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

(data leak)RollingRank-7.0，赚钱

Browse Source
This commit is contained in:
liaozhaorun
2025-04-09 22:57:01 +08:00
parent dc1e62c77c
commit 8aad47ce33
10 changed files with 3689 additions and 3701 deletions
Download Patch File Download Diff File Expand all files Collapse all files

137
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": "2025-04-06T15:34:19.686298Z",
"start_time": "2025-04-06T15:34:19.679462Z"
"end_time": "2025-04-08T13:37:11.623192Z",
"start_time": "2025-04-08T13:37:10.611486Z"
}
},
"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": "2025-04-06T15:34:29.569406Z",
"start_time": "2025-04-06T15:34:19.711970Z"
"end_time": "2025-04-08T13:37:32.754262Z",
"start_time": "2025-04-08T13:37:11.629198Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Index: 8343458 entries, 0 to 20511\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: 191.0+ MB\n",
"None\n",
"20250403\n",
"start_date: 20250407\n"
]
}
],
"source": [
"import pandas as pd\n",
"import time\n",
@@ -66,37 +45,39 @@
"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": "2025-04-06T15:34:32.842166Z",
"start_time": "2025-04-06T15:34:29.601368Z"
},
"scrolled": true
},
],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"任务 20250417 完成\n",
"任务 20250418 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 20250409 完成\n",
"任务 20250410 完成\n",
"任务 20250408 完成\n",
"任务 20250407 完成\n"
"<class 'pandas.core.frame.DataFrame'>\n",
"Index: 8348584 entries, 0 to 5125\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: 191.1+ MB\n",
"None\n",
"20250407\n",
"start_date: 20250408\n"
]
}
],
"execution_count": 2
},
{
"cell_type": "code",
"id": "679ce40e-8d62-4887-970c-e1d8cbdeee6b",
"metadata": {
"scrolled": true,
"ExecuteTime": {
"end_time": "2025-04-08T13:37:34.659267Z",
"start_time": "2025-04-08T13:37:33.094502Z"
}
},
"source": [
"from concurrent.futures import ThreadPoolExecutor, as_completed\n",
"\n",
@@ -126,33 +107,59 @@
" 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 20250417 完成\n",
"任务 20250418 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"
]
}
],
"execution_count": 3
},
{
"cell_type": "code",
"execution_count": 4,
"id": "9af80516849d4e80",
"metadata": {
"ExecuteTime": {
"end_time": "2025-04-06T15:34:32.851075Z",
"start_time": "2025-04-06T15:34:32.844866Z"
"end_time": "2025-04-08T13:37:34.678164Z",
"start_time": "2025-04-08T13:37:34.674804Z"
}
},
"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": "2025-04-06T15:34:35.261741Z",
"start_time": "2025-04-06T15:34:32.864789Z"
"end_time": "2025-04-08T13:37:37.285649Z",
"start_time": "2025-04-08T13:37:34.694595Z"
}
},
"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",
@@ -162,15 +169,7 @@
]
}
],
"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": {