Pandas 连接合并函数merge()详解

DataFrame1.merge(DataFrame2, how=‘inner', on=None, left_on=None, right_on=None, left_index=False, right_index=False, sort=False, suffixes=('_x', ‘_y'))

#利用字典dict创建数据框
dataDf1=pd.DataFrame({'lkey':['foo','bar','baz','foo'],
      'value':[1,2,3,4]})
dataDf2=pd.DataFrame({'rkey':['foo','bar','qux','bar'],
      'value':[5,6,7,8]})
print(dataDf1)
print(dataDf2)
>>>
 lkey value
0 foo  1
1 bar  2
2 baz  3
3 foo  4

 rkey value
0 foo  5
1 bar  6
2 qux  7
3 bar  8

#inner链接
dataLfDf=dataDf1.merge(dataDf2, left_on='lkey',right_on='rkey')
>>>
 lkey value_x rkey value_y
0 foo  1 foo  5
1 foo  4 foo  5
2 bar  2 bar  6
3 bar  2 bar  8

#Right链接
dataDf1.merge(dataDf2, left_on='lkey', right_on='rkey',how='right')
>>>
 lkey value_x rkey value_y
0 foo  1.0 foo  5
1 foo  4.0 foo  5
2 bar  2.0 bar  6
3 bar  2.0 bar  8
4 NaN  NaN qux  7

#Outer链接
dataDf1.merge(dataDf2, left_on='lkey', right_on='rkey', how='outer')
>>>
 lkey value_x rkey value_y
0 foo  1.0 foo  5.0
1 foo  4.0 foo  5.0
2 bar  2.0 bar  6.0
3 bar  2.0 bar  8.0
4 baz  3.0 NaN  NaN
5 NaN  NaN qux  7.0