: 2024-02-05\n", "划分后的训练集大小: 4913, 验证集大小: 228\n", "train_data最大日期: 2024-01-30, 训练天数5\n", "test_data最大日期: 2024-02-06\n", "划分后的训练集大小: 3941, 验证集大小: 462\n", "train_data最大日期: 2024-01-31, 训练天数5\n", "test_data最大日期: 2024-02-07\n", "划分后的训练集大小: 3112, 验证集大小: 569\n", "Label 19 is not less than the number of label mappings (19)\n", "[2.0, 5.0, 11.0, 7.0, 3.0, 14.0, 15.0, 4.0, 8.0, 16.0, 12.0, 13.0, 10.0, 9.0, 19.0, 6.0, 1.0, 17.0, 18.0]\n", "train_data最大日期: 2024-02-01, 训练天数5\n", "test_data最大日期: 2024-02-08\n", "划分后的训练集大小: 2889, 验证集大小: 1010\n", "Label 19 is not less than the number of label mappings (18)\n", "[8.0, 13.0, 7.0, 9.0, 11.0, 14.0, 16.0, 10.0, 6.0, 19.0, 18.0, 12.0, 15.0, 17.0, 4.0, 5.0, 3.0, 2.0]\n", "train_data最大日期: 2024-02-02, 训练天数5\n", "test_data最大日期: 2024-02-19\n", "划分后的训练集大小: 3643, 验证集大小: 1374\n", "train_data最大日期: 2024-02-05, 训练天数5\n", "test_data最大日期: 2024-02-20\n", "划分后的训练集大小: 4770, 验证集大小: 1355\n", "train_data最大日期: 2024-02-06, 训练天数5\n", "test_data最大日期: 2024-02-21\n", "划分后的训练集大小: 5710, 验证集大小: 1402\n", "train_data最大日期: 2024-02-07, 训练天数5\n", "test_data最大日期: 2024-02-22\n", "划分后的训练集大小: 6030, 验证集大小: 889\n", "train_data最大日期: 2024-02-08, 训练天数5\n", "test_data最大日期: 2024-02-23\n", "划分后的训练集大小: 6240, 验证集大小: 1220\n", "train_data最大日期: 2024-02-19, 训练天数5\n", "test_data最大日期: 2024-02-26\n", "划分后的训练集大小: 6188, 验证集大小: 1322\n", "train_data最大日期: 2024-02-20, 训练天数5\n", "test_data最大日期: 2024-02-27\n", "划分后的训练集大小: 6110, 验证集大小: 1277\n", "train_data最大日期: 2024-02-21, 训练天数5\n", "test_data最大日期: 2024-02-28\n", "划分后的训练集大小: 6117, 验证集大小: 1409\n", "train_data最大日期: 2024-02-22, 训练天数5\n", "test_data最大日期: 2024-02-29\n", "划分后的训练集大小: 6647, 验证集大小: 1419\n", "train_data最大日期: 2024-02-23, 训练天数5\n", "test_data最大日期: 2024-03-01\n", "划分后的训练集大小: 6861, 验证集大小: 1434\n", "train_data最大日期: 2024-02-26, 训练天数5\n", "test_data最大日期: 2024-03-04\n", "划分后的训练集大小: 6960, 验证集大小: 1421\n", "train_data最大日期: 2024-02-27, 训练天数5\n", "test_data最大日期: 2024-03-05\n", "划分后的训练集大小: 7116, 验证集大小: 1433\n", "train_data最大日期: 2024-02-28, 训练天数5\n", "test_data最大日期: 2024-03-06\n", "划分后的训练集大小: 7113, 验证集大小: 1406\n", "train_data最大日期: 2024-02-29, 训练天数5\n", "test_data最大日期: 2024-03-07\n", "划分后的训练集大小: 7131, 验证集大小: 1437\n", "train_data最大日期: 2024-03-01, 训练天数5\n", "test_data最大日期: 2024-03-08\n", "划分后的训练集大小: 7130, 验证集大小: 1433\n", "train_data最大日期: 2024-03-04, 训练天数5\n", "test_data最大日期: 2024-03-11\n", "划分后的训练集大小: 7147, 验证集大小: 1438\n", "train_data最大日期: 2024-03-05, 训练天数5\n", "test_data最大日期: 2024-03-12\n", "划分后的训练集大小: 7140, 验证集大小: 1426\n", "train_data最大日期: 2024-03-06, 训练天数5\n", "test_data最大日期: 2024-03-13\n", "划分后的训练集大小: 7167, 验证集大小: 1433\n", "train_data最大日期: 2024-03-07, 训练天数5\n", "test_data最大日期: 2024-03-14\n", "划分后的训练集大小: 7162, 验证集大小: 1432\n", "train_data最大日期: 2024-03-08, 训练天数5\n", "test_data最大日期: 2024-03-15\n", "划分后的训练集大小: 7160, 验证集大小: 1431\n", "train_data最大日期: 2024-03-11, 训练天数5\n", "test_data最大日期: 2024-03-18\n", "划分后的训练集大小: 7149, 验证集大小: 1427\n", "train_data最大日期: 2024-03-12, 训练天数5\n", "test_data最大日期: 2024-03-19\n", "划分后的训练集大小: 7154, 验证集大小: 1431\n", "train_data最大日期: 2024-03-13, 训练天数5\n", "test_data最大日期: 2024-03-20\n", "划分后的训练集大小: 7139, 验证集大小: 1418\n", "train_data最大日期: 2024-03-14, 训练天数5\n", "test_data最大日期: 2024-03-21\n", "划分后的训练集大小: 7123, 验证集大小: 1416\n", "train_data最大日期: 2024-03-15, 训练天数5\n", "test_data最大日期: 2024-03-22\n", "划分后的训练集大小: 7114, 验证集大小: 1422\n", "train_data最大日期: 2024-03-18, 训练天数5\n", "test_data最大日期: 2024-03-25\n", "划分后的训练集大小: 7117, 验证集大小: 1430\n", "train_data最大日期: 2024-03-19, 训练天数5\n", "test_data最大日期: 2024-03-26\n", "划分后的训练集大小: 7117, 验证集大小: 1431\n", "train_data最大日期: 2024-03-20, 训练天数5\n", "test_data最大日期: 2024-03-27\n", "划分后的训练集大小: 7108, 验证集大小: 1409\n", "train_data最大日期: 2024-03-21, 训练天数5\n", "test_data最大日期: 2024-03-28\n", "划分后的训练集大小: 7119, 验证集大小: 1427\n", "train_data最大日期: 2024-03-22, 训练天数5\n", "test_data最大日期: 2024-03-29\n", "划分后的训练集大小: 7132, 验证集大小: 1435\n", "train_data最大日期: 2024-03-25, 训练天数5\n", "test_data最大日期: 2024-04-01\n", "划分后的训练集大小: 7134, 验证集大小: 1432\n", "train_data最大日期: 2024-03-26, 训练天数5\n", "test_data最大日期: 2024-04-02\n", "划分后的训练集大小: 7134, 验证集大小: 1431\n", "train_data最大日期: 2024-03-27, 训练天数5\n", "test_data最大日期: 2024-04-03\n", "划分后的训练集大小: 7139, 验证集大小: 1414\n", "train_data最大日期: 2024-03-28, 训练天数5\n", "test_data最大日期: 2024-04-08\n", "划分后的训练集大小: 7134, 验证集大小: 1422\n", "train_data最大日期: 2024-03-29, 训练天数5\n", "test_data最大日期: 