赞
踩
def merge(left, right, how='inner', on=None, left_on=None, right_on=None,
left_index=False, right_index=False, sort=False,
suffixes=('_x', '_y'), copy=True, indicator=False,
validate=None):
1、默认参数:以重叠的列名当作连接键
2、how=‘left’:取左边的交集
import pandas as pd
import numpy as np
df1 = pd.DataFrame({'key': ['one', 'two', 'two'],
'data1': np.arange(3)})
df2 = pd.DataFrame({'key': ['one', 'three', 'three'],
'data2': np.arange(3)})
df3 = pd.merge(df1, df2)
df4 = pd.merge(df1, df2, how='left')
print(df1)
print(df2)
print(df3)
print(df4)
key data1
0 one 0
1 two 1
2 two 2
key data2
0 one 0
1 three 1
2 three 2
key data1 data2
0 one 0 0
key data1 data2
0 one 0 0.0
1 two 1 NaN
2 two 2 NaN
3、多键连接时将连接键做成列表传入。on默认是两者同时存在的列,outer取并集
import pandas as pd
import numpy as np
df1 = pd.DataFrame({'key': ['one', 'two', 'two'],
'value': ['a', 'b', 'c'],
'data1': np.arange(3)})
df2 = pd.DataFrame({'key': ['one', 'two', 'three'],
'value': ['a', 'c', 'c'],
'data2': np.arange(3)})
df5 = pd.merge(df1, df2)
df6 = pd.merge(df1, df2, on=['key', 'value'], how='outer')
print(df1)
print(df2)
print(df5)
print(df6)
key value data1
0 one a 0
1 two b 1
2 two c 2
key value data2
0 one a 0
1 two c 1
2 three c 2
key value data1 data2
0 one a 0 0
1 two c 2 1
key value data1 data2
0 one a 0.0 0.0
1 two b 1.0 NaN
2 two c 2.0 1.0
3 three c NaN 2.0
4、两个对象的列名不同,需要分别制定
import pandas as pd
import numpy as np
df7 = pd.merge(df1, df2, left_on=['key1','data1'], right_on=['key2','data2'], how='outer')
print(df7)
key1 value_x data1 key2 value_y data2
0 one a 0.0 one a 0.0
1 two b 1.0 two c 1.0
2 two c 2.0 NaN NaN NaN
3 NaN NaN NaN three c 2.0
def join(self, other, on=None, how='left', lsuffix='', rsuffix='',
sort=False):
import pandas as pd
import numpy as np
df1 = pd.DataFrame({'A': ['A0', 'A1', 'A1'],
'B': ['B0', 'B1', 'B2']},
index=['K0', 'K1', 'K2'])
df2 = pd.DataFrame({'C': ['C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2']},
index=['K0', 'K1', 'K3'])
df3 = df1.join(df2)
df4 = df1.join(df2, how='outer')
df5 = df1.join(df2, how='inner')
print(df1)
print(df2)
print(df3)
print(df4)
print(df5)
A B
K0 A0 B0
K1 A1 B1
K2 A1 B2
C D
K0 C1 D0
K1 C2 D1
K3 C3 D2
A B C D
K0 A0 B0 C1 D0
K1 A1 B1 C2 D1
K2 A1 B2 NaN NaN
A B C D
K0 A0 B0 C1 D0
K1 A1 B1 C2 D1
K2 A1 B2 NaN NaN
K3 NaN NaN C3 D2
A B C D
K0 A0 B0 C1 D0
K1 A1 B1 C2 D1
def concat(objs, axis=0, join='outer', join_axes=None, ignore_index=False,
keys=None, levels=None, names=None, verify_integrity=False,
sort=None, copy=True):
实例1
import pandas as pd
import numpy as np
s1 = pd.Series(['a', 'b'])
s2 = pd.Series(['c', 'd'])
s3 = pd.concat([s1, s2])
s4 = pd.concat([s1, s2], ignore_index=True)
print(s1)
print(s2)
print(s3)
print(s4)
0 a
1 b
dtype: object
0 c
1 d
dtype: object
0 a
1 b
0 c
1 d
dtype: object
0 a
1 b
2 c
3 d
dtype: object
实例2
import pandas as pd
import numpy as np
df1 = pd.DataFrame([['a', 1], ['b', 2]], columns=['A', 0])
df2 = pd.DataFrame([['a', 1], ['b', 2]], columns=['B', 0])
df3 = pd.concat([df1, df2], join='inner')
print(df1)
print(df2)
print(df3)
A 0
0 a 1
1 b 2
B 0
0 a 1
1 b 2
0
0 1
1 2
0 1
1 2
实例3
import pandas as pd
import numpy as np
df1 = pd.DataFrame([['a', 1], ['b', 2]], columns=['A', 0])
df2 = pd.DataFrame([['a', 1], ['b', 2]], columns=['B', 0])
df3 = pd.concat([df1, df2], axis=1)
print(df1)
print(df2)
print(df3)
A 0
0 a 1
1 b 2
B 0
0 a 1
1 b 2
A 0 B 0
0 a 1 a 1
1 b 2 b 2
import pandas as pd
import numpy as np
df1 = pd.DataFrame({'A': ['A0', 'A1', 'A1'],
'B': ['B0', 'B1', 'B2']},
index=['K0', 'K1', 'K2'])
s2 = pd.Series(['X0','X1'], index=['A','B'])
result = df1.append(s2, ignore_index=True)
print(df1)
print(s2)
print(result)
A B
K0 A0 B0
K1 A1 B1
K2 A1 B2
A X0
B X1
dtype: object
A B
0 A0 B0
1 A1 B1
2 A1 B2
3 X0 X1
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。