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",
      "4872  600206.SH   20250926\n",
      "4873  600207.SH   20250926\n",
      "4874  600208.SH   20250926\n",
      "4876  600211.SH   20250926\n",
      "7280  920037.BJ   20250926\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 11170571 entries, 0 to 36462\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: 255.7+ MB\n",
      "None\n",
      "20250926\n",
      "20250929\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='20251020')\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 20251020 完成\n",
      "任务 20251017 完成\n",
      "任务 20251015 完成\n",
      "任务 20251016 完成\n",
      "任务 20251013 完成\n",
      "任务 20251014 完成\n",
      "任务 20251010 完成\n",
      "任务 20251009 完成\n",
      "任务 20250929 完成\n",
      "任务 20250930 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      20251010  000001.SZ     12.54       10.26\n",
      "1      20251010  000002.SZ      7.47        6.11\n",
      "2      20251010  000004.SZ     12.26       11.10\n",
      "3      20251010  000006.SZ     11.94        9.77\n",
      "4      20251010  000007.SZ      8.12        6.64\n",
      "...         ...        ...       ...         ...\n",
      "7309   20251010  920978.BJ     50.08       26.98\n",
      "7310   20251010  920981.BJ     48.04       25.88\n",
      "7311   20251010  920982.BJ    354.64      190.96\n",
      "7312   20251010  920985.BJ     11.86        6.40\n",
      "7313   20251010  920992.BJ     27.87       15.01\n",
      "\n",
      "[7314 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20251009  000001.SZ     12.47       10.21\n",
      "1      20251009  000002.SZ      7.58        6.20\n",
      "2      20251009  000004.SZ     11.68       10.56\n",
      "3      20251009  000006.SZ     11.32        9.26\n",
      "4      20251009  000007.SZ      8.02        6.56\n",
      "...         ...        ...       ...         ...\n",
      "7306   20251009  920978.BJ     50.44       27.16\n",
      "7307   20251009  920981.BJ     48.11       25.91\n",
      "7308   20251009  920982.BJ    366.06      197.12\n",
      "7309   20251009  920985.BJ     12.01        6.47\n",
      "7310   20251009  920992.BJ     27.39       14.75\n",
      "\n",
      "[7311 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20250929  000001.SZ     12.54       10.26\n",
      "1      20250929  000002.SZ      7.48        6.12\n",
      "2      20250929  000004.SZ     11.00        9.96\n",
      "3      20250929  000006.SZ     10.46        8.56\n",
      "4      20250929  000007.SZ      7.63        6.25\n",
      "...         ...        ...       ...         ...\n",
      "7302   20250929  920445.BJ     14.37        7.75\n",
      "7303   20250929  920489.BJ     29.34       15.80\n",
      "7304   20250929  920682.BJ     13.10        7.06\n",
      "7305   20250929  920799.BJ     70.78       38.12\n",
      "7306   20250929  920819.BJ      5.52        2.98\n",
      "\n",
      "[7307 rows x 4 columns],      trade_date    ts_code  up_limit  down_limit\n",
      "0      20250930  000001.SZ     12.51       10.23\n",
      "1      20250930  000002.SZ      7.49        6.13\n",
      "2      20250930  000004.SZ     11.12       10.06\n",
      "3      20250930  000006.SZ     10.29        8.42\n",
      "4      20250930  000007.SZ      7.92        6.48\n",
      "...         ...        ...       ...         ...\n",
      "7305   20250930  920445.BJ     14.67        7.91\n",
      "7306   20250930  920489.BJ     29.26       15.76\n",
      "7307   20250930  920682.BJ     12.92        6.96\n",
      "7308   20250930  920799.BJ     73.19       39.41\n",
      "7309   20250930  920819.BJ      5.55        2.99\n",
      "\n",
      "[7310 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
}