2024-04-09\n", "划分后的训练集大小: 7132, 验证集大小: 1433\n", "train_data最大日期: 2024-04-01, 训练天数5\n", "test_data最大日期: 2024-04-10\n", "划分后的训练集大小: 7105, 验证集大小: 1405\n", "train_data最大日期: 2024-04-02, 训练天数5\n", "test_data最大日期: 2024-04-11\n", "划分后的训练集大小: 7084, 验证集大小: 1410\n", "train_data最大日期: 2024-04-03, 训练天数5\n", "test_data最大日期: 2024-04-12\n", "划分后的训练集大小: 7093, 验证集大小: 1423\n", "train_data最大日期: 2024-04-08, 训练天数5\n", "test_data最大日期: 2024-04-15\n", "划分后的训练集大小: 7091, 验证集大小: 1420\n", "train_data最大日期: 2024-04-09, 训练天数5\n", "test_data最大日期: 2024-04-16\n", "划分后的训练集大小: 6564, 验证集大小: 906\n", "train_data最大日期: 2024-04-10, 训练天数5\n", "test_data最大日期: 2024-04-17\n", "划分后的训练集大小: 6561, 验证集大小: 1402\n", "train_data最大日期: 2024-04-11, 训练天数5\n", "test_data最大日期: 2024-04-18\n", "划分后的训练集大小: 6525, 验证集大小: 1374\n", "train_data最大日期: 2024-04-12, 训练天数5\n", "test_data最大日期: 2024-04-19\n", "划分后的训练集大小: 6501, 验证集大小: 1399\n", "train_data最大日期: 2024-04-15, 训练天数5\n", "test_data最大日期: 2024-04-22\n", "划分后的训练集大小: 6517, 验证集大小: 1436\n", "train_data最大日期: 2024-04-16, 训练天数5\n", "test_data最大日期: 2024-04-23\n", "划分后的训练集大小: 7039, 验证集大小: 1428\n", "train_data最大日期: 2024-04-17, 训练天数5\n", "test_data最大日期: 2024-04-24\n", "划分后的训练集大小: 7077, 验证集大小: 1440\n", "train_data最大日期: 2024-04-18, 训练天数5\n", "test_data最大日期: 2024-04-25\n", "划分后的训练集大小: 7144, 验证集大小: 1441\n", "train_data最大日期: 2024-04-19, 训练天数5\n", "test_data最大日期: 2024-04-26\n", "划分后的训练集大小: 7181, 验证集大小: 1436\n", "train_data最大日期: 2024-04-22, 训练天数5\n", "test_data最大日期: 2024-04-29\n", "划分后的训练集大小: 7170, 验证集大小: 1425\n", "train_data最大日期: 2024-04-23, 训练天数5\n", "test_data最大日期: 2024-04-30\n", "划分后的训练集大小: 7141, 验证集大小: 1399\n", "train_data最大日期: 2024-04-24, 训练天数5\n", "test_data最大日期: 2024-05-06\n", "划分后的训练集大小: 7096, 验证集大小: 1395\n", "train_data最大日期: 2024-04-25, 训练天数5\n", "test_data最大日期: 2024-05-07\n", "划分后的训练集大小: 7044, 验证集大小: 1389\n", "train_data最大日期: 2024-04-26, 训练天数5\n", "test_data最大日期: 2024-05-08\n", "划分后的训练集大小: 7009, 验证集大小: 1401\n", "train_data最大日期: 2024-04-29, 训练天数5\n", "test_data最大日期: 2024-05-09\n", "划分后的训练集大小: 7005, 验证集大小: 1421\n", "train_data最大日期: 2024-04-30, 训练天数5\n", "test_data最大日期: 2024-05-10\n", "划分后的训练集大小: 7066, 验证集大小: 1460\n", "train_data最大日期: 2024-05-06, 训练天数5\n", "test_data最大日期: 2024-05-13\n", "划分后的训练集大小: 7107, 验证集大小: 1436\n", "train_data最大日期: 2024-05-07, 训练天数5\n", "test_data最大日期: 2024-05-14\n", "划分后的训练集大小: 7174, 验证集大小: 1456\n", "train_data最大日期: 2024-05-08, 训练天数5\n", "test_data最大日期: 2024-05-15\n", "划分后的训练集大小: 7225, 验证集大小: 1452\n", "train_data最大日期: 2024-05-09, 训练天数5\n", "test_data最大日期: 2024-05-16\n", "划分后的训练集大小: 7257, 验证集大小: 1453\n", "train_data最大日期: 2024-05-10, 训练天数5\n", "test_data最大日期: 2024-05-17\n", "划分后的训练集大小: 7254, 验证集大小: 1457\n", "train_data最大日期: 2024-05-13, 训练天数5\n", "test_data最大日期: 2024-05-20\n", "划分后的训练集大小: 7273, 验证集大小: 1455\n", "train_data最大日期: 2024-05-14, 训练天数5\n", "test_data最大日期: 2024-05-21\n", "划分后的训练集大小: 7278, 验证集大小: 1461\n", "train_data最大日期: 2024-05-15, 训练天数5\n", "test_data最大日期: 2024-05-22\n", "划分后的训练集大小: 7289, 验证集大小: 1463\n", "train_data最大日期: 2024-05-16, 训练天数5\n", "test_data最大日期: 2024-05-23\n", "划分后的训练集大小: 7300, 验证集大小: 1464\n", "train_data最大日期: 2024-05-17, 训练天数5\n", "test_data最大日期: 2024-05-24\n", "划分后的训练集大小: 7304, 验证集大小: 1461\n", "train_data最大日期: 2024-05-20, 训练天数5\n", "test_data最大日期: 2024-05-27\n", "划分后的训练集大小: 7301, 验证集大小: 1452\n", "train_data最大日期: 2024-05-21, 训练天数5\n", "test_data最大日期: 2024-05-28\n", "划分后的训练集大小: 7298, 验证集大小: 1458\n", "train_data最大日期: 2024-05-22, 训练天数5\n", "test_data最大日期: 2024-05-29\n", "划分后的训练集大小: 7291, 验证集大小: 1456\n", "train_data最大日期: 2024-05-23, 训练天数5\n", "test_data最大日期: 2024-05-30\n", "划分后的训练集大小: 7287, 验证集大小: 1460\n", "train_data最大日期: 2024-05-24, 训练天数5\n", "test_data最大日期: 2024-05-31\n", "划分后的训练集大小: 7292, 验证集大小: 1466\n", "train_data最大日期: 2024-05-27, 训练天数5\n", "test_data最大日期: 2024-06-03\n", "划分后的训练集大小: 7302, 验证集大小: 1462\n", "train_data最大日期: 2024-05-28, 训练天数5\n", "test_data最大日期: 2024-06-04\n", "划分后的训练集大小: 7304, 验证集大小: 1460\n", "train_data最大日期: 2024-05-29, 训练天数5\n", "test_data最大日期: 2024-06-05\n", "划分后的训练集大小: 7297, 验证集大小: 1449\n", "train_data最大日期: 2024-05-30, 训练天数5\n", "test_data最大日期: 2024-06-06\n", "划分后的训练集大小: 7225, 验证集大小: 1388\n", "train_data最大日期: 2024-05-31, 训练天数5\n", "test_data最大日期: 2024-06-07\n", "划分后的训练集大小: 7211, 验证集大小: 1452\n", "train_data最大日期: 2024-06-03, 训练天数5\n", "test_data最大日期: 2024-06-11\n", "划分后的训练集大小: 