NewStock/main/data/index_and_industry.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "initial_id",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:27.092313Z",
     "start_time": "2025-04-09T14:57:26.124592Z"
    }
   },
   "outputs": [],
   "source": [
    "from operator import index\n",
    "\n",
    "import tushare as ts\n",
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f448da220816bf98",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:37.680808Z",
     "start_time": "2025-04-09T14:57:27.392846Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "数据已经成功存储到index_data.h5文件中\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\liaozhaorun\\AppData\\Local\\Temp\\ipykernel_16940\\1832869062.py:13: FutureWarning: The behavior of DataFrame concatenation with empty or all-NA entries is deprecated. In a future version, this will no longer exclude empty or all-NA columns when determining the result dtypes. To retain the old behavior, exclude the relevant entries before the concat operation.\n",
      "  final_df = pd.concat(all_data, ignore_index=True)\n"
     ]
    }
   ],
   "source": [
    "# 定义四个指数\n",
    "index_list = ['399300.SH', '000905.SH', '000852.SH', '399006.SZ']\n",
    "\n",
    "# 获取并存储数据\n",
    "all_data = []\n",
    "\n",
    "for ts_code in index_list:\n",
    "    df = pro.index_daily(ts_code=ts_code)  # 可根据需要设置日期\n",
    "    df['ts_code'] = ts_code  # 添加ts_code列来区分数据\n",
    "    all_data.append(df)\n",
    "\n",
    "# 合并所有数据\n",
    "final_df = pd.concat(all_data, ignore_index=True)\n",
    "\n",
    "# 存储到H5文件\n",
    "final_df.to_hdf('../../data/index_data.h5', key='index_data', mode='w')\n",
    "\n",
    "print(\"数据已经成功存储到index_data.h5文件中\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "907f732d3c397bf",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:37.730922Z",
     "start_time": "2025-04-09T14:57:37.695917Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         ts_code trade_date      close       open       high        low  \\\n",
      "0      000905.SH   20250509  5721.7225  5770.4410  5770.4410  5705.1654   \n",
      "1      000905.SH   20250508  5773.8056  5731.7157  5783.7915  5724.9511   \n",
      "2      000905.SH   20250507  5750.2911  5805.6560  5819.2422  5713.2734   \n",
      "3      000905.SH   20250506  5740.3338  5668.8762  5740.3338  5666.4698   \n",
      "4      000905.SH   20250430  5631.8249  5604.6537  5647.7821  5603.1718   \n",
      "...          ...        ...        ...        ...        ...        ...   \n",
      "13501  399006.SZ   20100607  1069.4680  1005.0280  1075.2250  1001.7020   \n",
      "13502  399006.SZ   20100604  1027.6810   989.6810  1027.6810   986.5040   \n",
      "13503  399006.SZ   20100603   998.3940  1002.3550  1026.7020   997.7750   \n",
      "13504  399006.SZ   20100602   997.1190   967.6090   997.1190   952.6110   \n",
      "13505  399006.SZ   20100601   973.2330   986.0150   994.7930   948.1180   \n",
      "\n",
      "       pre_close    change  pct_chg           vol        amount  \n",
      "0      5773.8056  -52.0831  -0.9021  1.239390e+08  1.781623e+08  \n",
      "1      5750.2911   23.5145   0.4089  1.361403e+08  1.870326e+08  \n",
      "2      5740.3338    9.9573   0.1735  1.710118e+08  2.275662e+08  \n",
      "3      5631.8249  108.5089   1.9267  1.627736e+08  2.170600e+08  \n",
      "4      5604.9057   26.9192   0.4803  1.383866e+08  1.816166e+08  \n",
      "...          ...       ...      ...           ...           ...  \n",
      "13501  1027.6810   41.7870   4.0661  2.655275e+06  9.106095e+06  \n",
      "13502   998.3940   29.2870   2.9334  1.500295e+06  5.269441e+06  \n",
      "13503   997.1190    1.2750   0.1279  1.616805e+06  6.240835e+06  \n",
      "13504   973.2330   23.8860   2.4543  1.074628e+06  4.001206e+06  \n",
      "13505  1000.0000  -26.7670  -2.6767  1.356285e+06  4.924177e+06  \n",
      "\n",
      "[13506 rows x 11 columns]\n"
     ]
    }
   ],
   "source": [
    "h5_filename = '../../data/index_data.h5'\n",
    "key = '/index_data'\n",
    "with pd.HDFStore(h5_filename, mode='r') as store:\n",
    "    df = store[key]\n",
    "    print(df)\n"
   ]
  }
 ],
 "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
}