404
Home Archives Tags Categories Gallery Link About
Numpy and Pandas
Word count: 3.9k|Reading time: 22 min|Post View:

Numpy

Create Numpy Array

1
2
3
4
5
6
7
8
9
10
a = np.array([2,23,4])  # list 1d
print(a)
# [2 23 4]

a = np.array([[2,23,4],[2,32,4]])  # 2d 矩阵 2行3列
print(a)
"""
[[ 2 23  4]
 [ 2 32  4]]
"""

dtype

1
2
3
4
5
6
7
8
9
10
a = np.array([2,23,4],dtype=np.int)
print(a.dtype)
# int 64

a = np.ones((3,4),dtype = np.int)   # 数据为1，3行4列
"""
array([[1, 1, 1, 1],
       [1, 1, 1, 1],
       [1, 1, 1, 1]])
"""

np.ones

1
2
3
4
5
6
a = np.zeros((3,4)) # 数据全为0，3行4列
"""
array([[ 0.,  0.,  0.,  0.],
       [ 0.,  0.,  0.,  0.],
       [ 0.,  0.,  0.,  0.]])
"""

np.empty

1
2
3
4
5
6
7
8
9
a = np.empty((3,4)) # 数据为empty，3行4列
"""
array([[  0.00000000e+000,   4.94065646e-324,   9.88131292e-324,
          1.48219694e-323],
       [  1.97626258e-323,   2.47032823e-323,   2.96439388e-323,
          3.45845952e-323],
       [  3.95252517e-323,   4.44659081e-323,   4.94065646e-323,
          5.43472210e-323]])
"""

np.arrange

1
2
3
4
a = np.arange(10,20,2) # 10-19 的数据，2步长
"""
array([10, 12, 14, 16, 18])
"""

np.reshape

1
2
3
4
5
6
a = np.arange(12).reshape((3,4))    # 3行4列，0到11
"""
array([[ 0,  1,  2,  3],
       [ 4,  5,  6,  7],
       [ 8,  9, 10, 11]])
"""

np.linspace

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
a = np.linspace(1,10,20)    # 开始端1，结束端10，且分割成20个数据，生成线段
"""
array([  1.        ,   1.47368421,   1.94736842,   2.42105263,
         2.89473684,   3.36842105,   3.84210526,   4.31578947,
         4.78947368,   5.26315789,   5.73684211,   6.21052632,
         6.68421053,   7.15789474,   7.63157895,   8.10526316,
         8.57894737,   9.05263158,   9.52631579,  10.        ])
"""

a = np.linspace(1,10,20).reshape((5,4)) # 更改shape
"""
array([[  1.        ,   1.47368421,   1.94736842,   2.42105263],
       [  2.89473684,   3.36842105,   3.84210526,   4.31578947],
       [  4.78947368,   5.26315789,   5.73684211,   6.21052632],
       [  6.68421053,   7.15789474,   7.63157895,   8.10526316],
       [  8.57894737,   9.05263158,   9.52631579,  10.        ]])
"""

Operation between numpy.array

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
import numpy as np
a=np.array([10,20,30,40])   # array([10, 20, 30, 40])
b=np.arange(4)              # array([0, 1, 2, 3])

c=a-b  # array([10, 19, 28, 37])

c=a+b   # array([10, 21, 32, 43])

c=a*b   # array([  0,  20,  60, 120])

c=b**2  # array([0, 1, 4, 9])

c=10*np.sin(a)  
# array([-5.44021111,  9.12945251, -9.88031624,  7.4511316 ])

print(b<3)  
# array([ True,  True,  True, False], dtype=bool)

matrix

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
a=np.array([[1,1],[0,1]])
b=np.arange(4).reshape((2,2))

print(a)
# array([[1, 1],
#       [0, 1]])

print(b)
# array([[0, 1],
#       [2, 3]])

c_dot = np.dot(a,b)
# array([[2, 4],
#       [2, 3]])

# Or 
c_dot_2 = a.dot(b)
# array([[2, 4],
#       [2, 3]])

np.sum(a)
np.min(a)
np.max(a)
np.mean()
np.median()

Find the index

1
2
3
4
5
6
7
8
9
import numpy as np
A = np.arange(2,14).reshape((3,4)) 