7214, 验证集大小: 1465\n", "train_data最大日期: 2024-06-04, 训练天数5\n", "test_data最大日期: 2024-06-12\n", "划分后的训练集大小: 7226, 验证集大小: 1472\n", "train_data最大日期: 2024-06-05, 训练天数5\n", "test_data最大日期: 2024-06-13\n", "划分后的训练集大小: 7243, 验证集大小: 1466\n", "train_data最大日期: 2024-06-06, 训练天数5\n", "test_data最大日期: 2024-06-14\n", "划分后的训练集大小: 7314, 验证集大小: 1459\n", "train_data最大日期: 2024-06-07, 训练天数5\n", "test_data最大日期: 2024-06-17\n", "划分后的训练集大小: 7322, 验证集大小: 1460\n", "train_data最大日期: 2024-06-11, 训练天数5\n", "test_data最大日期: 2024-06-18\n", "划分后的训练集大小: 7320, 验证集大小: 1463\n", "train_data最大日期: 2024-06-12, 训练天数5\n", "test_data最大日期: 2024-06-19\n", "划分后的训练集大小: 7309, 验证集大小: 1461\n", "train_data最大日期: 2024-06-13, 训练天数5\n", "test_data最大日期: 2024-06-20\n", "划分后的训练集大小: 7306, 验证集大小: 1463\n", "train_data最大日期: 2024-06-14, 训练天数5\n", "test_data最大日期: 2024-06-21\n", "划分后的训练集大小: 7308, 验证集大小: 1461\n", "train_data最大日期: 2024-06-17, 训练天数5\n", "test_data最大日期: 2024-06-24\n", "划分后的训练集大小: 7309, 验证集大小: 1461\n", "train_data最大日期: 2024-06-18, 训练天数5\n", "test_data最大日期: 2024-06-25\n", "划分后的训练集大小: 7308, 验证集大小: 1462\n", "train_data最大日期: 2024-06-19, 训练天数5\n", "test_data最大日期: 2024-06-26\n", "划分后的训练集大小: 7310, 验证集大小: 1463\n", "train_data最大日期: 2024-06-20, 训练天数5\n", "test_data最大日期: 2024-06-27\n", "划分后的训练集大小: 7310, 验证集大小: 1463\n", "train_data最大日期: 2024-06-21, 训练天数5\n", "test_data最大日期: 2024-06-28\n", "划分后的训练集大小: 7315, 验证集大小: 1466\n", "train_data最大日期: 2024-06-24, 训练天数5\n", "test_data最大日期: 2024-07-01\n", "划分后的训练集大小: 7321, 验证集大小: 1467\n", "train_data最大日期: 2024-06-25, 训练天数5\n", "test_data最大日期: 2024-07-02\n", "划分后的训练集大小: 7327, 验证集大小: 1468\n", "train_data最大日期: 2024-06-26, 训练天数5\n", "test_data最大日期: 2024-07-03\n", "划分后的训练集大小: 7327, 验证集大小: 1463\n", "train_data最大日期: 2024-06-27, 训练天数5\n", "test_data最大日期: 2024-07-04\n", "划分后的训练集大小: 7330, 验证集大小: 1466\n", "train_data最大日期: 2024-06-28, 训练天数5\n", "test_data最大日期: 2024-07-05\n", "划分后的训练集大小: 7334, 验证集大小: 1470\n", "train_data最大日期: 2024-07-01, 训练天数5\n", "test_data最大日期: 2024-07-08\n", "划分后的训练集大小: 7335, 验证集大小: 1468\n", "train_data最大日期: 2024-07-02, 训练天数5\n", "test_data最大日期: 2024-07-09\n", "划分后的训练集大小: 7334, 验证集大小: 1467\n", "train_data最大日期: 2024-07-03, 训练天数5\n", "test_data最大日期: 2024-07-10\n", "划分后的训练集大小: 7335, 验证集大小: 1464\n", "train_data最大日期: 2024-07-04, 训练天数5\n", "test_data最大日期: 2024-07-11\n", "划分后的训练集大小: 7340, 验证集大小: 1471\n", "train_data最大日期: 2024-07-05, 训练天数5\n", "test_data最大日期: 2024-07-12\n", "划分后的训练集大小: 7340, 验证集大小: 1470\n", "train_data最大日期: 2024-07-08, 训练天数5\n", "test_data最大日期: 2024-07-15\n", "划分后的训练集大小: 7345, 验证集大小: 1473\n", "train_data最大日期: 2024-07-09, 训练天数5\n", "test_data最大日期: 2024-07-16\n", "划分后的训练集大小: 7350, 验证集大小: 1472\n", "train_data最大日期: 2024-07-10, 训练天数5\n", "test_data最大日期: 2024-07-17\n", "划分后的训练集大小: 7358, 验证集大小: 1472\n", "train_data最大日期: 2024-07-11, 训练天数5\n", "test_data最大日期: 2024-07-18\n", "划分后的训练集大小: 7356, 验证集大小: 1469\n", "train_data最大日期: 2024-07-12, 训练天数5\n", "test_data最大日期: 2024-07-19\n", "划分后的训练集大小: 7353, 验证集大小: 1467\n", "train_data最大日期: 2024-07-15, 训练天数5\n", "test_data最大日期: 2024-07-22\n", "划分后的训练集大小: 7349, 验证集大小: 1469\n", "train_data最大日期: 2024-07-16, 训练天数5\n", "test_data最大日期: 2024-07-23\n", "划分后的训练集大小: 7352, 验证集大小: 1475\n", "train_data最大日期: 2024-07-17, 训练天数5\n", "test_data最大日期: 2024-07-24\n", "划分后的训练集大小: 7349, 验证集大小: 1469\n", "train_data最大日期: 2024-07-18, 训练天数5\n", "test_data最大日期: 2024-07-25\n", "划分后的训练集大小: 7346, 验证集大小: 1466\n", "train_data最大日期: 2024-07-19, 训练天数5\n", "test_data最大日期: 2024-07-26\n", "划分后的训练集大小: 7349, 验证集大小: 1470\n", "train_data最大日期: 2024-07-22, 训练天数5\n", "test_data最大日期: 2024-07-29\n", "划分后的训练集大小: 7343, 验证集大小: 1463\n", "train_data最大日期: 2024-07-23, 训练天数5\n", "test_data最大日期: 2024-07-30\n", "划分后的训练集大小: 7333, 验证集大小: 1465\n", "train_data最大日期: 2024-07-24, 训练天数5\n", "test_data最大日期: 2024-07-31\n", "划分后的训练集大小: 7327, 验证集大小: 1463\n", "train_data最大日期: 2024-07-25, 训练天数5\n", "test_data最大日期: 2024-08-01\n", "划分后的训练集大小: 7318, 验证集大小: 1457\n", "train_data最大日期: 2024-07-26, 训练天数5\n", "test_data最大日期: 2024-08-02\n", "划分后的训练集大小: 7304, 验证集大小: 1456\n", "train_data最大日期: 2024-07-29, 训练天数5\n", "test_data最大日期: 2024-08-05\n", "划分后的训练集大小: 7299, 验证集大小: 1458\n", "train_data最大日期: 2024-07-30, 训练天数5\n", "test_data最大日期: 2024-08-06\n", "划分后的训练集大小: 7286, 验证集大小: 1452\n", "train_data最大日期: 2024-07-31, 训练天数5\n", "test_data最大日期: 2024-08-07\n", "划分后的训练集大小: 7286, 验证集大小: 