NewStock/code/data/update/update_stk_limit.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "id": "500802dc-7a20-48b7-a470-a4bae3ec534b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:41.532210Z",
     "start_time": "2025-04-09T14:57:40.584930Z"
    }
   },
   "source": [
    "import tushare as ts\n",
    "\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ],
   "outputs": [],
   "execution_count": 1
  },
  {
   "cell_type": "code",
   "id": "5a84bc9da6d54868",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:04.911924Z",
     "start_time": "2025-04-09T14:57:41.540345Z"
    }
   },
   "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)"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        ts_code trade_date\n",
      "4721  600284.SH   20250408\n",
      "4722  600285.SH   20250408\n",
      "4723  600287.SH   20250408\n",
      "4712  600272.SH   20250408\n",
      "5     000008.SZ   20250408\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 10315620 entries, 0 to 14151\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: 236.1+ MB\n",
      "None\n",
      "20250408\n",
      "20250409\n"
     ]
    }
   ],
   "execution_count": 2
  },
  {
   "cell_type": "code",
   "id": "bb3191de-27a2-4c89-a3b5-32a0d7b9496f",
   "metadata": {
    "scrolled": true,
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.342522Z",
     "start_time": "2025-04-09T14:58:05.259974Z"
    }
   },
   "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"
   ],
   "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 20250410 完成\n",
      "任务 20250409 完成\n",
      "任务 20250411 完成\n"
     ]
    }
   ],
   "execution_count": 3
  },
  {
   "cell_type": "code",
   "id": "96a81aa5890ea3c3",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.353560Z",
     "start_time": "2025-04-09T14:58:09.346528Z"
    }
   },
   "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)"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[     trade_date    ts_code  up_limit  down_limit\n",
      "0      20250409  000001.SZ     11.90        9.74\n",
      "1      20250409  000002.SZ      7.48        6.12\n",
      "2      20250409  000004.SZ      9.53        7.79\n",
      "3      20250409  000006.SZ      6.28        5.14\n",
      "4      20250409  000007.SZ      5.91        4.83\n",
      "...         ...        ...       ...         ...\n",
      "7077   20250409  920108.BJ     26.55       14.31\n",
      "7078   20250409  920111.BJ     30.84       16.62\n",
      "7079   20250409  920116.BJ    100.29       54.01\n",
      "7080   20250409  920118.BJ     31.62       17.04\n",
      "7081   20250409  920128.BJ     35.26       19.00\n",
      "\n",
      "[7082 rows x 4 columns]]\n"
     ]
    }
   ],
   "execution_count": 4
  },
  {
   "cell_type": "code",
   "id": "ad9733a1-2f42-43ee-a98c-0bf699304c21",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.674078Z",
     "start_time": "2025-04-09T14:58:09.366441Z"
    }
   },
   "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！\")"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "所有每日基础数据获取并保存完毕！\n"
     ]
    }
   ],
   "execution_count": 5
  },
  {
   "cell_type": "code",
   "id": "7e777f1f-4d54-4a74-b916-691ede6af055",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:09.689422Z",
     "start_time": "2025-04-09T14:58:09.686524Z"
    }
   },
   "source": [],
   "outputs": [],
   "execution_count": null
  }
 ],
 "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
}