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
|
"""!
@brief Unit-tests for K-Medians algorithm.
@authors Andrei Novikov (pyclustering@yandex.ru)
@date 2014-2020
@copyright BSD-3-Clause
"""
import unittest
import numpy
# Generate images without having a window appear.
import matplotlib
matplotlib.use('Agg')
from pyclustering.cluster.tests.kmedians_templates import KmediansTestTemplates
from pyclustering.cluster.kmedians import kmedians
from pyclustering.samples.definitions import SIMPLE_SAMPLES
from pyclustering.utils import read_sample
from pyclustering.utils.metric import type_metric, distance_metric
class KmediansUnitTest(unittest.TestCase):
def testClusterAllocationSampleSimple1(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False)
def testClusterAllocationSampleSimple1Euclidean(self):
metric = distance_metric(type_metric.EUCLIDEAN)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1EuclideanSquare(self):
metric = distance_metric(type_metric.EUCLIDEAN_SQUARE)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Manhattan(self):
metric = distance_metric(type_metric.MANHATTAN)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Chebyshev(self):
metric = distance_metric(type_metric.CHEBYSHEV)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Minkowski(self):
metric = distance_metric(type_metric.MINKOWSKI, degree=2.0)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined(self):
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSample1NumpyArrayUserDefined(self):
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
input_data = numpy.array(read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1))
initial_centers = numpy.array([[3.7, 5.5], [6.7, 7.5]])
KmediansTestTemplates.templateLengthProcessData(input_data, initial_centers, [5, 5], False, metric=metric)
def testClusterAllocationSample2NumpyArrayUserDefined(self):
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN_SQUARE))
input_data = numpy.array(read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2))
initial_centers = numpy.array([[3.5, 4.8], [6.9, 7], [7.5, 0.5]])
KmediansTestTemplates.templateLengthProcessData(input_data, initial_centers, [10, 5, 8], False, metric=metric)
def testClusterOneAllocationSampleSimple1(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[1.0, 2.5]], [10], False)
def testClusterAllocationSampleSimple2(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False)
def testClusterOneAllocationSampleSimple2(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[0.5, 0.2]], [23], False)
def testClusterAllocationSampleSimple3(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]], [10, 10, 10, 30], False)
def testClusterOneAllocationSampleSimple3(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, [[0.2, 0.1]], [60], False)
def testClusterAllocationSampleSimple5(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[0.0, 1.0], [0.0, 0.0], [1.0, 1.0], [1.0, 0.0]], [15, 15, 15, 15], False)
def testClusterOneAllocationSampleSimple5(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[0.0, 0.0]], [60], False)
def testClusterAllocationSample1WrongInitialNumberCenters1(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[2.8, 9.5], [3.5, 6.6], [1.3, 4.0]], None, False)
def testClusterAllocationSample1WrongInitialNumberCenters2(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[2.8, 9.5], [3.5, 6.6], [1.3, 4.0], [1.2, 4.5]], None, False)
def testClusterAllocationSample2WrongInitialNumberCenters(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5], [7.3, 4.5], [3.1, 5.4]], None, False)
def testClusterTheSameData1(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE9, [ [4.1], [7.3] ], [10, 20], False)
def testClusterTheSameData2(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE12, [ [1.1, 1.0], [3.0, 3.1], [5.0, 4.9] ], [5, 5, 5], False)
def testOddSize(self):
# Bug issue #428 (https://github.com/annoviko/pyclustering/issues/428)
data = [[59.00732, 9.748167], [59.00608, 9.749117], [59.0047, 9.749933]]
KmediansTestTemplates.templateLengthProcessData(data, [[59.00732, 9.748167], [59.00608, 9.749117]], None, False, tolerance=10)
def testDifferentDimensions(self):
kmedians_instance = kmedians([ [0, 1, 5], [0, 2, 3] ], [ [0, 3] ], ccore=False)
self.assertRaises(NameError, kmedians_instance.process)
def testClusterAllocationOneDimensionData(self):
KmediansTestTemplates.templateClusterAllocationOneDimensionData(False)
def testClusterAllocationTheSameObjectsOneInitialCenter(self):
KmediansTestTemplates.templateClusterAllocationTheSameObjects(20, 1, False)
def testClusterAllocationTheSameObjectsTwoInitialCenters(self):
KmediansTestTemplates.templateClusterAllocationTheSameObjects(15, 2, False)
def testClusterAllocationTheSameObjectsThreeInitialCenters(self):
KmediansTestTemplates.templateClusterAllocationTheSameObjects(25, 3, False)
def testClusterAllocationSampleRoughMediansSimple10(self):
initial_medians = [[0.0772944481804071, 0.05224990900863469], [1.6021689021213712, 1.0347579135245601], [2.3341008076636096, 1.280022869739064]]
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE10, initial_medians, None, False)
def testTotalWCESimple4(self):
sample = [[0, 1, 5], [7, 8, 9], [0, 2, 3], [4, 5, 6]]
initial_medians = [[0, 3, 2], [4, 6, 5]]
kmedians_instance = kmedians(sample, initial_medians, ccore=False)
self.assertNotEqual(self, kmedians_instance.get_total_wce(), 16.0)
def testPredictOnePoint(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[0.3, 0.2]], [0], False)
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[4.1, 1.1]], [1], False)
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[2.1, 1.9]], [2], False)
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[2.1, 4.1]], [3], False)
def testPredictOnePointUserMetric(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[0.3, 0.2]], [0], False, metric=metric)
def testPredictTwoPoints(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[0.3, 0.2], [2.1, 1.9]], [0, 2], False)
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[2.1, 4.1], [2.1, 1.9]], [3, 2], False)
def testPredictTwoPointsUserMetric(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[0.3, 0.2], [2.1, 1.9]], [0, 2], False, metric=metric)
def testPredictFourPoints(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
to_predict = [[0.3, 0.2], [4.1, 1.1], [2.1, 1.9], [2.1, 4.1]]
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 2, 3], False)
def testPredictFivePoints(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
to_predict = [[0.3, 0.2], [4.1, 1.1], [3.9, 1.1], [2.1, 1.9], [2.1, 4.1]]
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False)
def testPredictFivePointsUserMetric(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
to_predict = [[0.3, 0.2], [4.1, 1.1], [3.9, 1.1], [2.1, 1.9], [2.1, 4.1]]
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmediansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testItermax0(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [], False, itermax=0)
def testItermax1(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, itermax=1)
def testItermax10Simple01(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, itermax=10)
def testItermax10Simple02(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False, itermax=10)
def test_incorrect_data(self):
self.assertRaises(ValueError, kmedians, [], [[1]])
def test_incorrect_centers(self):
self.assertRaises(ValueError, kmedians, [[0], [1], [2]], [])
def test_incorrect_tolerance(self):
self.assertRaises(ValueError, kmedians, [[0], [1], [2]], [[1]], -1.0)
def test_incorrect_itermax(self):
self.assertRaises(ValueError, kmedians, [[0], [1], [2]], [[1]], itermax=-5)
|
