Pandas玩转数据（四) -- DataFrame的merge

import pandas as pd
import numpy as np
from pandas import Series, DataFrame

df1 = DataFrame({'key':['X','Y','Z'], 'data_set_1':[1,2,3]})

df1
Out[5]: 
   data_set_1 key
0           1   X
1           2   Y
2           3   Z

df2 = DataFrame({'key':['A','B','C'], 'data_set_2':[4,5,6]})
df2
Out[7]: 
   data_set_2 key
0           4   A
1           5   B
2           6   C

# 没有相同的列值    
pd.merge(df1,df2)
Out[8]: 
Empty DataFrame
Columns: [data_set_1, key, data_set_2]
Index: []

# 默认合并
df2 = DataFrame({'key':['X','B','C'], 'data_set_2':[4,5,6]})

pd.merge(df1,df2)
Out[10]: 
   data_set_1 key  data_set_2
0           1   X           4

df1 = DataFrame({'key':['X','Y','Z','X'], 'data_set_1':[1,2,3,4]})
pd.merge(df1,df2)
Out[12]: 
   data_set_1 key  data_set_2
0           1   X           4
1           4   X           4

# on为指定列，默认情况下会自动找到相同名列,若指定了不同名列会保错，有两列以上相同的需要指定on
pd.merge(df1,df2,on='key')
Out[13]: 
   data_set_1 key  data_set_2
0           1   X           4
1           4   X           4

# 连接的方式,how=inner(默认),left,right,outer
pd.merge(df1,df2,on='key',how='inner')
Out[15]: 
   data_set_1 key  data_set_2
0           1   X           4
1           4   X           4

pd.merge(df1,df2,on='key',how='left')
Out[16]: 
   data_set_1 key  data_set_2
0           1   X         4.0
1           2   Y         NaN
2           3   Z         NaN
3           4   X         4.0

pd.merge(df1,df2,on='key',how='right')
Out[17]: 
   data_set_1 key  data_set_2
0         1.0   X           4
1         4.0   X           4
2         NaN   B           5
3         NaN   C           6

pd.merge(df1,df2,on='key',how='outer')
Out[18]: 
   data_set_1 key  data_set_2
0         1.0   X         4.0
1         4.0   X         4.0
2         2.0   Y         NaN
3         3.0   Z         NaN
4         NaN   B         5.0
5         NaN   C         6.0