NewStock/code/data/index_and_industry.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "id": "initial_id",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-03-30T16:42:23.864275Z",
     "start_time": "2025-03-30T16:42:22.963221Z"
    }
   },
   "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()"
   ],
   "outputs": [],
   "execution_count": 1
  },
  {
   "cell_type": "code",
   "id": "f448da220816bf98",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-03-30T16:42:25.559047Z",
     "start_time": "2025-03-30T16:42:23.868783Z"
    }
   },
   "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\")"
   ],
   "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_6192\\3209233630.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"
     ]
    }
   ],
   "execution_count": 2
  },
  {
   "cell_type": "code",
   "id": "907f732d3c397bf",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-03-30T16:42:25.802535Z",
     "start_time": "2025-03-30T16:42:25.766399Z"
    }
   },
   "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"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         ts_code trade_date      close       open       high        low  \\\n",
      "0      000905.SH   20250328  5916.0314  5954.7297  5973.8015  5904.9159   \n",
      "1      000905.SH   20250327  5957.6017  5932.5165  6000.6615  5891.7664   \n",
      "2      000905.SH   20250326  5948.4986  5935.8537  5983.4739  5935.8537   \n",
      "3      000905.SH   20250325  5946.9510  5969.4164  5993.9312  5929.6734   \n",
      "4      000905.SH   20250324  5969.0789  5973.0466  5987.0606  5882.8780   \n",
      "...          ...        ...        ...        ...        ...        ...   \n",
      "13423  399006.SZ   20100607  1069.4680  1005.0280  1075.2250  1001.7020   \n",
      "13424  399006.SZ   20100604  1027.6810   989.6810  1027.6810   986.5040   \n",
      "13425  399006.SZ   20100603   998.3940  1002.3550  1026.7020   997.7750   \n",
      "13426  399006.SZ   20100602   997.1190   967.6090   997.1190   952.6110   \n",
      "13427  399006.SZ   20100601   973.2330   986.0150   994.7930   948.1180   \n",
      "\n",
      "       pre_close   change  pct_chg           vol        amount  \n",
      "0      5957.6017 -41.5703  -0.6978  1.342619e+08  1.688995e+08  \n",
      "1      5948.4986   9.1031   0.1530  1.347089e+08  1.765905e+08  \n",
      "2      5946.9510   1.5476   0.0260  1.367021e+08  1.716958e+08  \n",
      "3      5969.0789 -22.1279  -0.3707  1.474839e+08  1.922270e+08  \n",
      "4      5971.9302  -2.8513  -0.0477  1.691924e+08  2.200943e+08  \n",
      "...          ...      ...      ...           ...           ...  \n",
      "13423  1027.6810  41.7870   4.0661  2.655275e+06  9.106095e+06  \n",
      "13424   998.3940  29.2870   2.9334  1.500295e+06  5.269441e+06  \n",
      "13425   997.1190   1.2750   0.1279  1.616805e+06  6.240835e+06  \n",
      "13426   973.2330  23.8860   2.4543  1.074628e+06  4.001206e+06  \n",
      "13427  1000.0000 -26.7670  -2.6767  1.356285e+06  4.924177e+06  \n",
      "\n",
      "[13428 rows x 11 columns]\n"
     ]
    }
   ],
   "execution_count": 3
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}