liaozhaorun/NewStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

(exception)勉强赚钱rank

Browse Source
This commit is contained in:
liaozhaorun
2025-03-31 23:08:03 +08:00
parent ee35513935
commit 01092b8cae
14 changed files with 5561 additions and 2922 deletions
Download Patch File Download Diff File Expand all files Collapse all files

148
code/data/update/update_money_flow.ipynb
View File

@@ -2,52 +2,31 @@
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "b94bb1f2-5332-485e-ae1b-eea01f938106",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-11T15:21:54.821950Z",
"start_time": "2025-02-11T15:21:54.050569Z"
"end_time": "2025-03-30T16:42:37.847407Z",
"start_time": "2025-03-30T16:42:36.773187Z"
}
},
"outputs": [],
"source": [
"import tushare as ts\n",
"\n",
"ts.set_token('3a0741c702ee7e5e5f2bf1f0846bafaafe4e320833240b2a7e4a685f')\n",
"pro = ts.pro_api()"
]
],
"outputs": [],
"execution_count": 1
},
{
"cell_type": "code",
"execution_count": 2,
"id": "742c29d453b9bb38",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-11T15:22:32.726905Z",
"start_time": "2025-02-11T15:22:25.018135Z"
"end_time": "2025-03-30T16:42:59.016187Z",
"start_time": "2025-03-30T16:42:37.850022Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Index: 8153941 entries, 0 to 5120\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: 186.6+ MB\n",
"None\n",
"20250211\n",
"start_date: 20250212\n"
]
}
],
"source": [
"import pandas as pd\n",
"import time\n",
@@ -61,39 +40,44 @@
" 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 = 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}')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "679ce40e-8d62-4887-970c-e1d8cbdeee6b",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-11T15:22:14.513527Z",
"start_time": "2025-02-11T15:22:12.973331Z"
},
"scrolled": true
},
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"任务 20250220 完成\n",
"任务 20250219 完成\n",
"任务 20250217 完成\n",
"任务 20250218 完成\n",
"任务 20250213 完成\n",
"任务 20250214 完成\n",
"任务 20250212 完成\n"
"<class 'pandas.core.frame.DataFrame'>\n",
"Index: 8297316 entries, 0 to 30724\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: 189.9+ MB\n",
"None\n",
"20250321\n",
"start_date: 20250324\n"
]
}
],
"execution_count": 2
},
{
"cell_type": "code",
"id": "679ce40e-8d62-4887-970c-e1d8cbdeee6b",
"metadata": {
"scrolled": true,
"ExecuteTime": {
"end_time": "2025-03-30T16:43:03.168764Z",
"start_time": "2025-03-30T16:42:59.422934Z"
}
},
"source": [
"from concurrent.futures import ThreadPoolExecutor, as_completed\n",
"\n",
@@ -123,33 +107,69 @@
" 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 20250418 完成\n",
"任务 20250417 完成\n",
"任务 20250415 完成\n",
"任务 20250416 完成\n",
"任务 20250414 完成\n",
"任务 20250411 完成\n",
"任务 20250410 完成\n",
"任务 20250409 完成\n",
"任务 20250408 完成\n",
"任务 20250407 完成\n",
"任务 20250403 完成\n",
"任务 20250402 完成\n",
"任务 20250401 完成\n",
"任务 20250331 完成\n",
"任务 20250328 完成\n",
"任务 20250327 完成\n",
"任务 20250326 完成\n",
"任务 20250325 完成\n",
"任务 20250324 完成\n"
]
}
],
"execution_count": 3
},
{
"cell_type": "code",
"execution_count": 4,
"id": "9af80516849d4e80",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-11T15:22:16.656650Z",
"start_time": "2025-02-11T15:22:16.639271Z"
"end_time": "2025-03-30T16:43:03.181032Z",
"start_time": "2025-03-30T16:43:03.173867Z"
}
},
"outputs": [],
"source": [
"all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n"
]
],
"outputs": [],
"execution_count": 4
},
{
"cell_type": "code",
"execution_count": 5,
"id": "a2b05187-437f-4053-bc43-bd80d4cf8b0e",
"metadata": {
"ExecuteTime": {
"end_time": "2025-02-11T15:22:20.447350Z",
"start_time": "2025-02-11T15:22:19.145561Z"
"end_time": "2025-03-30T16:43:05.401668Z",
"start_time": "2025-03-30T16:43:03.197033Z"
}
},
"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",
@@ -159,15 +179,7 @@
]
}
],
"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！\")"
]
"execution_count": 5
}
],
"metadata": {
@@ -186,7 +198,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.19"
"version": "3.11.11"
}
},
"nbformat": 4,