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

2.15

Browse Source
This commit is contained in:
liaozhaorun
2025-02-15 23:33:34 +08:00
parent 18d0876d86
commit 49fa31ac63
13 changed files with 2028 additions and 2580 deletions
Download Patch File Download Diff File Expand all files Collapse all files

119
code/data/update/update_money_flow.ipynb
View File

@@ -2,6 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "b94bb1f2-5332-485e-ae1b-eea01f938106",
"metadata": {
"ExecuteTime": {
@@ -9,43 +10,24 @@
"start_time": "2025-02-11T15:21:54.050569Z"
}
},
"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"
}
},
"cell_type": "code",
"source": [
"import pandas as pd\n",
"import time\n",
"\n",
"h5_filename = '../../../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='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(f'start_date: {start_date}')"
],
"id": "742c29d453b9bb38",
"outputs": [
{
"name": "stdout",
@@ -66,18 +48,52 @@
]
}
],
"execution_count": 6
"source": [
"import pandas as pd\n",
"import time\n",
"\n",
"h5_filename = '../../../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='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(f'start_date: {start_date}')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "679ce40e-8d62-4887-970c-e1d8cbdeee6b",
"metadata": {
"scrolled": true,
"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"
]
}
],
"source": [
"from concurrent.futures import ThreadPoolExecutor, as_completed\n",
"\n",
@@ -107,40 +123,26 @@
" 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 20250219 完成\n",
"任务 20250220 完成\n",
"任务 20250218 完成\n",
"任务 20250217 完成\n",
"任务 20250214 完成\n",
"任务 20250213 完成\n",
"任务 20250212 完成\n",
"任务 20250211 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"
}
},
"cell_type": "code",
"source": "all_daily_data_df = pd.concat(all_daily_data, ignore_index=True)\n",
"id": "9af80516849d4e80",
"outputs": [],
"execution_count": 4
"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": {
@@ -148,15 +150,6 @@
"start_time": "2025-02-11T15:22:19.145561Z"
}
},
"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",
@@ -166,7 +159,15 @@
]
}
],
"execution_count": 5
"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！\")"
]
}
],
"metadata": {