1463\n", "train_data最大日期: 2024-08-01, 训练天数5\n", "test_data最大日期: 2024-08-08\n", "划分后的训练集大小: 7292, 验证集大小: 1463\n", "train_data最大日期: 2024-08-02, 训练天数5\n", "test_data最大日期: 2024-08-09\n", "划分后的训练集大小: 7301, 验证集大小: 1465\n", "train_data最大日期: 2024-08-05, 训练天数5\n", "test_data最大日期: 2024-08-12\n", "划分后的训练集大小: 7306, 验证集大小: 1463\n", "train_data最大日期: 2024-08-06, 训练天数5\n", "test_data最大日期: 2024-08-13\n", "划分后的训练集大小: 7323, 验证集大小: 1469\n", "train_data最大日期: 2024-08-07, 训练天数5\n", "test_data最大日期: 2024-08-14\n", "划分后的训练集大小: 7331, 验证集大小: 1471\n", "train_data最大日期: 2024-08-08, 训练天数5\n", "test_data最大日期: 2024-08-15\n", "划分后的训练集大小: 7336, 验证集大小: 1468\n", "train_data最大日期: 2024-08-09, 训练天数5\n", "test_data最大日期: 2024-08-16\n", "划分后的训练集大小: 7342, 验证集大小: 1471\n", "train_data最大日期: 2024-08-12, 训练天数5\n", "test_data最大日期: 2024-08-19\n", "划分后的训练集大小: 7343, 验证集大小: 1464\n", "train_data最大日期: 2024-08-13, 训练天数5\n", "test_data最大日期: 2024-08-20\n", "划分后的训练集大小: 7341, 验证集大小: 1467\n", "train_data最大日期: 2024-08-14, 训练天数5\n", "test_data最大日期: 2024-08-21\n", "划分后的训练集大小: 7338, 验证集大小: 1468\n", "train_data最大日期: 2024-08-15, 训练天数5\n", "test_data最大日期: 2024-08-22\n", "划分后的训练集大小: 7340, 验证集大小: 1470\n", "train_data最大日期: 2024-08-16, 训练天数5\n", "test_data最大日期: 2024-08-23\n", "划分后的训练集大小: 7335, 验证集大小: 1466\n", "train_data最大日期: 2024-08-19, 训练天数5\n", "test_data最大日期: 2024-08-26\n", "划分后的训练集大小: 7340, 验证集大小: 1469\n", "train_data最大日期: 2024-08-20, 训练天数5\n", "test_data最大日期: 2024-08-27\n", "划分后的训练集大小: 7345, 验证集大小: 1472\n", "train_data最大日期: 2024-08-21, 训练天数5\n", "test_data最大日期: 2024-08-28\n", "划分后的训练集大小: 7348, 验证集大小: 1471\n", "train_data最大日期: 2024-08-22, 训练天数5\n", "test_data最大日期: 2024-08-29\n", "划分后的训练集大小: 7350, 验证集大小: 1472\n", "train_data最大日期: 2024-08-23, 训练天数5\n", "test_data最大日期: 2024-08-30\n", "划分后的训练集大小: 7354, 验证集大小: 1470\n", "train_data最大日期: 2024-08-26, 训练天数5\n", "test_data最大日期: 2024-09-02\n", "划分后的训练集大小: 7356, 验证集大小: 1471\n", "train_data最大日期: 2024-08-27, 训练天数5\n", "test_data最大日期: 2024-09-03\n", "划分后的训练集大小: 7349, 验证集大小: 1465\n", "train_data最大日期: 2024-08-28, 训练天数5\n", "test_data最大日期: 2024-09-04\n", "划分后的训练集大小: 7346, 验证集大小: 1468\n", "train_data最大日期: 2024-08-29, 训练天数5\n", "test_data最大日期: 2024-09-05\n", "划分后的训练集大小: 7345, 验证集大小: 1471\n", "train_data最大日期: 2024-08-30, 训练天数5\n", "test_data最大日期: 2024-09-06\n", "划分后的训练集大小: 7346, 验证集大小: 1471\n", "train_data最大日期: 2024-09-02, 训练天数5\n", "test_data最大日期: 2024-09-09\n", "划分后的训练集大小: 7341, 验证集大小: 1466\n", "train_data最大日期: 2024-09-03, 训练天数5\n", "test_data最大日期: 2024-09-10\n", "划分后的训练集大小: 7342, 验证集大小: 1466\n", "train_data最大日期: 2024-09-04, 训练天数5\n", "test_data最大日期: 2024-09-11\n", "划分后的训练集大小: 7341, 验证集大小: 1467\n", "train_data最大日期: 2024-09-05, 训练天数5\n", "test_data最大日期: 2024-09-12\n", "划分后的训练集大小: 7335, 验证集大小: 1465\n", "train_data最大日期: 2024-09-06, 训练天数5\n", "test_data最大日期: 2024-09-13\n", "划分后的训练集大小: 7329, 验证集大小: 1465\n", "train_data最大日期: 2024-09-09, 训练天数5\n", "test_data最大日期: 2024-09-18\n", "划分后的训练集大小: 7323, 验证集大小: 1460\n", "train_data最大日期: 2024-09-10, 训练天数5\n", "test_data最大日期: 2024-09-19\n", "划分后的训练集大小: 7319, 验证集大小: 1462\n", "train_data最大日期: 2024-09-11, 训练天数5\n", "test_data最大日期: 2024-09-20\n", "划分后的训练集大小: 7309, 验证集大小: 1457\n", "train_data最大日期: 2024-09-12, 训练天数5\n", "test_data最大日期: 2024-09-23\n", "划分后的训练集大小: 7299, 验证集大小: 1455\n", "train_data最大日期: 2024-09-13, 训练天数5\n", "test_data最大日期: 2024-09-24\n", "划分后的训练集大小: 7284, 验证集大小: 1450\n", "train_data最大日期: 2024-09-18, 训练天数5\n", "test_data最大日期: 2024-09-25\n", "划分后的训练集大小: 7279, 验证集大小: 1455\n", "train_data最大日期: 2024-09-19, 训练天数5\n", "test_data最大日期: 2024-09-26\n", "划分后的训练集大小: 7273, 验证集大小: 1456\n", "train_data最大日期: 2024-09-20, 训练天数5\n", "test_data最大日期: 2024-09-27\n", "划分后的训练集大小: 7234, 验证集大小: 1418\n", "train_data最大日期: 2024-09-23, 训练天数5\n", "test_data最大日期: 2024-09-30\n", "划分后的训练集大小: 6899, 验证集大小: 1120\n", "train_data最大日期: 2024-09-24, 训练天数5\n", "test_data最大日期: 2024-10-08\n", "划分后的训练集大小: 6396, 验证集大小: 947\n", "train_data最大日期: 2024-09-25, 训练天数5\n", "test_data最大日期: 2024-10-09\n", "划分后的训练集大小: 6316, 验证集大小: 1375\n", "train_data最大日期: 2024-09-26, 训练天数5\n", "test_data最大日期: 2024-10-10\n", "划分后的训练集大小: 6254, 验证集大小: 1394\n", "train_data最大日期: 2024-09-27, 训练天数5\n", "test_data最大日期: 2024-10-11\n", "划分后的训练集大小: 6248, 验证集大小: 1412\n", "train_data最大日期: 2024-09-30, 训练天数5\n", "test_data最大日期: 2024-10-14\n", "划分后的训练集大小: 6461, 验证集大小: 1333\n", "train_data最大日期: 