pandas中merge的用法

pandas中的merge和concat类似,但主要是用于两组有key column的数据,统一索引的数据. 通常也被用在Database的处理当中。

依据一组key合并：

import pandas as pd

#定义资料集并打印出
left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
                             'A': ['A0', 'A1', 'A2', 'A3'],
                             'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
                              'C': ['C0', 'C1', 'C2', 'C3'],
                              'D': ['D0', 'D1', 'D2', 'D3']})

print(left)
#    A   B key
# 0  A0  B0  K0
# 1  A1  B1  K1
# 2  A2  B2  K2
# 3  A3  B3  K3

print(right)
#    C   D key
# 0  C0  D0  K0
# 1  C1  D1  K1
# 2  C2  D2  K2
# 3  C3  D3  K3

#依据key column合并，并打印出
res = pd.merge(left, right, on='key')

print(res)
     A   B key   C   D
# 0  A0  B0  K0  C0  D0
# 1  A1  B1  K1  C1  D1
# 2  A2  B2  K2  C2  D2
# 3  A3  B3  K3  C3  D3

依据两组key合并：

合并时有4种方法how = ['left', 'right', 'outer', 'inner']，默认值how='inner'

import pandas as pd

#定义资料集并打印出
left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
                      'key2': ['K0', 'K1', 'K0', 'K1'],
                      'A': ['A0', 'A1', 'A2', 'A3'],
                      'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
                       'key2': ['K0', 'K0', 'K0', 'K0'],
                       'C': ['C0', 'C1', 'C2', 'C3'],
                       'D': ['D0', 'D1', 'D2', 'D3']})

print(left)
#    A   B key1 key2
# 0  A0  B0   K0   K0
# 1  A1  B1   K0   K1
# 2  A2  B2   K1   K0
# 3  A3  B3   K2   K1

print(right)
#    C   D key1 key2
# 0  C0  D0   K0   K0
# 1  C1  D1   K1   K0
# 2  C2  D2   K1   K0
# 3  C3  D3   K2   K0

#依据key1与key2 columns进行合并，并打印出四种结果['left', 'right', 'outer', 'inner']
res = pd.merge(left, right, on=['key1', 'key2'], how='inner')
print(res)
#    A   B key1 key2   C   D
# 0  A0  B0   K0   K0  C0  D0
# 1  A2  B2   K1   K0  C1  D1
# 2  A2  B2   K1   K0  C2  D2

res = pd.merge(left, right, on=['key1', 'key2'], how='outer')
print(res)
#     A    B key1 key2    C    D
# 0   A0   B0   K0   K0   C0   D0
# 1   A1   B1   K0   K1  NaN  NaN
# 2   A2   B2   K1   K0   C1   D1
# 3   A2   B2   K1   K0   C2   D2
# 4   A3   B3   K2   K1  NaN  NaN
# 5  NaN  NaN   K2   K0   C3   D3

res = pd.merge(left, right, on=['key1', 'key2'], how='left')
print(res)
#    A   B key1 key2    C    D
# 0  A0  B0   K0   K0   C0   D0
# 1  A1  B1   K0   K1  NaN  NaN
# 2  A2  B2   K1   K0   C1   D1
# 3  A2  B2   K1   K0   C2   D2
# 4  A3  B3   K2   K1  NaN  NaN

res = pd.merge(left, right, on=['key1', 'key2'], how='right')
print(res)
#     A    B key1 key2   C   D
# 0   A0   B0   K0   K0  C0  D0
# 1   A2   B2   K1   K0  C1  D1
# 2   A2   B2   K1   K0  C2  D2
# 3  NaN  NaN   K2   K0  C3  D3