NewStock/main/data/update/update_stk_limit.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "500802dc-7a20-48b7-a470-a4bae3ec534b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:41.532210Z",
     "start_time": "2025-04-09T14:57:40.584930Z"
    }
   },
   "outputs": [],
   "source": [
    "import tushare as ts\n",
    "\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5a84bc9da6d54868",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:04.911924Z",
     "start_time": "2025-04-09T14:57:41.540345Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        ts_code trade_date\n",
      "4979  600202.SH   20260206\n",
      "4980  600203.SH   20260206\n",
      "4981  600206.SH   20260206\n",
      "4969  600189.SH   20260206\n",
      "7454  920964.BJ   20260206\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 11812821 entries, 0 to 37293\n",
      "Data columns (total 2 columns):\n",
      " #   Column      Dtype \n",
      "---  ------      ----- \n",
      " 0   ts_code     object\n",
      " 1   trade_date  object\n",
      "dtypes: object(2)\n",
      "memory usage: 270.4+ MB\n",
      "None\n",
      "20260206\n",
      "20260209\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "h5_filename = '/mnt/d/PyProject/NewStock/data/stk_limit.h5'\n",
    "key = '/stk_limit'\n",
    "max_date = None\n",
    "with pd.HDFStore(h5_filename, mode='r') as store:\n",
    "    df = store[key][['ts_code', 'trade_date']]\n",
    "    print(df.sort_values(by='trade_date', ascending=True).tail())\n",
    "    print(df.info())\n",
    "    max_date = df['trade_date'].max()\n",
    "\n",
    "print(max_date)\n",
    "trade_cal = pro.trade_cal(exchange='', start_date='20170101', end_date='20260310')\n",
    "trade_cal = trade_cal[trade_cal['is_open'] == 1]  # 只保留交易日\n",
    "trade_dates = trade_cal[trade_cal['cal_date'] > max_date]['cal_date'].tolist()\n",
    "start_date = min(trade_dates)\n",
    "print(start_date)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "bb3191de-27a2-4c89-a3b5-32a0d7b9496f",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.342522Z",
     "start_time": "2025-04-09T14:58:05.259974Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "任务 20260310 完成\n",
      "任务 20260309 完成\n",
      "任务 20260306 完成\n",
      "任务 20260305 完成\n",
      "任务 20260304 完成\n",
      "任务 20260303 完成\n",
      "任务 20260302 完成\n",
      "任务 20260227 完成\n",
      "任务 20260226 完成\n",
      "任务 20260225 完成\n",
      "任务 20260224 完成\n",
      "任务 20260213 完成\n",
      "任务 20260212 完成\n",
      "任务 20260211 完成\n",
      "任务 20260210 完成\n",
      "任务 20260209 完成\n"
     ]
    }
   ],
   "source": [
    "from concurrent.futures import ThreadPoolExecutor, as_completed\n",
    "\n",
    "all_daily_data = []\n",
    "\n",
    "# API 调用计数和时间控制变量\n",
    "api_call_count = 0\n",
    "batch_start_time = time.time()\n",
    "\n",
    "\n",
    "def get_data(trade_date):\n",
    "    time.sleep(0.1)\n",
    "    stk_limit_data = pro.stk_limit(trade_date=trade_date)\n",
    "    if stk_limit_data is not None and not stk_limit_data.empty:\n",
    "        return stk_limit_data\n",
    "\n",
    "\n",
    "with ThreadPoolExecutor(max_workers=2) as executor:\n",
    "    future_to_date = {executor.submit(get_data, td): td for td in trade_dates}\n",
    "\n",
    "    for future in as_completed(future_to_date):\n",
    "        trade_date = future_to_date[future]  # 获取对应的交易日期\n",
    "        try:\n",
    "            result = future.result()  # 获取任务执行的结果\n",
    "            if result is not None:\n",
    "                all_daily_data.append(result)\n",
    "            print(f\"任务 {trade_date} 完成\")\n",
    "        except Exception as e:\n",
    "            print(f\"获取 {trade_date} 数据时出错: {e}\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "96a81aa5890ea3c3",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.353560Z",
     "start_time": "2025-04-09T14:58:09.346528Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[     trade_date    ts_code  up_limit  down_limit\n",
      "0      20260213  000001.SZ     12.06        9.86\n",
      "1      20260213  000002.SZ      5.41        4.43\n",
      "2      20260213  000004.SZ      8.36        7.56\n",
      "3      20260213  000006.SZ     10.12        8.28\n",
