281 lines
10 KiB
Plaintext
281 lines
10 KiB
Plaintext
{
|
||
"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: 8964780 entries, 0 to 25739\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: 205.2+ MB\n",
|
||
"None\n",
|
||
"20250926\n",
|
||
"start_date: 20250929\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='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(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 20251020 完成\n",
|
||
"任务 20251017 完成\n",
|
||
"任务 20251016 完成\n",
|
||
"任务 20251015 完成\n",
|
||
"任务 20251014 完成\n",
|
||
"任务 20251013 完成\n",
|
||
"任务 20251009 完成\n",
|
||
"任务 20251010 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",
|
||
" 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 603290.SH 20251009 45532 52028.67 42778 \n",
|
||
"1 600936.SH 20251009 42537 1545.21 42382 \n",
|
||
"2 300429.SZ 20251009 81914 11768.07 64063 \n",
|
||
"3 300879.SZ 20251009 15330 5366.90 11651 \n",
|
||
"4 300031.SZ 20251009 51381 12650.70 43869 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"20574 688083.SH 20250930 13247 10094.95 11236 \n",
|
||
"20575 002939.SZ 20250930 372609 43083.12 232240 \n",
|
||
"20576 688303.SH 20250930 62478 18094.19 55086 \n",
|
||
"20577 300146.SZ 20250930 50078 5792.85 35214 \n",
|
||
"20578 688351.SH 20250930 15096 3333.84 14017 \n",
|
||
"\n",
|
||
" sell_sm_amount buy_md_vol buy_md_amount sell_md_vol sell_md_amount \\\n",
|
||
"0 48942.98 53824 61495.85 54076 61851.39 \n",
|
||
"1 1538.97 24175 878.06 31948 1160.07 \n",
|
||
"2 9211.49 88583 12730.36 88244 12682.05 \n",
|
||
"3 4089.33 15591 5464.12 17057 5976.94 \n",
|
||
"4 10822.65 56173 13836.60 49423 12190.63 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"20574 8561.02 10482 7994.12 9858 7514.37 \n",
|
||
"20575 26867.01 279904 32371.96 324997 37595.57 \n",
|
||
"20576 15952.67 55867 16177.83 53776 15573.61 \n",
|
||
"20577 4076.10 46159 5337.00 39420 4560.91 \n",
|
||
"20578 3095.89 6482 1430.69 6675 1474.59 \n",
|
||
"\n",
|
||
" buy_lg_vol buy_lg_amount sell_lg_vol sell_lg_amount buy_elg_vol \\\n",
|
||
"0 36150 41253.53 36789 41932.43 10514 \n",
|
||
"1 11158 405.04 9212 334.60 5672 \n",
|
||
"2 64282 9239.06 72904 10475.38 8221 \n",
|
||
"3 10167 3562.24 12327 4313.59 3221 \n",
|
||
"4 40306 9938.01 41035 10103.23 6112 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"20574 6674 5082.80 8224 6273.43 3329 \n",
|
||
"20575 204229 23631.31 285167 32986.98 132696 \n",
|
||
"20576 33304 9638.04 34809 10074.64 5032 \n",
|
||
"20577 47161 5454.07 36321 4202.88 8662 \n",
|
||
"20578 2513 555.48 3398 749.54 0 \n",
|
||
"\n",
|
||
" buy_elg_amount sell_elg_vol sell_elg_amount net_mf_vol \\\n",
|
||
"0 12073.88 12377 14125.13 20027 \n",
|
||
"1 205.33 0 0.00 -21182 \n",
|
||
"2 1183.11 17790 2551.67 -840 \n",
|
||
"3 1133.90 3275 1147.29 -4996 \n",
|
||
"4 1507.28 19645 4816.08 1531 \n",
|
||
"... ... ... ... ... \n",
|
||
"20574 2538.01 4413 3361.05 7612 \n",
|
||
"20575 15366.29 147033 17003.12 84949 \n",
|
||
"20576 1459.24 13010 3768.39 15188 \n",
|
||
"20577 1000.95 41105 4744.98 -16754 \n",
|
||
"20578 0.00 0 0.00 3406 \n",
|
||
"\n",
|
||
" net_mf_amount \n",
|
||
"0 22734.35 \n",
|
||
"1 -766.75 \n",
|
||
"2 -90.83 \n",
|
||
"3 -1741.72 \n",
|
||
"4 385.00 \n",
|
||
"... ... \n",
|
||
"20574 5816.07 \n",
|
||
"20575 9927.60 \n",
|
||
"20576 4417.72 \n",
|
||
"20577 -1928.39 \n",
|
||
"20578 752.20 \n",
|
||
"\n",
|
||
"[20579 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": "3.13.2"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|