-
Notifications
You must be signed in to change notification settings - Fork 1.3k
/
Copy pathtest_adasyn.py
152 lines (141 loc) · 4.6 KB
/
test_adasyn.py
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
"""Test the module under sampler."""
# Authors: Guillaume Lemaitre <[email protected]>
# Christos Aridas
# License: MIT
import numpy as np
from sklearn.neighbors import NearestNeighbors
from sklearn.utils._testing import assert_allclose, assert_array_equal
from imblearn.over_sampling import ADASYN
RND_SEED = 0
X = np.array(
[
[0.11622591, -0.0317206],
[0.77481731, 0.60935141],
[1.25192108, -0.22367336],
[0.53366841, -0.30312976],
[1.52091956, -0.49283504],
[-0.28162401, -2.10400981],
[0.83680821, 1.72827342],
[0.3084254, 0.33299982],
[0.70472253, -0.73309052],
[0.28893132, -0.38761769],
[1.15514042, 0.0129463],
[0.88407872, 0.35454207],
[1.31301027, -0.92648734],
[-1.11515198, -0.93689695],
[-0.18410027, -0.45194484],
[0.9281014, 0.53085498],
[-0.14374509, 0.27370049],
[-0.41635887, -0.38299653],
[0.08711622, 0.93259929],
[1.70580611, -0.11219234],
]
)
Y = np.array([0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0])
R_TOL = 1e-4
XX = np.array(
[
[0.11622591, -0.0317206],
[0.77481731, 0.60935141],
[1.25192108, -0.22367336],
[0.53366841, -0.30312976],
[1.52091956, -0.49283504],
[-0.28162401, -2.10400981],
[0.83680821, 1.72827342],
[0.3084254, 0.33299982],
[0.70472253, -0.73309052],
[0.28893132, -0.38761769],
[1.15514042, 0.0129463],
[0.88407872, 0.35454207],
]
)
YY = np.array([0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0])
XXX = np.array(
[
[0.915, 0.892],
[0.926, 0.959],
[0.917, 0.983],
[0.945, 0.967],
[-0.844, -0.925],
[-0.987, -0.946],
[-0.962, -0.948],
]
)
YYY = np.array([1, 1, 1, 1, 0, 0, 0])
def test_ada_init():
sampling_strategy = "auto"
ada = ADASYN(sampling_strategy=sampling_strategy, random_state=RND_SEED)
assert ada.random_state == RND_SEED
def test_ada_fit_resample():
ada = ADASYN(random_state=RND_SEED)
X_resampled, y_resampled = ada.fit_resample(X, Y)
X_gt = np.array(
[
[0.11622591, -0.0317206],
[0.77481731, 0.60935141],
[1.25192108, -0.22367336],
[0.53366841, -0.30312976],
[1.52091956, -0.49283504],
[-0.28162401, -2.10400981],
[0.83680821, 1.72827342],
[0.3084254, 0.33299982],
[0.70472253, -0.73309052],
[0.28893132, -0.38761769],
[1.15514042, 0.0129463],
[0.88407872, 0.35454207],
[1.31301027, -0.92648734],
[-1.11515198, -0.93689695],
[-0.18410027, -0.45194484],
[0.9281014, 0.53085498],
[-0.14374509, 0.27370049],
[-0.41635887, -0.38299653],
[0.08711622, 0.93259929],
[1.70580611, -0.11219234],
[0.88161986, -0.2829741],
[0.35681689, -0.18814597],
[1.4148276, 0.05308106],
[0.3136591, -0.31327875],
]
)
y_gt = np.array(
[0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0]
)
assert_allclose(X_resampled, X_gt, rtol=R_TOL)
assert_array_equal(y_resampled, y_gt)
def test_ada_fit_resample_nn_obj():
nn = NearestNeighbors(n_neighbors=6)
ada = ADASYN(random_state=RND_SEED, n_neighbors=nn)
X_resampled, y_resampled = ada.fit_resample(X, Y)
X_gt = np.array(
[
[0.11622591, -0.0317206],
[0.77481731, 0.60935141],
[1.25192108, -0.22367336],
[0.53366841, -0.30312976],
[1.52091956, -0.49283504],
[-0.28162401, -2.10400981],
[0.83680821, 1.72827342],
[0.3084254, 0.33299982],
[0.70472253, -0.73309052],
[0.28893132, -0.38761769],
[1.15514042, 0.0129463],
[0.88407872, 0.35454207],
[1.31301027, -0.92648734],
[-1.11515198, -0.93689695],
[-0.18410027, -0.45194484],
[0.9281014, 0.53085498],
[-0.14374509, 0.27370049],
[-0.41635887, -0.38299653],
[0.08711622, 0.93259929],
[1.70580611, -0.11219234],
[0.88161986, -0.2829741],
[0.35681689, -0.18814597],
[1.4148276, 0.05308106],
[0.3136591, -0.31327875],
]
)
y_gt = np.array(
[0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0]
)
assert_allclose(X_resampled, X_gt, rtol=R_TOL)
assert_array_equal(y_resampled, y_gt)