python使用read_sql与to_sql读写数据库

详细说明

使用pandas读写数据库的方法（以Mysql为例）如下：

• 首先是打包一个工具函数：

  import pandas as pd
  import numpy as np
  from sqlalchemy import create_engine, text
  
  
  def get_sql_engine():
      # 数据库
      mysql_config = {
          "db": "test_db",
          "host": "127.0.0.1",
          "user": "test_user",
          "password": "test_pass",
          "port": 3306,
      }
      engine = create_engine(
          "mysql+pymysql://{}:{}@{}:{}/{}".format(mysql_config['user'], mysql_config['password'], mysql_config['host'],
                                                  mysql_config['port'], mysql_config['db']))
      return engine
  

• 读取数据库.read_sql()的方法：

  engine = get_sql_engine()
  
  # ======== 写入 ===========
  data_df = pd.DataFrame(np.random.random(size=(100, 5)))
  data_df.to_sql('test_data_df', con=engine, if_exists='replace', index=False)
  

• 读取数据库read_sql()的方法：

   data_df = pd.read_sql_query(text('select * from test_data_df'), con=engine.connect())
  

  在读取的时候容易报错，有几个要点：
  1. 首先导入from sqlalchemy import text，然后以text(sql语句)的形式传入第一个参数
  2. 在第二个参数需要使用engine.connect()

示例程序

import pandas as pd
import numpy as np
from sqlalchemy import create_engine, text


def get_sql_engine():
    # 数据库
    mysql_config = {
        "db": "test_db",
        "host": "127.0.0.1",
        "user": "test_user",
        "password": "test_pass",
        "port": 3306,
    }
    engine = create_engine(
        "mysql+pymysql://{}:{}@{}:{}/{}".format(mysql_config['user'], mysql_config['password'], mysql_config['host'],
                                                mysql_config['port'], mysql_config['db']))
    return engine


def main():
    engine = get_sql_engine()
    # ======== 写入 ===========
    data_df = pd.DataFrame(np.random.random(size=(100, 5)))
    data_df.to_sql('test_data_df', con=engine, if_exists='replace', index=False)
    # ======== 读取 ===========
    data_df = pd.read_sql_query(text('select * from test_data_df'), con=engine.connect())


if __name__ == '__main__':
    main()