2024-10-08, 训练天数5\n", "test_data最大日期: 2024-10-15\n", "划分后的训练集大小: 6615, 验证集大小: 1101\n", "train_data最大日期: 2024-10-09, 训练天数5\n", "test_data最大日期: 2024-10-16\n", "划分后的训练集大小: 6699, 验证集大小: 1459\n", "train_data最大日期: 2024-10-10, 训练天数5\n", "test_data最大日期: 2024-10-17\n", "划分后的训练集大小: 6763, 验证集大小: 1458\n", "train_data最大日期: 2024-10-11, 训练天数5\n", "test_data最大日期: 2024-10-18\n", "划分后的训练集大小: 6804, 验证集大小: 1453\n", "train_data最大日期: 2024-10-14, 训练天数5\n", "test_data最大日期: 2024-10-21\n", "划分后的训练集大小: 6921, 验证集大小: 1450\n", "train_data最大日期: 2024-10-15, 训练天数5\n", "test_data最大日期: 2024-10-22\n", "划分后的训练集大小: 7256, 验证集大小: 1436\n", "train_data最大日期: 2024-10-16, 训练天数5\n", "test_data最大日期: 2024-10-23\n", "划分后的训练集大小: 7241, 验证集大小: 1444\n", "train_data最大日期: 2024-10-17, 训练天数5\n", "test_data最大日期: 2024-10-24\n", "划分后的训练集大小: 7209, 验证集大小: 1426\n", "train_data最大日期: 2024-10-18, 训练天数5\n", "test_data最大日期: 2024-10-25\n", "划分后的训练集大小: 7175, 验证集大小: 1419\n", "train_data最大日期: 2024-10-21, 训练天数5\n", "test_data最大日期: 2024-10-28\n", "划分后的训练集大小: 7110, 验证集大小: 1385\n", "train_data最大日期: 2024-10-22, 训练天数5\n", "test_data最大日期: 2024-10-29\n", "划分后的训练集大小: 7089, 验证集大小: 1415\n", "train_data最大日期: 2024-10-23, 训练天数5\n", "test_data最大日期: 2024-10-30\n", "划分后的训练集大小: 7054, 验证集大小: 1409\n", "train_data最大日期: 2024-10-24, 训练天数5\n", "test_data最大日期: 2024-10-31\n", "划分后的训练集大小: 7031, 验证集大小: 1403\n", "train_data最大日期: 2024-10-25, 训练天数5\n", "test_data最大日期: 2024-11-01\n", "划分后的训练集大小: 7050, 验证集大小: 1438\n", "train_data最大日期: 2024-10-28, 训练天数5\n", "test_data最大日期: 2024-11-04\n", "划分后的训练集大小: 7107, 验证集大小: 1442\n", "train_data最大日期: 2024-10-29, 训练天数5\n", "test_data最大日期: 2024-11-05\n", "划分后的训练集大小: 7104, 验证集大小: 1412\n", "train_data最大日期: 2024-10-30, 训练天数5\n", "test_data最大日期: 2024-11-06\n", "划分后的训练集大小: 7126, 验证集大小: 1431\n", "train_data最大日期: 2024-10-31, 训练天数5\n", "test_data最大日期: 2024-11-07\n", "划分后的训练集大小: 7157, 验证集大小: 1434\n", "train_data最大日期: 2024-11-01, 训练天数5\n", "test_data最大日期: 2024-11-08\n", "划分后的训练集大小: 7147, 验证集大小: 1428\n", "train_data最大日期: 2024-11-04, 训练天数5\n", "test_data最大日期: 2024-11-11\n", "划分后的训练集大小: 7130, 验证集大小: 1425\n", "train_data最大日期: 2024-11-05, 训练天数5\n", "test_data最大日期: 2024-11-12\n", "划分后的训练集大小: 7172, 验证集大小: 1454\n", "train_data最大日期: 2024-11-06, 训练天数5\n", "test_data最大日期: 2024-11-13\n", "划分后的训练集大小: 7186, 验证集大小: 1445\n", "train_data最大日期: 2024-11-07, 训练天数5\n", "test_data最大日期: 2024-11-14\n", "划分后的训练集大小: 7204, 验证集大小: 1452\n", "train_data最大日期: 2024-11-08, 训练天数5\n", "test_data最大日期: 2024-11-15\n", "划分后的训练集大小: 7226, 验证集大小: 1450\n", "train_data最大日期: 2024-11-11, 训练天数5\n", "test_data最大日期: 2024-11-18\n", "划分后的训练集大小: 7235, 验证集大小: 1434\n", "train_data最大日期: 2024-11-12, 训练天数5\n", "test_data最大日期: 2024-11-19\n", "划分后的训练集大小: 7234, 验证集大小: 1453\n", "train_data最大日期: 2024-11-13, 训练天数5\n", "test_data最大日期: 2024-11-20\n", "划分后的训练集大小: 7247, 验证集大小: 1458\n", "train_data最大日期: 2024-11-14, 训练天数5\n", "test_data最大日期: 2024-11-21\n", "划分后的训练集大小: 7241, 验证集大小: 1446\n", "train_data最大日期: 2024-11-15, 训练天数5\n", "test_data最大日期: 2024-11-22\n", "划分后的训练集大小: 7234, 验证集大小: 1443\n", "train_data最大日期: 2024-11-18, 训练天数5\n", "test_data最大日期: 2024-11-25\n", "划分后的训练集大小: 7227, 验证集大小: 1427\n", "train_data最大日期: 2024-11-19, 训练天数5\n", "test_data最大日期: 2024-11-26\n", "划分后的训练集大小: 7222, 验证集大小: 1448\n", "train_data最大日期: 2024-11-20, 训练天数5\n", "test_data最大日期: 2024-11-27\n", "划分后的训练集大小: 7214, 验证集大小: 1450\n", "train_data最大日期: 2024-11-21, 训练天数5\n", "test_data最大日期: 2024-11-28\n", "划分后的训练集大小: 7210, 验证集大小: 1442\n", "train_data最大日期: 2024-11-22, 训练天数5\n", "test_data最大日期: 2024-11-29\n", "划分后的训练集大小: 7200, 验证集大小: 1433\n", "train_data最大日期: 2024-11-25, 训练天数5\n", "test_data最大日期: 2024-12-02\n", "划分后的训练集大小: 7215, 验证集大小: 1442\n", "train_data最大日期: 2024-11-26, 训练天数5\n", "test_data最大日期: 2024-12-03\n", "划分后的训练集大小: 7196, 验证集大小: 1429\n", "train_data最大日期: 2024-11-27, 训练天数5\n", "test_data最大日期: 2024-12-04\n", "划分后的训练集大小: 7185, 验证集大小: 1439\n", "train_data最大日期: 2024-11-28, 训练天数5\n", "test_data最大日期: 2024-12-05\n", "划分后的训练集大小: 7178, 验证集大小: 1435\n", "train_data最大日期: 2024-11-29, 训练天数5\n", "test_data最大日期: 2024-12-06\n", "划分后的训练集大小: 7186, 验证集大小: 1441\n", "train_data最大日期: 2024-12-02, 训练天数5\n", "test_data最大日期: 2024-12-09\n", "划分后的训练集大小: 7196, 验证集大小: 1452\n", "train_data最大日期: 2024-12-03, 训练天数5\n", "test_data最大日期: 2024-12-10\n", "划分后的训练集大小: 7214, 验证集大小: 1447\n", "train_data最大日期: 2024-12-04, 训练天数5\n", "test_data最大日期: 