# array([[ 2, 3, 4, 5]
#        [ 6, 7, 8, 9]
#        [10,11,12,13]])
         
print(np.argmin(A))    # 0
print(np.argmax(A))    # 11

np.cumsum

1
2
3
print(np.cumsum(A)) 
# 累加
# [2 5 9 14 20 27 35 44 54 65 77 90]

np.diff

1
2
3
4
5
print(np.diff(A))    
# 累差 后项减前项
# [[1 1 1]
#  [1 1 1]
#  [1 1 1]]

np.nonzero

1
2
3
print(np.nonzero(A))    

# (array([0,0,0,0,1,1,1,1,2,2,2,2]),array([0,1,2,3,0,1,2,3,0,1,2,3]))

np.transpose(A) = A.T

np.clip

1
2
3
4
5
6
7
8
9
print(A)
# array([[14,13,12,11]
#        [10, 9, 8, 7]
#        [ 6, 5, 4, 3]])

print(np.clip(A,5,9))    
# array([[ 9, 9, 9, 9]
#        [ 9, 9, 8, 7]
#        [ 6, 5, 5, 5]])

Index

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
A = np.arange(3,15).reshape((3,4))
"""
array([[ 3,  4,  5,  6]
       [ 7,  8,  9, 10]
       [11, 12, 13, 14]])
"""
         
print(A[2])         
# [11 12 13 14]

print(A[1][1])      # 8
print(A[1, 1])      # 8
print(A[1, 1:3])    # [8 9]

print(A.flatten())   
# array([3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14])

Combine Array

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
import numpy as np
A = np.array([1,1,1])
B = np.array([2,2,2])
         
print(np.vstack((A,B)))    # vertical stack
"""
[[1,1,1]
 [2,2,2]]
"""

D = np.hstack((A,B))       # horizontal stack

print(D)
# [1,1,1,2,2,2]

print(A.shape,D.shape)
# (3,) (6,)

np.array to matrix

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
print(A[np.newaxis,:])
# [[1 1 1]]

print(A[np.newaxis,:].shape)
# (1,3)

print(A[:,np.newaxis])
"""
[[1]
[1]
[1]]
"""

print(A[:,np.newaxis].shape)
# (3,1)

import numpy as np
A = np.array([1,1,1])[:,np.newaxis]
B = np.array([2,2,2])[:,np.newaxis]
         
C = np.vstack((A,B))   # vertical stack
D = np.hstack((A,B))   # horizontal stack

print(D)
"""
[[1 2]
[1 2]
[1 2]]
"""

print(A.shape,D.shape)
# (3,1) (3,2)

np.concatenate

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
C = np.concatenate((A,B,B,A),axis=0)

print(C)
"""
array([[1],
       [1],
       [1],
       [2],
       [2],
       [2],
       [2],
       [2],
       [2],
       [1],
       [1],
       [1]])
"""

D = np.concatenate((A,B,B,A),axis=1)

print(D)
"""
array([[1, 2, 2, 1],
       [1, 2, 2, 1],
       [1, 2, 2, 1]])
"""

Array Split

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
#只能做等量分割
A = np.arange(12).reshape((3, 4))
print(A)
"""
array([[ 0,  1,  2,  3],
    [ 4,  5,  6,  7],
    [ 8,  9, 10, 11]])
"""

print(np.split(A, 2, axis=1))
"""
[array([[0, 1],
        [4, 5],
        [8, 9]]), array([[ 2,  3],
        [ 6,  7],
        [10, 11]])]
"""

print(np.split(A, 3, axis=0))

# [array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8,  9, 10, 11]])]

# 不等量分割
print(np.array_split(A, 3, axis=1))
"""
[array([[0, 1],
        [4, 5],
        [8, 9]]), array([[ 2],
        [ 6],
        [10]]), array([[ 3],
        [ 7],
        [11]])]
"""

print(np.vsplit(A, 3)) #等于 print(np.split(A, 3, axis=0))

# [array([[0, 1, 2, 3]]), array([[4, 5, 6, 7]]), array([[ 8,  9, 10, 11]])]


print(np.hsplit(A, 2)) #等于 print(np.split(A, 2, axis=1))
"""
[array([[0, 1],
       [4, 5],
       [8, 9]]), array([[ 2,  3],
        [ 6,  7],
        [10, 11]])]
"""

Pandas

如果用 python 的列表和字典来作比较, 那么可以说 Numpy 是列表形式的，没有数值标签，而 Pandas 就是字典形式。Pandas是基于Numpy构建的，让Numpy为中心的应用变得更加简单。

