pandas表数据处理

最新推荐文章于 2024-11-14 08:53:59 发布

南城梦

最新推荐文章于 2024-11-14 08:53:59 发布

阅读量64

点赞数

文章标签： python Powered by 金山文档

本文链接：https://blog.csdn.net/qq_41717536/article/details/128838716

版权

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {
        "id":[1001,1002,1003,1004,1005,1006],
        "date":pd.date_range('20130102', periods=6),
        "city":['Beijing ', 'SH', ' guangzhou ', 'Shenzhen', 'shanghai', 'BEIJING '],
        "age":[23,44,54,32,34,32],
        "category":['100-A','100-B','110-A','110-C','210-A','130-F'],
        "price":[1200,np.nan,2133,5433,np.nan,4432]
    },
  columns =['id','date','city','category','age','price'])

df1=pd.DataFrame({"id":[1001,1002,1003,1004,1005,1006,1007,1008],
"gender":['male','female','male','female','male','female','male','female'],
"pay":['Y','N','Y','Y','N','Y','N','Y',],
"m-point":[10,12,20,40,40,40,30,20]})
print(df1)

#数据表合并
df_inner = pd.merge(df,df1,how='inner')
df_left = pd.merge(df,df1,how='left')
df_right = pd.merge(df,df1,how='right')
df_outer = pd.merge(df,df1,how='outer')
print('*************')
print(df_inner,end='\n')
print('*************')
print(df_left,end='\n')
print('*************')
print(df_right,end='\n')
print('*************')
print(df_outer,end='\n')

#append
result = df.append(df1)
print('输出追加的表数据（两张表的数据直接拼接在一起，缺失值为NaN）')
print(result)