252 lines
7.1 KiB
Plaintext
252 lines
7.1 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "500802dc-7a20-48b7-a470-a4bae3ec534b",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:57:41.532210Z",
|
||
"start_time": "2025-04-09T14:57:40.584930Z"
|
||
}
|
||
},
|
||
"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": "2025-04-09T14:58:04.911924Z",
|
||
"start_time": "2025-04-09T14:57:41.540345Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" ts_code trade_date\n",
|
||
"4915 600221.SH 20251120\n",
|
||
"4916 600222.SH 20251120\n",
|
||
"4917 600223.SH 20251120\n",
|
||
"4919 600227.SH 20251120\n",
|
||
"3693 301448.SZ 20251120\n",
|
||
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
"Index: 11412627 entries, 0 to 29456\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: 261.2+ MB\n",
|
||
"None\n",
|
||
"20251120\n",
|
||
"20251121\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"import time\n",
|
||
"\n",
|
||
"h5_filename = '/mnt/d/PyProject/NewStock/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='20251220')\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": "2025-04-09T14:58:09.342522Z",
|
||
"start_time": "2025-04-09T14:58:05.259974Z"
|
||
},
|
||
"scrolled": true
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"任务 20251219 完成\n",
|
||
"任务 20251218 完成\n",
|
||
"任务 20251217 完成\n",
|
||
"任务 20251216 完成\n",
|
||
"任务 20251215 完成\n",
|
||
"任务 20251212 完成\n",
|
||
"任务 20251211 完成\n",
|
||
"任务 20251210 完成\n",
|
||
"任务 20251209 完成\n",
|
||
"任务 20251208 完成\n",
|
||
"任务 20251205 完成\n",
|
||
"任务 20251204 完成\n",
|
||
"任务 20251203 完成\n",
|
||
"任务 20251202 完成\n",
|
||
"任务 20251201 完成\n",
|
||
"任务 20251128 完成\n",
|
||
"任务 20251127 完成\n",
|
||
"任务 20251126 完成\n",
|
||
"任务 20251125 完成\n",
|
||
"任务 20251124 完成\n",
|
||
"任务 20251121 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": "2025-04-09T14:58:09.353560Z",
|
||
"start_time": "2025-04-09T14:58:09.346528Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[ trade_date ts_code up_limit down_limit\n",
|
||
"0 20251121 000001.SZ 13.04 10.67\n",
|
||
"1 20251121 000002.SZ 6.82 5.58\n",
|
||
"2 20251121 000004.SZ 11.64 10.54\n",
|
||
"3 20251121 000006.SZ 12.07 9.87\n",
|
||
"4 20251121 000007.SZ 11.00 9.00\n",
|
||
"... ... ... ... ...\n",
|
||
"7363 20251121 920978.BJ 49.06 26.42\n",
|
||
"7364 20251121 920981.BJ 46.99 25.31\n",
|
||
"7365 20251121 920982.BJ 300.67 161.91\n",
|
||
"7366 20251121 920985.BJ 11.75 6.33\n",
|
||
"7367 20251121 920992.BJ 24.06 12.96\n",
|
||
"\n",
|
||
"[7368 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": "2025-04-09T14:58:09.674078Z",
|
||
"start_time": "2025-04-09T14:58:09.366441Z"
|
||
}
|
||
},
|
||
"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": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-04-09T14:58:09.689422Z",
|
||
"start_time": "2025-04-09T14:58:09.686524Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"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
|
||
}
|