2024-12-11\n", "划分后的训练集大小: 7199, 验证集大小: 1424\n", "train_data最大日期: 2024-12-05, 训练天数5\n", "test_data最大日期: 2024-12-12\n", "划分后的训练集大小: 7198, 验证集大小: 1434\n", "train_data最大日期: 2024-12-06, 训练天数5\n", "test_data最大日期: 2024-12-13\n", "划分后的训练集大小: 7194, 验证集大小: 1437\n", "train_data最大日期: 2024-12-09, 训练天数5\n", "test_data最大日期: 2024-12-16\n", "划分后的训练集大小: 7175, 验证集大小: 1433\n", "train_data最大日期: 2024-12-10, 训练天数5\n", "test_data最大日期: 2024-12-17\n", "划分后的训练集大小: 7184, 验证集大小: 1456\n", "train_data最大日期: 2024-12-11, 训练天数5\n", "test_data最大日期: 2024-12-18\n", "划分后的训练集大小: 7210, 验证集大小: 1450\n", "train_data最大日期: 2024-12-12, 训练天数5\n", "test_data最大日期: 2024-12-19\n", "划分后的训练集大小: 7215, 验证集大小: 1439\n", "train_data最大日期: 2024-12-13, 训练天数5\n", "test_data最大日期: 2024-12-20\n", "划分后的训练集大小: 7222, 验证集大小: 1444\n", "train_data最大日期: 2024-12-16, 训练天数5\n", "test_data最大日期: 2024-12-23\n", "划分后的训练集大小: 7167, 验证集大小: 1378\n", "train_data最大日期: 2024-12-17, 训练天数5\n", "test_data最大日期: 2024-12-24\n", "划分后的训练集大小: 7153, 验证集大小: 1442\n", "train_data最大日期: 2024-12-18, 训练天数5\n", "test_data最大日期: 2024-12-25\n", "划分后的训练集大小: 7117, 验证集大小: 1414\n", "train_data最大日期: 2024-12-19, 训练天数5\n", "test_data最大日期: 2024-12-26\n", "划分后的训练集大小: 7117, 验证集大小: 1439\n", "train_data最大日期: 2024-12-20, 训练天数5\n", "test_data最大日期: 2024-12-27\n", "划分后的训练集大小: 7128, 验证集大小: 1455\n", "train_data最大日期: 2024-12-23, 训练天数5\n", "test_data最大日期: 2024-12-30\n", "划分后的训练集大小: 7212, 验证集大小: 1462\n", "train_data最大日期: 2024-12-24, 训练天数5\n", "test_data最大日期: 2024-12-31\n", "划分后的训练集大小: 7224, 验证集大小: 1454\n", "train_data最大日期: 2024-12-25, 训练天数5\n", "test_data最大日期: 2025-01-02\n", "划分后的训练集大小: 7269, 验证集大小: 1459\n", "train_data最大日期: 2024-12-26, 训练天数5\n", "test_data最大日期: 2025-01-03\n", "划分后的训练集大小: 7258, 验证集大小: 1428\n", "train_data最大日期: 2024-12-27, 训练天数5\n", "test_data最大日期: 2025-01-06\n", "划分后的训练集大小: 7207, 验证集大小: 1404\n", "train_data最大日期: 2024-12-30, 训练天数5\n", "test_data最大日期: 2025-01-07\n", "划分后的训练集大小: 7188, 验证集大小: 1443\n", "train_data最大日期: 2024-12-31, 训练天数5\n", "test_data最大日期: 2025-01-08\n", "划分后的训练集大小: 7183, 验证集大小: 1449\n", "train_data最大日期: 2025-01-02, 训练天数5\n", "test_data最大日期: 2025-01-09\n", "划分后的训练集大小: 7180, 验证集大小: 1456\n", "train_data最大日期: 2025-01-03, 训练天数5\n", "test_data最大日期: 2025-01-10\n", "划分后的训练集大小: 7213, 验证集大小: 1461\n", "train_data最大日期: 2025-01-06, 训练天数5\n", "test_data最大日期: 2025-01-13\n", "划分后的训练集大小: 7263, 验证集大小: 1454\n", "train_data最大日期: 2025-01-07, 训练天数5\n", "test_data最大日期: 2025-01-14\n", "划分后的训练集大小: 7278, 验证集大小: 1458\n", "train_data最大日期: 2025-01-08, 训练天数5\n", "test_data最大日期: 2025-01-15\n", "划分后的训练集大小: 7293, 验证集大小: 1464\n", "train_data最大日期: 2025-01-09, 训练天数5\n", "test_data最大日期: 2025-01-16\n", "划分后的训练集大小: 7298, 验证集大小: 1461\n", "train_data最大日期: 2025-01-10, 训练天数5\n", "test_data最大日期: 2025-01-17\n", "划分后的训练集大小: 7293, 验证集大小: 1456\n", "train_data最大日期: 2025-01-13, 训练天数5\n", "test_data最大日期: 2025-01-20\n", "划分后的训练集大小: 7302, 验证集大小: 1463\n", "train_data最大日期: 2025-01-14, 训练天数5\n", "test_data最大日期: 2025-01-21\n", "划分后的训练集大小: 7306, 验证集大小: 1462\n", "train_data最大日期: 2025-01-15, 训练天数5\n", "test_data最大日期: 2025-01-22\n", "划分后的训练集大小: 7293, 验证集大小: 1451\n", "train_data最大日期: 2025-01-16, 训练天数5\n", "test_data最大日期: 2025-01-23\n", "划分后的训练集大小: 7270, 验证集大小: 1438\n", "train_data最大日期: 2025-01-17, 训练天数5\n", "test_data最大日期: 2025-01-24\n", "划分后的训练集大小: 7266, 验证集大小: 1452\n", "train_data最大日期: 2025-01-20, 训练天数5\n", "test_data最大日期: 2025-01-27\n", "划分后的训练集大小: 7262, 验证集大小: 1459\n", "train_data最大日期: 2025-01-21, 训练天数5\n", "test_data最大日期: 2025-02-05\n", "划分后的训练集大小: 7261, 验证集大小: 1461\n", "train_data最大日期: 2025-01-22, 训练天数5\n", "test_data最大日期: 2025-02-06\n", "划分后的训练集大小: 7281, 验证集大小: 1471\n", "train_data最大日期: 2025-01-23, 训练天数5\n", "test_data最大日期: 2025-02-07\n", "划分后的训练集大小: 7307, 验证集大小: 1464\n", "train_data最大日期: 2025-01-24, 训练天数5\n", "test_data最大日期: 2025-02-10\n", "划分后的训练集大小: 7311, 验证集大小: 1456\n", "train_data最大日期: 2025-01-27, 训练天数5\n", "test_data最大日期: 2025-02-11\n", "划分后的训练集大小: 7301, 验证集大小: 1449\n", "train_data最大日期: 2025-02-05, 训练天数5\n", "test_data最大日期: 2025-02-12\n", "划分后的训练集大小: 7294, 验证集大小: 1454\n", "train_data最大日期: 2025-02-06, 训练天数5\n", "test_data最大日期: 2025-02-13\n", "划分后的训练集大小: 7284, 验证集大小: 1461\n", "train_data最大日期: 2025-02-07, 训练天数5\n", "test_data最大日期: 2025-02-14\n", "划分后的训练集大小: 7289, 验证集大小: 1469\n", "train_data最大日期: 2025-02-10, 训练天数5\n", "test_data最大日期: 2025-02-17\n", "划分后的训练集大小: 