NewStock/main/data/update/update_money_flow.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "id": "b94bb1f2-5332-485e-ae1b-eea01f938106",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:57:40.184418Z",
     "start_time": "2025-04-09T14:57:39.137312Z"
    }
   },
   "source": [
    "import tushare as ts\n",
    "\n",
    "ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
    "pro = ts.pro_api()"
   ],
   "outputs": [],
   "execution_count": 1
  },
  {
   "cell_type": "code",
   "id": "742c29d453b9bb38",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:10.515830Z",
     "start_time": "2025-04-09T14:57:40.190466Z"
    }
   },
   "source": [
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "h5_filename = '../../../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='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(f'start_date: {start_date}')"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 8353711 entries, 0 to 5126\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: 191.2+ MB\n",
      "None\n",
      "20250408\n",
      "start_date: 20250409\n"
     ]
    }
   ],
   "execution_count": 2
  },
  {
   "cell_type": "code",
   "id": "679ce40e-8d62-4887-970c-e1d8cbdeee6b",
   "metadata": {
    "scrolled": true,
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:17.197319Z",
     "start_time": "2025-04-09T14:58:10.724923Z"
    }
   },
   "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"
   ],
   "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 20250411 完成\n",
      "任务 20250414 完成\n",
      "任务 20250410 完成\n",
      "任务 20250409 完成\n"
     ]
    }
   ],
   "execution_count": 3
  },
  {
   "cell_type": "code",
   "id": "9af80516849d4e80",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:17.214168Z",
     "start_time": "2025-04-09T14:58:17.210734Z"
    }
   },
   "source": [
    "all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n"
   ],
   "outputs": [],
   "execution_count": 4
  },
  {
   "cell_type": "code",
   "id": "a2b05187-437f-4053-bc43-bd80d4cf8b0e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:58:19.633456Z",
     "start_time": "2025-04-09T14:58:17.229837Z"
    }
   },
   "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！\")"
   ],
   "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
  }
 ],
 "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
}