Pandas具有全功能的，高性能内存中连接操作，与SQL等关系数据库非常相似
pd.merge(left, right, how='inner', on=None, left_on=None, right_on=None, left_index=False, right_index=False, sort=True, suffixes=('_x', '_y'), copy=True, indicator=False)
import pandas as pd
import numpy as np
# merge合并 → 类似excel的vlookup
df1 = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
df2 = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
df3 = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
'key2': ['K0', 'K1', 'K0', 'K1'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
df4 = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
'key2': ['K0', 'K0', 'K0', 'K0'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
print(pd.merge(df1, df2, on='key'))
print("1".center(40,'*'))
# left：第一个df
# right：第二个df
# on：参考键
print(pd.merge(df3, df4, on=['key1','key2']))
# 多个链接键
#执行结果
key A B C D
0 K0 A0 B0 C0 D0
1 K1 A1 B1 C1 D1
2 K2 A2 B2 C2 D2
3 K3 A3 B3 C3 D3
*******************1********************
key1 key2 A B C D
0 K0 K0 A0 B0 C0 D0
1 K1 K0 A2 B2 C1 D1
2 K1 K0 A2 B2 C2 D2
# 参数how → 合并方式
print("1".center(40,'*'))
print(pd.merge(df3, df4,on=['key1','key2'], how = 'inner'))
# inner：默认，取交集
print("2".center(40,'*'))
print(pd.merge(df3, df4, on=['key1','key2'], how = 'outer'))
# outer：取并集，数据缺失范围NaN
print("3".center(40,'*'))
print(pd.merge(df3, df4, on=['key1','key2'], how = 'left'))
# left：按照df3为参考合并，数据缺失范围NaN
print("4".center(40,'*'))
print(pd.merge(df3, df4, on=['key1','key2'], how = 'right'))
# right：按照df4为参考合并，数据缺失范围NaN
#执行结果
*******************1********************
key1 key2 A B C D
0 K0 K0 A0 B0 C0 D0
1 K1 K0 A2 B2 C1 D1
2 K1 K0 A2 B2 C2 D2
*******************2********************
key1 key2 A B C D
0 K0 K0 A0 B0 C0 D0
1 K0 K1 A1 B1 NaN NaN
2 K1 K0 A2 B2 C1 D1
3 K1 K0 A2 B2 C2 D2
4 K2 K1 A3 B3 NaN NaN
5 K2 K0 NaN NaN C3 D3
*******************3********************
key1 key2 A B C D
0 K0 K0 A0 B0 C0 D0
1 K0 K1 A1 B1 NaN NaN
2 K1 K0 A2 B2 C1 D1
3 K1 K0 A2 B2 C2 D2
4 K2 K1 A3 B3 NaN NaN
*******************4********************
key1 key2 A B C D
0 K0 K0 A0 B0 C0 D0
1 K1 K0 A2 B2 C1 D1
2 K1 K0 A2 B2 C2 D2
3 K2 K0 NaN NaN C3 D3
# 参数 left_on, right_on, left_index, right_index → 当键不为一个列时，可以单独设置左键与右键
df1 = pd.DataFrame({'lkey':list('bbacaab'),
'data1':range(7)})
df2 = pd.DataFrame({'rkey':list('abd'),
'date2':range(3)})
print(pd.merge(df1, df2, left_on='lkey', right_on='rkey'))
print('------')
# df1以‘lkey’为键，df2以‘rkey’为键
df1 = pd.DataFrame({'key':list('abcdfeg'),
'data1':range(7)})
df2 = pd.DataFrame({'date2':range(100,105)},
index = list('abcde'))
print(pd.merge(df1, df2, left_on='key', right_index=True))
