pandas 连接数据库直接查表建立dataframe。loc，sort_values数据清洗操作

 

 

#导入pandas
import pandas as pd
import numpy as np

#导入SqlAlchemy
from sqlalchemy import create_engine

if __name__ == "__main__":
    #建立数据库引擎
    engine = create_engine('mysql+pymysql://root:mysql@localhost:3306/mymac')
    #写一条sql
    sql = 'select id,name,age,gender from student'
    #建立dataframe
    df = pd.read_sql_query(sql,engine)
    # print(df)
    #按照年龄倒序    正序：ascending=True
    #翻译为sql  select * from student order by asc | desc
    # df = df.sort_values(['age','gender'],ascending=False)
    # print(df)

    #取年龄最小的学生  在尾部取值
    #翻译为sql select * from student order by age limit 1
    # df = df.sort_values(['age']).tail(1)
    # print(df)
    
    #求整个班的平均年龄 
    avg_age= df.age.mean()
    #使用loc方法指定字段
    print(df.loc[(df['age']<avg_age ) & df['gender']==1])

    #获取指定字段
    # print(df.loc[df['gender']==1,['id','name']])
                                      

    #将dataframe写入数据表,表名，数据引擎，索引是否入库
    # df.to_sql('student_copy',engine,index=False)
    
    #前提要安装好 openpyxl   安装命令 pip install openpyxl
    #导入成excel文件
    # df.to_excel('student.xlsx')

    # print(Student.objects.all())

 

转载于:https://www.cnblogs.com/Niuxingyu/p/10482314.html