要使用pandas，首先需要了解他主要两个数据结构：Series和DataFrame

Series

1
2
3
4
5
6
7
8
9
10
11
12
13
14
import pandas as pd
import numpy as np
s = pd.Series([1,3,6,np.nan,44,1])

print(s)
"""
0     1.0
1     3.0
2     6.0
3     NaN
4    44.0
5     1.0
dtype: float64
"""

DataFrame

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
dates = pd.date_range('20160101',periods=6)
df = pd.DataFrame(np.random.randn(6,4),index=dates,columns=['a','b','c','d'])

print(df)
"""
                   a         b         c         d
2016-01-01 -0.253065 -2.071051 -0.640515  0.613663
2016-01-02 -1.147178  1.532470  0.989255 -0.499761
2016-01-03  1.221656 -2.390171  1.862914  0.778070
2016-01-04  1.473877 -0.046419  0.610046  0.204672
2016-01-05 -1.584752 -0.700592  1.487264 -1.778293
2016-01-06  0.633675 -1.414157 -0.277066 -0.442545
"""

df1 = pd.DataFrame(np.arange(12).reshape((3,4)))
print(df1)

"""
   0  1   2   3
0  0  1   2   3
1  4  5   6   7
2  8  9  10  11
"""

df2 = pd.DataFrame({'A' : 1.,
                    'B' : pd.Timestamp('20130102'),
                    'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
                    'D' : np.array([3] * 4,dtype='int32'),
                    'E' : pd.Categorical(["test","train","test","train"]),
                    'F' : 'foo'})
                    
print(df2)

"""
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo
"""

print(df2.dtypes)

"""
df2.dtypes
A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object
"""

Select Data

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates, columns=['A','B','C','D'])

"""
             A   B   C   D
2013-01-01   0   1   2   3
2013-01-02   4   5   6   7
2013-01-03   8   9  10  11
2013-01-04  12  13  14  15
2013-01-05  16  17  18  19
2013-01-06  20  21  22  23
"""

print(df['A'])
print(df.A)

"""
2013-01-01     0
2013-01-02     4
2013-01-03     8
2013-01-04    12
2013-01-05    16
2013-01-06    20
Freq: D, Name: A, dtype: int64
"""

print(df[0:3])
 
"""
            A  B   C   D
2013-01-01  0  1   2   3
2013-01-02  4  5   6   7
2013-01-03  8  9  10  11
"""

print(df['20130102':'20130104'])

"""
A   B   C   D
2013-01-02   4   5   6   7
2013-01-03   8   9  10  11
2013-01-04  12  13  14  15
"""

df.loc

select with label

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
df.loc['20130102']
"""
A    4
B    5
C    6
D    7
Name: 2013-01-02 00:00:00, dtype: int64
"""

df.loc[:,['A','B']]
"""
             A   B
2013-01-01   0   1
2013-01-02   4   5
2013-01-03   8   9
2013-01-04  12  13
2013-01-05  16  17
2013-01-06  20  21
"""

df.loc['20130102',['A','B']]
"""
A    4
B    5
Name: 2013-01-02 00:00:00, dtype: int64
"""

df.iloc

select with index

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
df.iloc[3,1]
# 13

df.iloc[3:5,1:3]
"""
             B   C
2013-01-04  13  14
2013-01-05  17  18
"""

df.iloc[[1,3,5],1:3]
"""
             B   C
2013-01-02   5   6
2013-01-04  13  14
2013-01-06  21  22

"""

df.ix

Mix

1
2
3
4
5
6
7
8
9
10
11
12
13
14
print(df.ix[:3,['A','C']])
"""
            A   C
2013-01-01  0   2
2013-01-02  4   6
2013-01-03  8  10
"""

"""
             A   B   C   D
2013-01-04  12  13  14  15
2013-01-05  16  17  18  19
2013-01-06  20  21  22  23
"""

