第一部分,连接数据库
import pymysql
import pandas as pd
#连接mysql数据库
conn = pymysql.connect(host = "localhost",user = "root",passwd = "123456",db = "test",charset = "utf8")
sql_query = 'SELECT*FROM test.user limit 10'
data = pd.read_sql(sql_query,con=conn) #读取数据
data.info() #查看数据的描述信息
data.describe()#显示内存使用量,读取数据越多,内存使用量越大
data.isnull().sum()
conn.close() #关闭数据库链接
print(data.head()) #输出部分数据,head()函数默认读取数据前五行
输出结果如下所示
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10 entries, 0 to 9
Data columns (total 4 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 username 10 non-null object
1 last_login_time 10 non-null object
2 login_count 10 non-null object
3 addtime 10 non-null object
dtypes: object(4)
memory usa