NewStock/main/data/update/update_money_flow.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b94bb1f2-5332-485e-ae1b-eea01f938106",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:40.184418Z",
     "start_time": "2025-04-09T14:57:39.137312Z"
    }
   },
   "outputs": [],
   "source": [
    "import tushare as ts\n",
    "\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "742c29d453b9bb38",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:10.515830Z",
     "start_time": "2025-04-09T14:57:40.190466Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 9336127 entries, 0 to 25845\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: 213.7+ MB\n",
      "None\n",
      "20260116\n",
      "start_date: 20260119\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "h5_filename = '/mnt/d/PyProject/NewStock/data/money_flow.h5'\n",
    "key = '/money_flow'\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.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='20260201')\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(f'start_date: {start_date}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "679ce40e-8d62-4887-970c-e1d8cbdeee6b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:17.197319Z",
     "start_time": "2025-04-09T14:58:10.724923Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "任务 20260129 完成\n",
      "任务 20260130 完成\n",
      "任务 20260128 完成\n",
      "任务 20260127 完成\n",
      "任务 20260126 完成\n",
      "任务 20260123 完成\n",
      "任务 20260122 完成\n",
      "任务 20260121 完成\n",
      "任务 20260120 完成\n",
      "任务 20260119 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",
    "    money_flow_data = pro.moneyflow(trade_date=trade_date)\n",
    "    if money_flow_data is not None and not money_flow_data.empty:\n",
    "        return money_flow_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",
    "            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": "9af80516849d4e80",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:17.214168Z",
     "start_time": "2025-04-09T14:58:17.210734Z"
    }
   },
   "outputs": [],
   "source": [
    "all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a2b05187-437f-4053-bc43-bd80d4cf8b0e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:19.633456Z",
     "start_time": "2025-04-09T14:58:17.229837Z"
    }
   },
   "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",
    "# 将所有数据合并为一个 DataFrame\n",
    "\n",
    "# 将数据保存为 HDF5 文件（table 格式）\n",
    "all_daily_data_df.to_hdf(h5_filename, key='money_flow', 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": 6,
   "id": "e6f2a2fe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "         ts_code trade_date  buy_sm_vol  buy_sm_amount  sell_sm_vol  \\\n",
      "0      300284.SZ   20260123       57213        4682.01        45561   \n",
      "1      002835.SZ   20260123       10930        1886.39         9809   \n",
      "2      603175.SH   20260123       28945       21106.65        29993   \n",
      "3      600284.SH   20260123       62561        5324.31        55101   \n",
      "4      300855.SZ   20260123       41944       15903.55        33566   \n",
      "...          ...        ...         ...            ...          ...   \n",
      "25876  600211.SH   20260119       10915        4796.09        12174   \n",
      "25877  601229.SH   20260119      225161       21704.91       267726   \n",
      "25878  003042.SZ   20260119       17500        2893.60        11703   \n",
      "25879  601155.SH   20260119       75731       11076.12        70817   \n",
      "25880  600169.SH   20260119       81734        2005.16        84188   \n",
      "\n",
      "       sell_sm_amount  buy_md_vol  buy_md_amount  sell_md_vol  sell_md_amount  \\\n",
      "0             3728.28       48486        3966.28        59366         4856.95   \n",
      "1             1693.39        6499        1121.44         6017         1038.84   \n",
      "2            21840.97       22701       16511.38        23142        16835.79   \n",
      "3             4687.48       68181        5800.70        62114         5285.81   \n",
      "4            12712.79       35383       13409.44        40111        15213.47   \n",
      "...               ...         ...            ...          ...             ...   \n",
      "25876         5348.74        9594        4215.26         8253         3626.54   \n",
      "25877        25799.99      204041       19664.19       207361        19990.67   \n",
      "25878         1933.74       11780        1946.25        14398         2379.72   \n",
      "25879        10351.64       45622        6659.41        46251         6765.59   \n",
      "25880         2063.68      129391        3172.21       137053         3360.95   \n",
      "\n",
      "       buy_lg_vol  buy_lg_amount  sell_lg_vol  sell_lg_amount  buy_elg_vol  \\\n",
      "0           39133        3201.55        32920         2693.69         6576   \n",
      "1            4067         702.11         4633          799.04          241   \n",
      "2           11291        8249.67        11377         8302.90         3400   \n",
      "3           46517        3960.29        57644         4906.75        23366   \n",
      "4           24315        9212.24        24640         9342.34         5111   \n",
      "...           ...            ...          ...             ...          ...   \n",
      "25876        5507        2419.57         5204         2286.10            2   \n",
      "25877      134694       12983.30        86737         8363.03        24453   \n",
      "25878        4038         668.49         7218         1194.87            0   \n",
      "25879       23725        3458.86        23634         3453.46        21891   \n",
      "25880       63062        1545.61        49278         1208.05         5904   \n",
      "\n",
      "       buy_elg_amount  sell_elg_vol  sell_elg_amount  net_mf_vol  \\\n",
      "0              539.18         13561          1110.11       -4914   \n",
      "1               41.60          1278           220.26        1923   \n",
      "2             2437.55          1825          1325.59        1620   \n",
      "3             1991.65         25767          2196.91       46602   \n",
      "4             1934.73          8437          3191.36      -19491   \n",
      "...               ...           ...              ...         ...   \n",
      "25876            0.88           388           170.41         -44   \n",
      "25877         2359.23         26525          2557.95      -37774   \n",
      "25878            0.00             0             0.00        6587   \n",
      "25879         3125.39         26267          3749.10       28653   \n",
      "25880          144.65          9571           234.95      -10865   \n",
      "\n",
      "       net_mf_amount  \n",
      "0            -391.89  \n",
      "1             333.04  \n",
      "2            1372.40  \n",
      "3            3982.07  \n",
      "4           -7354.89  \n",
      "...              ...  \n",
      "25876         -16.04  \n",
      "25877       -3603.98  \n",
      "25878        1092.73  \n",
      "25879        4152.29  \n",
      "25880        -256.23  \n",
      "\n",
      "[25881 rows x 20 columns]\n"
     ]
    }
   ],
   "source": [
    "print(all_daily_data_df)"
   ]
  }
 ],
 "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": "3.12.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}