      "4      20260213  000007.SZ     13.44       11.00\n",
      "...         ...        ...       ...         ...\n",
      "7476   20260213  920978.BJ     39.09       21.05\n",
      "7477   20260213  920981.BJ     41.61       22.41\n",
      "7478   20260213  920982.BJ    284.06      152.96\n",
      "7479   20260213  920985.BJ     11.34        6.12\n",
      "7480   20260213  920992.BJ     21.77       11.73\n",
      "\n",
      "[7481 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20260212  000001.SZ     12.18        9.96\n",
      "1      20260212  000002.SZ      5.38        4.40\n",
      "2      20260212  000004.SZ      8.80        7.96\n",
      "3      20260212  000006.SZ     10.29        8.42\n",
      "4      20260212  000007.SZ     13.31       10.89\n",
      "...         ...        ...       ...         ...\n",
      "7476   20260212  920978.BJ     39.93       21.51\n",
      "7477   20260212  920981.BJ     41.60       22.40\n",
      "7478   20260212  920982.BJ    284.29      153.09\n",
      "7479   20260212  920985.BJ     11.01        5.93\n",
      "7480   20260212  920992.BJ     21.86       11.78\n",
      "\n",
      "[7481 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20260211  000001.SZ     12.17        9.95\n",
      "1      20260211  000002.SZ      5.37        4.39\n",
      "2      20260211  000004.SZ      9.26        8.38\n",
      "3      20260211  000006.SZ     10.18        8.33\n",
      "4      20260211  000007.SZ     13.37       10.94\n",
      "...         ...        ...       ...         ...\n",
      "7469   20260211  920978.BJ     41.02       22.10\n",
      "7470   20260211  920981.BJ     41.91       22.57\n",
      "7471   20260211  920982.BJ    286.35      154.19\n",
      "7472   20260211  920985.BJ     11.34        6.12\n",
      "7473   20260211  920992.BJ     22.04       11.88\n",
      "\n",
      "[7474 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20260210  000001.SZ     12.18        9.96\n",
      "1      20260210  000002.SZ      5.46        4.46\n",
      "2      20260210  000004.SZ      9.74        8.82\n",
      "3      20260210  000006.SZ     10.32        8.44\n",
      "4      20260210  000007.SZ     13.53       11.07\n",
      "...         ...        ...       ...         ...\n",
      "7466   20260210  920978.BJ     41.71       22.47\n",
      "7467   20260210  920981.BJ     42.05       22.65\n",
      "7468   20260210  920982.BJ    289.90      156.10\n",
      "7469   20260210  920985.BJ     11.83        6.37\n",
      "7470   20260210  920992.BJ     22.33       12.03\n",
      "\n",
      "[7471 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20260209  000001.SZ     12.16        9.95\n",
      "1      20260209  000002.SZ      5.29        4.33\n",
      "2      20260209  000004.SZ     10.26        9.28\n",
      "3      20260209  000006.SZ      9.88        8.08\n",
      "4      20260209  000007.SZ     13.00       10.64\n",
      "...         ...        ...       ...         ...\n",
      "7462   20260209  920978.BJ     42.45       22.87\n",
      "7463   20260209  920981.BJ     41.40       22.30\n",
      "7464   20260209  920982.BJ    291.70      157.08\n",
      "7465   20260209  920985.BJ     11.32        6.10\n",
      "7466   20260209  920992.BJ     22.13       11.93\n",
      "\n",
      "[7467 rows x 4 columns]]\n"
     ]
    }
   ],
   "source": [
    "print(all_daily_data)\n",
    "# 将所有数据合并为一个 DataFrame\n",
    "all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ad9733a1-2f42-43ee-a98c-0bf699304c21",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.674078Z",
     "start_time": "2025-04-09T14:58:09.366441Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "所有每日基础数据获取并保存完毕！\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "# 将数据保存为 HDF5 文件（table 格式）\n",
    "all_daily_data_df.to_hdf(h5_filename, key='stk_limit', mode='a', format='table', append=True, data_columns=True)\n",
    "\n",
    "print(\"所有每日基础数据获取并保存完毕！\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7e777f1f-4d54-4a74-b916-691ede6af055",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.689422Z",
     "start_time": "2025-04-09T14:58:09.686524Z"
    }
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "stock",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}