python数据表的合并_merge

Ref:https://nbviewer.jupyter.org/github/pydata/pydata-book/blob/2nd-edition/ch08.ipynb
import pandas as pd
df1 = pd.DataFrame({'key': ['b', 'b', 'a', 'c', 'a', 'a', 'b'],
                    'data1': range(7)})
df2 = pd.DataFrame({'key': ['a', 'b', 'd'],
                    'data2': range(3)})
df1

 

df2

 

pd.merge(df1, df2) #不指定on则以两个DataFrame的列名交集做为连接键 ，这里指的是"key"

pd.merge(df1,df2,on = "key")

　

 

pd.merge(df1,df2,on = "key",how = "left")  #左连接

pd.merge(df1,df2,on = "key",how = "right")  #右连接

df2.columns=["key2","data2"] #df2 改名
df2
pd.merge(df1,df2,left_on="key",right_on="key2")  ##当左右两个DataFrame的列名不同，指定不同的列明进行merge

 

 

#同样可以进行左外连接，右外连接，内链接
pd.merge(df1,df2,left_on="key",right_on="key2",how = "left")
pd.merge(df1,df2,left_on="key",right_on="key2",how = "right")
pd.merge(df1,df2,left_on="key",right_on="key2",how = "inner")