【数据分析可视化】 DataFrame的merge操作

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

# 通过字典，创建两个DataFrame
df1 = DataFrame({'data1':[1,2,3,4],'key':['a','b','c','a']})
df1

	data1	key
0	1	a
1	2	b
2	3	c
3	4	a

df2 = DataFrame({'data2':[4,5,6],'key':['a','e','d']})
df2

	data2	key
0	4	a
1	5	e
2	6	d

# 前提两个数框（必须有相同的列名-key相同的情况）
pd.merge(df1,df2) 

	data1	key	data2
0	1	a	4
1	4	a	4

# merge参数on (两组数据靠哪一列merge)
pd.merge(df1,df2, on='key')

	data1	key	data2
0	1	a	4
1	4	a	4

# merge参数on 
pd.merge(df1,df2, on=None)

	data1	key	data2
0	1	a	4
1	4	a	4

# 参数how（如何去merge） how='inner' 共有
pd.merge(df1,df2, on='key', how='inner')

	data1	key	data2
0	1	a	4
1	4	a	4

# 左边为准
pd.merge(df1,df2, on='key', how='left')

	data1	key	data2
0	1	a	4.0
1	2	b	NaN
2	3	c	NaN
3	4	a	4.0

# 右边为准
pd.merge(df1,df2, on='key', how='right')

	data1	key	data2
0	1.0	a	4
1	4.0	a	4
2	NaN	e	5
3	NaN	d	6

# 左右边为准
pd.merge(df1,df2, on='key', how='outer')

	data1	key	data2
0	1.0	a	4.0
1	4.0	a	4.0
2	2.0	b	NaN
3	3.0	c	NaN
4	NaN	e	5.0
5	NaN	d	6.0