Na in Pandas

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates, columns=['A','B','C','D'])
df.iloc[0,1] = np.nan
df.iloc[1,2] = np.nan
"""
             A     B     C   D
2013-01-01   0   NaN   2.0   3
2013-01-02   4   5.0   NaN   7
2013-01-03   8   9.0  10.0  11
2013-01-04  12  13.0  14.0  15
2013-01-05  16  17.0  18.0  19
2013-01-06  20  21.0  22.0  23
"""

df.dropna(
    axis=0,     # 0: 对行进行操作; 1: 对列进行操作
    how='any'   # 'any': 只要存在 NaN 就 drop 掉; 'all': 必须全部是 NaN 才 drop 
    ) 
"""
             A     B     C   D
2013-01-03   8   9.0  10.0  11
2013-01-04  12  13.0  14.0  15
2013-01-05  16  17.0  18.0  19
2013-01-06  20  21.0  22.0  23
"""

df.fillna(value=0)
"""
             A     B     C   D
2013-01-01   0   0.0   2.0   3
2013-01-02   4   5.0   0.0   7
2013-01-03   8   9.0  10.0  11
2013-01-04  12  13.0  14.0  15
2013-01-05  16  17.0  18.0  19
2013-01-06  20  21.0  22.0  23
"""

df.isnull() 
"""
                A      B      C      D
2013-01-01  False   True  False  False
2013-01-02  False  False   True  False
2013-01-03  False  False  False  False
2013-01-04  False  False  False  False
2013-01-05  False  False  False  False
2013-01-06  False  False  False  False
"""

pd.concat

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['a','b','c','d'])
df3 = pd.DataFrame(np.ones((3,4))*2, columns=['a','b','c','d'])

#concat纵向合并
res = pd.concat([df1, df2, df3], axis=0)

#打印结果
print(res)
#     a    b    c    d
# 0  0.0  0.0  0.0  0.0
# 1  0.0  0.0  0.0  0.0
# 2  0.0  0.0  0.0  0.0
# 0  1.0  1.0  1.0  1.0
# 1  1.0  1.0  1.0  1.0
# 2  1.0  1.0  1.0  1.0
# 0  2.0  2.0  2.0  2.0
# 1  2.0  2.0  2.0  2.0
# 2  2.0  2.0  2.0  2.0

#承上一个例子，并将index_ignore设定为True
res = pd.concat([df1, df2, df3], axis=0, ignore_index=True)

#打印结果
print(res)
#     a    b    c    d
# 0  0.0  0.0  0.0  0.0
# 1  0.0  0.0  0.0  0.0
# 2  0.0  0.0  0.0  0.0
# 3  1.0  1.0  1.0  1.0
# 4  1.0  1.0  1.0  1.0
# 5  1.0  1.0  1.0  1.0
# 6  2.0  2.0  2.0  2.0
# 7  2.0  2.0  2.0  2.0
# 8  2.0  2.0  2.0  2.0

### join
## 此方式是依照column来做纵向合并，有相同的column上下合并在一起，其他独自的column个自成列，原本没有值的位置皆以NaN填充
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'], index=[1,2,3])
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['b','c','d','e'], index=[2,3,4])

#纵向"外"合并df1与df2
res = pd.concat([df1, df2], axis=0, join='outer')

print(res)
#     a    b    c    d    e
# 1  0.0  0.0  0.0  0.0  NaN
# 2  0.0  0.0  0.0  0.0  NaN
# 3  0.0  0.0  0.0  0.0  NaN
# 2  NaN  1.0  1.0  1.0  1.0
# 3  NaN  1.0  1.0  1.0  1.0
# 4  NaN  1.0  1.0  1.0  1.0


#纵向"内"合并df1与df2
res = pd.concat([df1, df2], axis=0, join='inner')

#打印结果
print(res)
#     b    c    d
# 1  0.0  0.0  0.0
# 2  0.0  0.0  0.0
# 3  0.0  0.0  0.0
# 2  1.0  1.0  1.0
# 3  1.0  1.0  1.0
# 4  1.0  1.0  1.0

#重置index并打印结果
res = pd.concat([df1, df2], axis=0, join='inner', ignore_index=True)
print(res)
#     b    c    d
# 0  0.0  0.0  0.0
# 1  0.0  0.0  0.0
# 2  0.0  0.0  0.0
# 3  1.0  1.0  1.0
# 4  1.0  1.0  1.0
# 5  1.0  1.0  1.0

df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'], index=[1,2,3])
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['b','c','d','e'], index=[2,3,4])

#依照`df1.index`进行横向合并
res = pd.concat([df1, df2], axis=1, join_axes=[df1.index])

#打印结果
print(res)
#     a    b    c    d    b    c    d    e
# 1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN
# 2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
# 3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0