7302, 验证集大小: 1469\n", "train_data最大日期: 2025-02-11, 训练天数5\n", "test_data最大日期: 2025-02-18\n", "划分后的训练集大小: 7317, 验证集大小: 1464\n", "train_data最大日期: 2025-02-12, 训练天数5\n", "test_data最大日期: 2025-02-19\n", "划分后的训练集大小: 7327, 验证集大小: 1464\n", "train_data最大日期: 2025-02-13, 训练天数5\n", "test_data最大日期: 2025-02-20\n", "划分后的训练集大小: 7331, 验证集大小: 1465\n", "train_data最大日期: 2025-02-14, 训练天数5\n", "test_data最大日期: 2025-02-21\n", "划分后的训练集大小: 7322, 验证集大小: 1460\n", "train_data最大日期: 2025-02-17, 训练天数5\n", "test_data最大日期: 2025-02-24\n", "划分后的训练集大小: 7317, 验证集大小: 1464\n", "train_data最大日期: 2025-02-18, 训练天数5\n", "test_data最大日期: 2025-02-25\n", "划分后的训练集大小: 7310, 验证集大小: 1457\n", "train_data最大日期: 2025-02-19, 训练天数5\n", "test_data最大日期: 2025-02-26\n", "划分后的训练集大小: 7302, 验证集大小: 1456\n", "train_data最大日期: 2025-02-20, 训练天数5\n", "test_data最大日期: 2025-02-27\n", "划分后的训练集大小: 7288, 验证集大小: 1451\n", "train_data最大日期: 2025-02-21, 训练天数5\n", "test_data最大日期: 2025-02-28\n", "划分后的训练集大小: 7287, 验证集大小: 1459\n", "train_data最大日期: 2025-02-24, 训练天数5\n", "test_data最大日期: 2025-03-03\n", "划分后的训练集大小: 7289, 验证集大小: 1466\n", "train_data最大日期: 2025-02-25, 训练天数5\n", "test_data最大日期: 2025-03-04\n", "划分后的训练集大小: 7299, 验证集大小: 1467\n", "train_data最大日期: 2025-02-26, 训练天数5\n", "test_data最大日期: 2025-03-05\n", "划分后的训练集大小: 7304, 验证集大小: 1461\n", "train_data最大日期: 2025-02-27, 训练天数5\n", "test_data最大日期: 2025-03-06\n", "划分后的训练集大小: 7314, 验证集大小: 1461\n", "train_data最大日期: 2025-02-28, 训练天数5\n", "test_data最大日期: 2025-03-07\n", "划分后的训练集大小: 7312, 验证集大小: 1457\n", "train_data最大日期: 2025-03-03, 训练天数5\n", "test_data最大日期: 2025-03-10\n", "划分后的训练集大小: 7300, 验证集大小: 1454\n", "train_data最大日期: 2025-03-04, 训练天数5\n", "test_data最大日期: 2025-03-11\n", "划分后的训练集大小: 7294, 验证集大小: 1461\n", "train_data最大日期: 2025-03-05, 训练天数5\n", "test_data最大日期: 2025-03-12\n", "划分后的训练集大小: 7290, 验证集大小: 1457\n", "train_data最大日期: 2025-03-06, 训练天数5\n", "test_data最大日期: 2025-03-13\n", "划分后的训练集大小: 7289, 验证集大小: 1460\n", "train_data最大日期: 2025-03-07, 训练天数5\n", "test_data最大日期: 2025-03-14\n", "划分后的训练集大小: 7298, 验证集大小: 1466\n", "train_data最大日期: 2025-03-10, 训练天数5\n", "test_data最大日期: 2025-03-17\n", "划分后的训练集大小: 7304, 验证集大小: 1460\n", "train_data最大日期: 2025-03-11, 训练天数5\n", "test_data最大日期: 2025-03-18\n", "划分后的训练集大小: 7305, 验证集大小: 1462\n", "train_data最大日期: 2025-03-12, 训练天数5\n", "test_data最大日期: 2025-03-19\n", "划分后的训练集大小: 7306, 验证集大小: 1458\n", "train_data最大日期: 2025-03-13, 训练天数5\n", "test_data最大日期: 2025-03-20\n", "划分后的训练集大小: 7294, 验证集大小: 1448\n", "train_data最大日期: 2025-03-14, 训练天数5\n", "test_data最大日期: 2025-03-21\n", "划分后的训练集大小: 7277, 验证集大小: 1449\n", "train_data最大日期: 2025-03-17, 训练天数5\n", "test_data最大日期: 2025-03-24\n", "划分后的训练集大小: 7272, 验证集大小: 1455\n", "train_data最大日期: 2025-03-18, 训练天数5\n", "test_data最大日期: 2025-03-25\n", "划分后的训练集大小: 7253, 验证集大小: 1443\n", "train_data最大日期: 2025-03-19, 训练天数5\n", "test_data最大日期: 2025-03-26\n", "划分后的训练集大小: 7248, 验证集大小: 1453\n", "train_data最大日期: 2025-03-20, 训练天数5\n", "test_data最大日期: 2025-03-27\n", "划分后的训练集大小: 7241, 验证集大小: 1441\n", "train_data最大日期: 2025-03-21, 训练天数5\n", "test_data最大日期: 2025-03-28\n", "划分后的训练集大小: 7238, 验证集大小: 1446\n", "train_data最大日期: 2025-03-24, 训练天数5\n", "test_data最大日期: 2025-03-31\n", "划分后的训练集大小: 7237, 验证集大小: 1454\n", "train_data最大日期: 2025-03-25, 训练天数5\n", "test_data最大日期: 2025-04-01\n", "划分后的训练集大小: 7252, 验证集大小: 1458\n", "train_data最大日期: 2025-03-26, 训练天数5\n", "test_data最大日期: 2025-04-02\n", "划分后的训练集大小: 7261, 验证集大小: 1462\n", "train_data最大日期: 2025-03-27, 训练天数5\n", "test_data最大日期: 2025-04-03\n", "划分后的训练集大小: 7281, 验证集大小: 1461\n", "train_data最大日期: 2025-03-28, 训练天数5\n", "test_data最大日期: 2025-04-07\n", "划分后的训练集大小: 7274, 验证集大小: 1439\n", "train_data最大日期: 2025-03-31, 训练天数5\n", "test_data最大日期: 2025-04-08\n", "划分后的训练集大小: 7083, 验证集大小: 1263\n", "train_data最大日期: 2025-04-01, 训练天数5\n", "test_data最大日期: 2025-04-09\n", "划分后的训练集大小: 6969, 验证集大小: 1344\n" ] } ], "source": [ "\n", "gc.collect()\n", "\n", "print('finish')\n", "# qdf = qdf[qdf['trade_date'] >= '2022-01-01']\n", "\n", "final_predictions = rolling_train_predict(\n", " pdf[(pdf['trade_date'] >= '2022-01-01') & (pdf['trade_date'] <= '2029-03-26')], 5, 1, feature_columns,\n", " days=days, validation_days=0, filter_index=filter_index, params=light_params)\n", "final_predictions.to_csv('predictions_test.tsv', index=False)\n" ] }, { "cell_type": "code", "execution_count": 63, "id": "0dc75517-c857-4f1d-8815-e807400a6d33", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:59:10.691231Z", "start_time": "2025-04-10T14:59:10.687575Z" } }, "outputs": [], "source": [ "# pdf1 = select_pre_zt_stocks_dynamic(df[(df['trade_date'] >= '2022-03-26') & (df['trade_date'] <= '2029-03-26')])\n", "# pdf1 = pdf1.