网捷达

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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import numpy as np

print(np.__version__)
# 1.26.1

a = np.genfromtxt('data/src/sample_nan.csv', delimiter=',')
print(a)
# [[11. 12. nan 14.]
#  [21. nan nan 24.]
#  [31. 32. 33. 34.]]

a_nan = np.array([0, 1, np.nan, float('nan')])
print(a_nan)
# [ 0.  1. nan nan]

print(np.nan == np.nan)
# False

print(np.isnan(np.nan))
# True

print(a_nan == np.nan)
# [False False False False]

print(np.isnan(a_nan))
# [False False  True  True]

a_fill = np.genfromtxt('data/src/sample_nan.csv', delimiter=',',
                       filling_values=0)
print(a_fill)
# [[11. 12.  0. 14.]
#  [21.  0.  0. 24.]
#  [31. 32. 33. 34.]]

a = np.genfromtxt('data/src/sample_nan.csv', delimiter=',')
print(a)
# [[11. 12. nan 14.]
#  [21. nan nan 24.]
#  [31. 32. 33. 34.]]

print(np.nan_to_num(a))
# [[11. 12.  0. 14.]
#  [21.  0.  0. 24.]
#  [31. 32. 33. 34.]]

print(a)
# [[11. 12. nan 14.]
#  [21. nan nan 24.]
#  [31. 32. 33. 34.]]

np.nan_to_num(a, copy=False)
print(a)
# [[11. 12.  0. 14.]
#  [21.  0.  0. 24.]
#  [31. 32. 33. 34.]]

a = np.genfromtxt('data/src/sample_nan.csv', delimiter=',')
print(a)
# [[11. 12. nan 14.]
#  [21. nan nan 24.]
#  [31. 32. 33. 34.]]

print(np.nan_to_num(a, nan=-1))
# [[11. 12. -1. 14.]
#  [21. -1. -1. 24.]
#  [31. 32. 33. 34.]]

print(np.nanmean(a))
# 23.555555555555557

print(np.nan_to_num(a, nan=np.nanmean(a)))
# [[11.         12.         23.55555556 14.        ]
#  [21.         23.55555556 23.55555556 24.        ]
#  [31.         32.         33.         34.        ]]

print(np.nanmean(a, axis=0, keepdims=True))
# [[21. 22. 33. 24.]]

print(np.nan_to_num(a, nan=np.nanmean(a, axis=0, keepdims=True)))
# [[11. 12. 33. 14.]
#  [21. 22. 33. 24.]
#  [31. 32. 33. 34.]]

print(np.nanmean(a, axis=1, keepdims=True))
# [[12.33333333]
#  [22.5       ]
#  [32.5       ]]

print(np.nan_to_num(a, nan=np.nanmean(a, axis=1, keepdims=True)))
# [[11.         12.         12.33333333 14.        ]
#  [21.         22.5        22.5        24.        ]
#  [31.         32.         33.         34.        ]]

a = np.genfromtxt('data/src/sample_nan.csv', delimiter=',')
print(a)
# [[11. 12. nan 14.]
#  [21. nan nan 24.]
#  [31. 32. 33. 34.]]

print(np.isnan(a))
# [[False False  True False]
#  [False  True  True False]
#  [False False False False]]

a[np.isnan(a)] = 0
print(a)
# [[11. 12.  0. 14.]
#  [21.  0.  0. 24.]
#  [31. 32. 33. 34.]]

a = np.genfromtxt('data/src/sample_nan.csv', delimiter=',')

a[np.isnan(a)] = np.nanmean(a)
print(a)
# [[11.         12.         23.55555556 14.        ]
#  [21.         23.55555556 23.55555556 24.        ]
#  [31.         32.         33.         34.        ]]

a = np.genfromtxt('data/src/sample_nan.csv', delimiter=',')

print(np.where(np.isnan(a), np.nanmean(a, axis=0, keepdims=True), a))
# [[11. 12. 33. 14.]
#  [21. 22. 33. 24.]
#  [31. 32. 33. 34.]]

print(np.where(np.isnan(a), np.nanmean(a, axis=1, keepdims=True), a))
# [[11.         12.         12.33333333 14.        ]
#  [21.         22.5        22.5        24.        ]
#  [31.         32.         33.         34.        ]]