246 lines
7.3 KiB
Plaintext
246 lines
7.3 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "500802dc-7a20-48b7-a470-a4bae3ec534b",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-11T15:18:36.892437Z",
|
||
"start_time": "2025-02-11T15:18:36.020822Z"
|
||
}
|
||
},
|
||
"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": "2025-02-11T15:20:12.573607Z",
|
||
"start_time": "2025-02-11T15:20:00.110127Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" ts_code trade_date\n",
|
||
"4682 600310.SH 20250211\n",
|
||
"4683 600312.SH 20250211\n",
|
||
"4684 600313.SH 20250211\n",
|
||
"4673 600299.SH 20250211\n",
|
||
"0 000001.SZ 20250211\n",
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Index: 10040878 entries, 0 to 10040877\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: 229.8+ MB\n",
|
||
"None\n",
|
||
"20250211\n",
|
||
"20250212\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import time\n",
|
||
"\n",
|
||
"h5_filename = '../../../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='20250220')\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": "2025-02-11T15:21:27.831699Z",
|
||
"start_time": "2025-02-11T15:21:26.665039Z"
|
||
},
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"任务 20250219 完成\n",
|
||
"任务 20250220 完成\n",
|
||
"任务 20250217 完成\n",
|
||
"任务 20250218 完成\n",
|
||
"任务 20250214 完成\n",
|
||
"任务 20250213 完成\n",
|
||
"任务 20250212 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": "2025-02-11T15:21:29.294283Z",
|
||
"start_time": "2025-02-11T15:21:29.247112Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[ trade_date ts_code up_limit down_limit\n",
|
||
"0 20250213 000001.SZ 12.56 10.28\n",
|
||
"1 20250213 000002.SZ 8.76 7.16\n",
|
||
"2 20250213 000004.SZ 15.40 12.60\n",
|
||
"3 20250213 000006.SZ 7.92 6.48\n",
|
||
"4 20250213 000007.SZ 7.39 6.05\n",
|
||
"... ... ... ... ...\n",
|
||
"7014 20250213 920108.BJ 27.22 14.66\n",
|
||
"7015 20250213 920111.BJ 35.98 19.38\n",
|
||
"7016 20250213 920116.BJ 80.44 43.32\n",
|
||
"7017 20250213 920118.BJ 34.46 18.56\n",
|
||
"7018 20250213 920128.BJ 39.84 21.46\n",
|
||
"\n",
|
||
"[7019 rows x 4 columns], trade_date ts_code up_limit down_limit\n",
|
||
"0 20250212 000001.SZ 12.56 10.28\n",
|
||
"1 20250212 000002.SZ 7.96 6.52\n",
|
||
"2 20250212 000004.SZ 15.07 12.33\n",
|
||
"3 20250212 000006.SZ 7.74 6.34\n",
|
||
"4 20250212 000007.SZ 7.40 6.06\n",
|
||
"... ... ... ... ...\n",
|
||
"7014 20250212 920108.BJ 27.41 14.77\n",
|
||
"7015 20250212 920111.BJ 34.51 18.59\n",
|
||
"7016 20250212 920116.BJ 79.66 42.90\n",
|
||
"7017 20250212 920118.BJ 34.81 18.75\n",
|
||
"7018 20250212 920128.BJ 38.98 21.00\n",
|
||
"\n",
|
||
"[7019 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": "2025-02-11T15:20:37.999493Z",
|
||
"start_time": "2025-02-11T15:20:37.375220Z"
|
||
}
|
||
},
|
||
"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": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"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": "3.8.19"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|