1
0
This repository has been archived on 2025-01-12. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
stock_learning/0_材料准备/1_数据更新.ipynb
2024-12-30 22:37:50 +08:00

124 lines
3.6 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"cells": [
{
"cell_type": "code",
"id": "initial_id",
"metadata": {
"collapsed": true,
"ExecuteTime": {
"end_time": "2024-12-27T08:11:08.133652Z",
"start_time": "2024-12-27T08:11:08.099503Z"
}
},
"source": [
"import pymysql\n",
"\n",
"# db = pymysql.connect(host=\"frp-air.top\", port=43458, user=\"stock\", password=\"c&J#USr9~J5hrUiP\", database=\"stock\")\n",
"db = pymysql.connect(host=\"localhost\", port=3307, user=\"test\", password=\"test\", database=\"main\")"
],
"outputs": [],
"execution_count": 1
},
{
"cell_type": "code",
"id": "7fdf7baf7e494f5d",
"metadata": {
"ExecuteTime": {
"end_time": "2024-12-27T08:11:43.530387Z",
"start_time": "2024-12-27T08:11:43.527288Z"
}
},
"source": "cursor = db.cursor()",
"outputs": [],
"execution_count": 3
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2024-12-27T08:29:21.672366Z",
"start_time": "2024-12-27T08:29:13.248490Z"
}
},
"cell_type": "code",
"source": [
"import pandas as pd\n",
"\n",
"df = pd.read_csv('../document/Tushare股票信息.csv',\n",
" names=['ts_code', 'symbol', 'name', 'area', 'industry', 'fullname', 'enname', 'cnspell', 'market',\n",
" 'exchange', 'curr_type', 'list_status', 'list_date', 'act_name', 'act_ent_type'])\n",
"# ts_code列按英文句号分割将分割后的两个字符串交换位置\n",
"df['ts_code'] = df['ts_code'].str.split('.').str[::-1].str.join('.')\n",
"# 只留下ts_code、name、marketfullname列\n",
"df = df[['ts_code', 'name', 'market', 'fullname']]\n",
"# 遍历所有行生成插入sql语句\n",
"for i in range(len(df)):\n",
" sql = \"insert into target(code, name, description, market, type) values ('%s','%s','%s','%s','%s') on duplicate key update name = values(name), description = values(description), market = values(market), type = values(type)\" % (\n",
" df.iloc[i]['ts_code'], df.iloc[i]['name'], df.iloc[i]['fullname'], df.iloc[i]['market'], 'stock'\n",
" )\n",
" cursor.execute(sql)\n",
"db.commit()"
],
"id": "bff56fafd1219dfa",
"outputs": [],
"execution_count": 24
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2024-12-27T08:29:45.830427Z",
"start_time": "2024-12-27T08:29:44.310167Z"
}
},
"cell_type": "code",
"source": [
"df = pd.read_csv('../document/ETF信息.csv', usecols=[0, 1, 2], names=['index', 'code', 'name'], index_col='index')\n",
"for i in range(len(df)):\n",
" sql = \"insert into target(code, name, type) values ('%s','%s','%s') on duplicate key update name = values(name), type = values(type)\" % (\n",
" df.iloc[i]['code'], df.iloc[i]['name'], 'etf'\n",
" )\n",
" cursor.execute(sql)\n",
"db.commit()"
],
"id": "577d97871a0acbe7",
"outputs": [],
"execution_count": 25
},
{
"cell_type": "code",
"id": "9cc56d42dac5ea9",
"metadata": {
"ExecuteTime": {
"end_time": "2024-12-27T08:49:40.805003Z",
"start_time": "2024-12-27T08:49:40.762113Z"
}
},
"source": [
"db.close()"
],
"outputs": [],
"execution_count": 26
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}