287 lines
10 KiB
Plaintext
287 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: 9413748 entries, 0 to 25875\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: 215.5+ MB\n",
|
||
"None\n",
|
||
"20260206\n",
|
||
"start_date: 20260209\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='20260310')\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 20260310 完成\n",
|
||
"任务 20260309 完成\n",
|
||
"任务 20260306 完成\n",
|
||
"任务 20260305 完成\n",
|
||
"任务 20260304 完成\n",
|
||
"任务 20260303 完成\n",
|
||
"任务 20260302 完成\n",
|
||
"任务 20260227 完成\n",
|
||
"任务 20260226 完成\n",
|
||
"任务 20260225 完成\n",
|
||
"任务 20260224 完成\n",
|
||
"任务 20260213 完成\n",
|
||
"任务 20260212 完成\n",
|
||
"任务 20260211 完成\n",
|
||
"任务 20260210 完成\n",
|
||
"任务 20260209 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 300587.SZ 20260213 154110 9661.44 160598 \n",
|
||
"1 601000.SH 20260213 150959 6301.54 197344 \n",
|
||
"2 002338.SZ 20260213 9215 5012.78 8260 \n",
|
||
"3 688373.SH 20260213 29166 1845.78 30329 \n",
|
||
"4 002226.SZ 20260213 101435 6137.98 79302 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"25887 603713.SH 20260209 9898 6481.74 10208 \n",
|
||
"25888 300004.SZ 20260209 41923 5934.14 50255 \n",
|
||
"25889 300975.SZ 20260209 198244 30367.70 159191 \n",
|
||
"25890 603381.SH 20260209 85934 22581.16 95505 \n",
|
||
"25891 002836.SZ 20260209 27160 4238.25 22047 \n",
|
||
"\n",
|
||
" sell_sm_amount buy_md_vol buy_md_amount sell_md_vol sell_md_amount \\\n",
|
||
"0 10061.76 183752 11498.51 186971 11701.15 \n",
|
||
"1 8233.85 84549 3527.41 71932 3003.18 \n",
|
||
"2 4495.09 9488 5163.47 9035 4920.33 \n",
|
||
"3 1918.49 10043 635.49 10005 633.64 \n",
|
||
"4 4796.49 104000 6296.98 78239 4741.21 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"25887 6683.01 6735 4413.49 7402 4854.70 \n",
|
||
"25888 7133.88 53004 7510.03 58384 8274.31 \n",
|
||
"25889 24423.94 164520 25222.01 193044 29612.42 \n",
|
||
"25890 25109.67 65977 17316.88 71008 18669.88 \n",
|
||
"25891 3438.16 21123 3293.94 20955 3271.07 \n",
|
||
"\n",
|
||
" buy_lg_vol buy_lg_amount sell_lg_vol sell_lg_amount buy_elg_vol \\\n",
|
||
"0 139274 8711.00 168037 10519.91 60907 \n",
|
||
"1 57471 2398.28 37552 1567.23 21177 \n",
|
||
"2 5873 3195.64 5312 2890.59 514 \n",
|
||
"3 8238 521.88 7113 451.02 0 \n",
|
||
"4 50394 3048.72 69021 4177.39 9335 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"25887 3515 2307.87 4056 2660.17 2867 \n",
|
||
"25888 49767 7060.10 39566 5596.12 8820 \n",
|
||
"25889 116306 17856.14 144536 22152.02 51550 \n",
|
||
"25890 46270 12156.66 38176 10028.63 11944 \n",
|
||
"25891 9676 1508.43 11383 1772.18 1000 \n",
|
||
"\n",
|
||
" buy_elg_amount sell_elg_vol sell_elg_amount net_mf_vol \\\n",
|
||
"0 3816.45 22437 1404.58 142435 \n",
|
||
"1 882.70 7328 305.66 -48700 \n",
|
||
"2 280.52 2483 1346.40 -483 \n",
|
||
"3 0.00 0 0.00 982 \n",
|
||
"4 565.27 38602 2333.86 -103058 \n",
|
||
"... ... ... ... ... \n",
|
||
"25887 1885.53 1349 890.75 1237 \n",
|
||
"25888 1251.47 5309 751.42 8180 \n",
|
||
"25889 7924.73 33850 5182.21 -41375 \n",
|
||
"25890 3157.32 5436 1403.84 -11696 \n",
|
||
"25891 155.40 4574 714.61 1257 \n",
|
||
"\n",
|
||
" net_mf_amount \n",
|
||
"0 8918.59 \n",
|
||
"1 -2025.73 \n",
|
||
"2 -250.58 \n",
|
||
"3 64.60 \n",
|
||
"4 -6231.26 \n",
|
||
"... ... \n",
|
||
"25887 814.61 \n",
|
||
"25888 1173.63 \n",
|
||
"25889 -6267.77 \n",
|
||
"25890 -3055.51 \n",
|
||
"25891 191.86 \n",
|
||
"\n",
|
||
"[25892 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
|
||
}
|