forked from scikit-learn-contrib/imbalanced-learn
/
test_instance_hardness_threshold.py
224 lines (184 loc) · 9.8 KB
/
test_instance_hardness_threshold.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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
"""Test the module ."""
from __future__ import print_function
import numpy as np
from numpy.testing import (assert_array_equal, assert_equal, assert_raises,
assert_raises_regex)
from sklearn.ensemble import GradientBoostingClassifier
from imblearn.under_sampling import InstanceHardnessThreshold
# Generate a global dataset to use
RND_SEED = 0
X = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.03852113, 0.40910479], [-0.43877303, 1.07366684],
[-0.85795321, 0.82980738], [-0.18430329, 0.52328473],
[-0.30126957, -0.66268378], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [0.20246714, -0.34727125],
[1.06446472, -1.09279772], [0.30543283, -0.02589502],
[-0.00717161, 0.00318087]])
Y = np.array([0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0])
ESTIMATOR = 'gradient-boosting'
def test_iht_wrong_estimator():
# Resample the data
ratio = 0.7
est = 'rnd'
iht = InstanceHardnessThreshold(
estimator=est, ratio=ratio, random_state=RND_SEED)
assert_raises(NotImplementedError, iht.fit_sample, X, Y)
def test_iht_init():
# Define a ratio
ratio = 'auto'
iht = InstanceHardnessThreshold(
ESTIMATOR, ratio=ratio, random_state=RND_SEED)
assert_equal(iht.ratio, ratio)
assert_equal(iht.random_state, RND_SEED)
def test_iht_fit_sample():
# Resample the data
iht = InstanceHardnessThreshold(ESTIMATOR, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_with_indices():
# Resample the data
iht = InstanceHardnessThreshold(
ESTIMATOR, return_indices=True, random_state=RND_SEED)
X_resampled, y_resampled, idx_under = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
idx_gt = np.array([0, 1, 2, 3, 5, 6, 7, 9, 10, 12, 13, 14])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
assert_array_equal(idx_under, idx_gt)
def test_iht_fit_sample_half():
# Resample the data
ratio = 0.7
iht = InstanceHardnessThreshold(
ESTIMATOR, ratio=ratio, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.03852113, 0.40910479], [-0.43877303, 1.07366684],
[-0.85795321, 0.82980738], [-0.18430329, 0.52328473],
[-0.30126957, -0.66268378], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_knn():
# Resample the data
est = 'knn'
iht = InstanceHardnessThreshold(est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.30126957, -0.66268378], [-0.65571327, 0.42412021],
[0.20246714, -0.34727125], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_decision_tree():
# Resample the data
est = 'decision-tree'
iht = InstanceHardnessThreshold(est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_random_forest():
# Resample the data
est = 'random-forest'
iht = InstanceHardnessThreshold(est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.03852113, 0.40910479], [-0.43877303, 1.07366684],
[-0.85795321, 0.82980738], [-0.18430329, 0.52328473],
[-0.65571327, 0.42412021], [-0.28305528, 0.30284991],
[1.06446472, -1.09279772], [0.30543283, -0.02589502],
[-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_adaboost():
# Resample the data
est = 'adaboost'
iht = InstanceHardnessThreshold(est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_gradient_boosting():
# Resample the data
est = 'gradient-boosting'
iht = InstanceHardnessThreshold(est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_linear_svm():
# Resample the data
est = 'linear-svm'
iht = InstanceHardnessThreshold(est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.03852113, 0.40910479], [-0.43877303, 1.07366684],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_class_obj():
# Resample the data
est = GradientBoostingClassifier(random_state=RND_SEED)
iht = InstanceHardnessThreshold(estimator=est, random_state=RND_SEED)
X_resampled, y_resampled = iht.fit_sample(X, Y)
X_gt = np.array([[-0.3879569, 0.6894251], [-0.09322739, 1.28177189],
[-0.77740357, 0.74097941], [0.91542919, -0.65453327],
[-0.43877303, 1.07366684], [-0.85795321, 0.82980738],
[-0.18430329, 0.52328473], [-0.65571327, 0.42412021],
[-0.28305528, 0.30284991], [1.06446472, -1.09279772],
[0.30543283, -0.02589502], [-0.00717161, 0.00318087]])
y_gt = np.array([0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0])
assert_array_equal(X_resampled, X_gt)
assert_array_equal(y_resampled, y_gt)
def test_iht_fit_sample_wrong_class_obj():
# Resample the data
from sklearn.cluster import KMeans
est = KMeans()
iht = InstanceHardnessThreshold(estimator=est, random_state=RND_SEED)
assert_raises_regex(ValueError, "Invalid parameter `estimator`",
iht.fit_sample, X, Y)