# df1以‘key’为键，df2以index为键
# left_index：为True时，第一个df以index为键，默认False
# right_index：为True时，第二个df以index为键，默认False
# 所以left_on, right_on, left_index, right_index可以相互组合：
# left_on + right_on, left_on + right_index, left_index + right_on, left_index + right_index
#执行结果
lkey data1 rkey date2
0 b 0 b 1
1 b 1 b 1
2 b 6 b 1
3 a 2 a 0
4 a 4 a 0
5 a 5 a 0
------
key data1 date2
0 a 0 100
1 b 1 101
2 c 2 102
3 d 3 103
5 e 5 104
# 参数 sort
df1 = pd.DataFrame({'key':list('bbacaab'),
'data1':[1,3,2,4,5,9,7]})
df2 = pd.DataFrame({'key':list('abd'),
'date2':[11,2,33]})
x1 = pd.merge(df1,df2, on = 'key', how = 'outer')
x2 = pd.merge(df1,df2, on = 'key', sort=True, how = 'outer')
print(x1)
print(x2)
print('------')
# sort：按照字典顺序通过 连接键 对结果DataFrame进行排序。默认为False，设置为False会大幅提高性能
print(x2.sort_values('data1'))
# 也可直接用Dataframe的排序方法：sort_values，sort_index
#执行结果
key data1 date2
0 b 1.0 2.0
1 b 3.0 2.0
2 b 7.0 2.0
3 a 2.0 11.0
4 a 5.0 11.0
5 a 9.0 11.0
6 c 4.0 NaN
7 d NaN 33.0
key data1 date2
0 a 2.0 11.0
1 a 5.0 11.0
2 a 9.0 11.0
3 b 1.0 2.0
4 b 3.0 2.0
5 b 7.0 2.0
6 c 4.0 NaN
7 d NaN 33.0
------
key data1 date2
3 b 1.0 2.0
0 a 2.0 11.0
4 b 3.0 2.0
6 c 4.0 NaN
1 a 5.0 11.0
5 b 7.0 2.0
2 a 9.0 11.0
7 d NaN 33.0
# pd.join() → 直接通过索引链接
left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
'B': ['B0', 'B1', 'B2']},
index=['K0', 'K1', 'K2'])
right = pd.DataFrame({'C': ['C0', 'C2', 'C3'],
'D': ['D0', 'D2', 'D3']},
index=['K0', 'K2', 'K3'])
print(left)
print(right)
print(left.join(right))
print(left.join(right, how='outer'))
print('-----')
# 等价于：pd.merge(left, right, left_index=True, right_index=True, how='outer')
df1 = pd.DataFrame({'key':list('bbacaab'),
'data1':[1,3,2,4,5,9,7]})
df2 = pd.DataFrame({'key':list('abd'),
'date2':[11,2,33]})
print(df1)
print(df2)
print(pd.merge(df1, df2, left_index=True, right_index=True, suffixes=('_1', '_2')))
print(df1.join(df2['date2']))
print('-----')
# suffixes=('_x', '_y')默认
left = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3'],
'key': ['K0', 'K1', 'K0', 'K1']})
right = pd.DataFrame({'C': ['C0', 'C1'],
'D': ['D0', 'D1']},
index=['K0', 'K1'])
print(left)
print(right)
print(left.join(right, on = 'key'))
# 等价于pd.merge(left, right, left_on='key', right_index=True, how='left', sort=False);
# left的‘key’和right的index
# 执行结果
A B
K0 A0 B0
K1 A1 B1
K2 A2 B2
C D
K0 C0 D0
K2 C2 D2
K3 C3 D3
A B C D
K0 A0 B0 C0 D0
K1 A1 B1 NaN NaN
K2 A2 B2 C2 D2
A B C D
K0 A0 B0 C0 D0
K1 A1 B1 NaN NaN
K2 A2 B2 C2 D2
K3 NaN NaN C3 D3
-----
key data1
0 b 1
1 b 3
2 a 2
3 c 4
4 a 5
5 a 9
6 b 7
key date2
0 a 11
1 b 2
2 d 33
key_1 data1 key_2 date2
0 b 1 a 11
1 b 3 b 2
2 a 2 d 33
key data1 date2
0 b 1 11.0
1 b 3 2.0
2 a 2 33.0
3 c 4 NaN
4 a 5 NaN
5 a 9 NaN
6 b 7 NaN
-----
A B key
0 A0 B0 K0
1 A1 B1 K1
2 A2 B2 K0
3 A3 B3 K1
C D
K0 C0 D0
K1 C1 D1
A B key C D
0 A0 B0 K0 C0 D0
1 A1 B1 K1 C1 D1
2 A2 B2 K0 C0 D0
3 A3 B3 K1 C1 D1
