NewStock/code/data/update/update_stk_limit.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "500802dc-7a20-48b7-a470-a4bae3ec534b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-06T15:34:34.020485Z",
     "start_time": "2025-04-06T15:34:33.497731Z"
    }
   },
   "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": "2025-04-06T15:34:46.227924Z",
     "start_time": "2025-04-06T15:34:34.042810Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        ts_code trade_date\n",
      "4717  600285.SH   20250403\n",
      "4718  600287.SH   20250403\n",
      "4719  600288.SH   20250403\n",
      "4708  600273.SH   20250403\n",
      "5309  601121.SH   20250403\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 10301468 entries, 0 to 28272\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: 235.8+ MB\n",
      "None\n",
      "20250403\n",
      "20250407\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "h5_filename = '../../../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='20250420')\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": "2025-04-06T15:34:48.652346Z",
     "start_time": "2025-04-06T15:34:46.236695Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "任务 20250417 完成\n",
      "任务 20250418 完成\n",
      "任务 20250416 完成\n",
      "任务 20250415 完成\n",
      "任务 20250414 完成\n",
      "任务 20250411 完成\n",
      "任务 20250410 完成\n",
      "任务 20250409 完成\n",
      "任务 20250408 完成\n",
      "任务 20250407 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": "2025-04-06T15:34:48.680504Z",
     "start_time": "2025-04-06T15:34:48.665530Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[     trade_date    ts_code  up_limit  down_limit\n",
      "0      20250408  000001.SZ     11.77        9.63\n",
      "1      20250408  000002.SZ      7.26        5.94\n",
      "2      20250408  000004.SZ      9.72        7.96\n",
      "3      20250408  000006.SZ      6.90        5.64\n",
      "4      20250408  000007.SZ      6.14        5.02\n",
      "...         ...        ...       ...         ...\n",
      "7072   20250408  920108.BJ     25.33       13.65\n",
      "7073   20250408  920111.BJ     29.38       15.82\n",
      "7074   20250408  920116.BJ     96.40       51.92\n",
      "7075   20250408  920118.BJ     30.16       16.24\n",
      "7076   20250408  920128.BJ     34.15       18.39\n",
      "\n",
      "[7077 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20250407  000001.SZ     12.47       10.21\n",
      "1      20250407  000002.SZ      7.85        6.43\n",
      "2      20250407  000004.SZ     10.80        8.84\n",
      "3      20250407  000006.SZ      7.67        6.27\n",
      "4      20250407  000007.SZ      6.82        5.58\n",
      "...         ...        ...       ...         ...\n",
      "7070   20250407  920108.BJ     31.72       17.08\n",
      "7071   20250407  920111.BJ     36.85       19.85\n",
      "7072   20250407  920116.BJ    116.05       62.49\n",
      "7073   20250407  920118.BJ     38.07       20.51\n",
      "7074   20250407  920128.BJ     43.38       23.36\n",
      "\n",
      "[7075 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": "2025-04-06T15:34:48.966102Z",
     "start_time": "2025-04-06T15:34:48.693158Z"
    }
   },
   "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": "2025-04-06T15:34:48.980659Z",
     "start_time": "2025-04-06T15:34:48.977771Z"
    }
   },
   "outputs": [],
   "source": []
  }
 ],
 "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
}