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n", "# pdf1 = pdf1.replace([np.inf, -np.inf], np.nan)\n", "#\n", "# feature_columns = [col for col in pdf1.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", "# # feature_columns = [col for col in feature_columns if col not in ['ts_code', 'trade_date', 'vol_std_5', 'cov', 'delta_cov', 'alpha_22_improved', 'alpha_007', 'consecutive_up_limit', 'mv_volatility', 'volume_growth', 'mv_growth', 'arbr']]\n", "#\n", "# print(feature_columns)\n", "# numeric_columns = pdf.select_dtypes(include=['float64', 'int64']).columns\n", "# numeric_columns = [col for col in numeric_columns if col in feature_columns]\n", "#\n", "# pdf1 = cross_sectional_quantile_filter(pdf1, numeric_columns)\n", "# pdf1 = cross_sectional_standardization(pdf1, numeric_columns)\n", "#\n", "# # pdf1 = cross_sectional_standardization(pdf1, numeric_columns)\n", "# # pdf1 = pdf1[pdf1['trade_date'] <= '2025-03-26']\n", "# pdf1 = pdf1.sort_values(by=['ts_code', 'trade_date'])\n", "# filter_index1 = pdf1['future_return'].between(pdf1['future_return'].quantile(0.01), pdf1['future_return'].quantile(0.99))\n", "#\n", "# print('-----------------------------------------')\n", "# pdf2 = select_pre_zt_stocks_dynamic(df[(df['trade_date'] >= '2022-03-26') & (df['trade_date'] <= '2025-03-26')])\n", "# pdf2 = pdf2.merge(industry_df, on=['cat_l2_code', 'trade_date'], how='left')\n", "# pdf2 = pdf2.replace([np.inf, -np.inf], np.nan)\n", "#\n", "# pdf2 = cross_sectional_quantile_filter(pdf2, numeric_columns)\n", "# pdf2 = cross_sectional_standardization(pdf2, numeric_columns)\n", "#\n", "# # pdf2 = cross_sectional_standardization(pdf2, numeric_columns)\n", "#\n", "# # pdf2 = pdf2[pdf2['trade_date'] <= '2025-03-26']\n", "# pdf2 = pdf2.sort_values(by=['ts_code', 'trade_date'])\n", "# filter_index2 = pdf2['future_return'].between(pdf2['future_return'].quantile(0.01), pdf2['future_return'].quantile(0.99))\n" ] }, { "cell_type": "code", "execution_count": 64, "id": "8299a6f461097f14", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:59:10.827746Z", "start_time": "2025-04-10T14:59:10.824106Z" } }, "outputs": [], "source": [ "# are_equal = pdf1[filter_index1].equals(pdf2[filter_index2])\n", "# print(are_equal) # 输出 True 或 False\n", "#\n", "# are_equal = pdf1.equals(pdf2)\n", "# print(are_equal) # 输出 True 或 False\n", "#\n", "# are_equal = filter_index1.equals(filter_index2)\n", "# print(are_equal) # 输出 True 或 False" ] }, { "cell_type": "code", "execution_count": 65, "id": "3f5079aa2c937c22", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:59:10.845209Z", "start_time": "2025-04-10T14:59:10.837769Z" } }, "outputs": [], "source": [ "# final_predictions1 = rolling_train_predict(\n", "# pdf1[(pdf1['trade_date'] >= '2024-12-01')], 5, 1, feature_columns,\n", "# days=days, validation_days=0, filter_index=filter_index1, params=light_params)\n", "# final_predictions.to_csv('test1.tsv', index=False)\n", "#\n", "# final_predictions2 = rolling_train_predict(\n", "# pdf2[(pdf2['trade_date'] >= '2024-12-01')], 5, 1, feature_columns,\n", "# days=days, validation_days=0, filter_index=filter_index2, params=light_params)\n", "# final_predictions2.to_csv('test2.tsv', index=False)" ] }, { "cell_type": "code", "execution_count": 66, "id": "199b12e7e20e4e6a", "metadata": { "ExecuteTime": { "end_time": "2025-04-10T14:59:10.901682Z", "start_time": "2025-04-10T14:59:10.887182Z" } }, "outputs": [], "source": [ "# print(final_predictions1['trade_date'].max())\n", "# print(final_predictions2['trade_date'].max())\n", "#\n", "# are_equal = final_predictions1[(final_predictions1['trade_date'] >= '2022-12-01') & (final_predictions1['trade_date'] <= '2025-03-26')].equals(final_predictions2[(final_predictions2['trade_date'] >= '2022-12-01') & (final_predictions2['trade_date'] <= '2025-03-26')])\n", "# print(are_equal) # 输出 True 或 False" ] } ], "metadata": { "kernelspec": { "display_name": "new_trader", "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 }