#移除join_axes，并打印结果
res = pd.concat([df1, df2], axis=1)
print(res)
#     a    b    c    d    b    c    d    e
# 1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN
# 2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
# 3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
# 4  NaN  NaN  NaN  NaN  1.0  1.0  1.0  1.0

append

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
#只有纵向合并
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['a','b','c','d'])
df3 = pd.DataFrame(np.ones((3,4))*1, columns=['a','b','c','d'])
s1 = pd.Series([1,2,3,4], index=['a','b','c','d'])

#将df2合并到df1的下面，以及重置index，并打印出结果
res = df1.append(df2, ignore_index=True)
print(res)
#     a    b    c    d
# 0  0.0  0.0  0.0  0.0
# 1  0.0  0.0  0.0  0.0
# 2  0.0  0.0  0.0  0.0
# 3  1.0  1.0  1.0  1.0
# 4  1.0  1.0  1.0  1.0
# 5  1.0  1.0  1.0  1.0

#合并多个df，将df2与df3合并至df1的下面，以及重置index，并打印出结果
res = df1.append([df2, df3], ignore_index=True)
print(res)
#     a    b    c    d
# 0  0.0  0.0  0.0  0.0
# 1  0.0  0.0  0.0  0.0
# 2  0.0  0.0  0.0  0.0
# 3  1.0  1.0  1.0  1.0
# 4  1.0  1.0  1.0  1.0
# 5  1.0  1.0  1.0  1.0
# 6  1.0  1.0  1.0  1.0
# 7  1.0  1.0  1.0  1.0
# 8  1.0  1.0  1.0  1.0

#合并series，将s1合并至df1，以及重置index，并打印出结果
res = df1.append(s1, ignore_index=True)
print(res)
#     a    b    c    d
# 0  0.0  0.0  0.0  0.0
# 1  0.0  0.0  0.0  0.0
# 2  0.0  0.0  0.0  0.0
# 3  1.0  2.0  3.0  4.0

merge

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
#基于 key clolumn 合并
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

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

indicator

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
import pandas as pd

#定义资料集并打印出
df1 = pd.DataFrame({'col1':[0,1], 'col_left':['a','b']})
df2 = pd.DataFrame({'col1':[1,2,2],'col_right':[2,2,2]})

print(df1)
#   col1 col_left
# 0     0        a
# 1     1        b

print(df2)
#   col1  col_right
# 0     1          2
# 1     2          2
# 2     2          2

# 依据col1进行合并，并启用indicator=True，最后打印出
res = pd.merge(df1, df2, on='col1', how='outer', indicator=True)
print(res)
#   col1 col_left  col_right      _merge
# 0   0.0        a        NaN   left_only
# 1   1.0        b        2.0        both
# 2   2.0      NaN        2.0  right_only
# 3   2.0      NaN        2.0  right_only

# 自定indicator column的名称，并打印出
res = pd.merge(df1, df2, on='col1', how='outer', indicator='indicator_column')
print(res)
#   col1 col_left  col_right indicator_column
# 0   0.0        a        NaN        left_only
# 1   1.0        b        2.0             both
# 2   2.0      NaN        2.0       right_only
# 3   2.0      NaN        2.0       right_only

index

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
import pandas as pd

#定义资料集并打印出
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)
#     A   B
# K0  A0  B0
# K1  A1  B1
# K2  A2  B2

print(right)
#     C   D
# K0  C0  D0
# K2  C2  D2
# K3  C3  D3

#依据左右资料集的index进行合并，how='outer',并打印出
res = pd.merge(left, right, left_index=True, right_index=True, how='outer')
print(res)
#      A    B    C    D
# K0   A0   B0   C0   D0
# K1   A1   B1  NaN  NaN
# K2   A2   B2   C2   D2
# K3  NaN  NaN   C3   D3

#依据左右资料集的index进行合并，how='inner',并打印出
res = pd.merge(left, right, left_index=True, right_index=True, how='inner')
print(res)
#     A   B   C   D
# K0  A0  B0  C0  D0
# K2  A2  B2  C2  D2


boys = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [1, 2, 3]})
girls = pd.DataFrame({'k': ['K0', 'K0', 'K3'], 'age': [4, 5, 6]})

#使用suffixes解决overlapping的问题
res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='inner')
print(res)
#    age_boy   k  age_girl
# 0        1  K0         4
# 1        1  K0         5
Author: shixuan liu
Link: http://tedlsx.github.io/2019/06/24/numpy-pandas/
Copyright Notice: All articles in this blog are licensed under CC BY-NC-SA 4.0 unless stating additionally.
numpy
Donate
  • Wechat
  • Alipay
Comment
简