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
|
"""!
@brief Integration-tests for K-Medians algorithm.
@authors Andrei Novikov (pyclustering@yandex.ru)
@date 2014-2020
@copyright BSD-3-Clause
"""
import unittest
import numpy
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.core.tests import remove_library
from pyclustering.utils import read_sample
from pyclustering.utils.metric import type_metric, distance_metric
class KmediansIntegrationTest(unittest.TestCase):
def testClusterAllocationSampleSimple1Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True)
def testClusterAllocationSampleSimple1EuclideanCore(self):
metric = distance_metric(type_metric.EUCLIDEAN)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True, metric=metric)
def testClusterAllocationSampleSimple1EuclideanSquareCore(self):
metric = distance_metric(type_metric.EUCLIDEAN_SQUARE)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True, metric=metric)
def testClusterAllocationSampleSimple1ManhattanCore(self):
metric = distance_metric(type_metric.MANHATTAN)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True, metric=metric)
def testClusterAllocationSampleSimple1ChebyshevCore(self):
metric = distance_metric(type_metric.CHEBYSHEV)
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True, metric=metric)
def testClusterAllocationSampleSimple1MinkowskiCore(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], True, metric=metric)
def testClusterAllocationSampleSimple1UserDefinedCore(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], True, metric=metric)
def testClusterOneAllocationSampleSimple1Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[1.0, 2.5]], [10], True)
def testClusterAllocationSampleSimple2Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], True)
def testClusterOneAllocationSampleSimple2Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[0.5, 0.2]], [23], True)
def testClusterAllocationSampleSimple3Core(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], True)
def testClusterOneAllocationSampleSimple3Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, [[0.2, 0.1]], [60], True)
def testClusterAllocationSampleSimple5Core(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], True)
def testClusterOneAllocationSampleSimple5Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[0.0, 0.0]], [60], True)
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], True, 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], True, metric=metric)
def testClusterAllocationSample1WrongInitialNumberCenters1Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[2.8, 9.5], [3.5, 6.6], [1.3, 4.0]], None, True)
def testClusterAllocationSample1WrongInitialNumberCenters2Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[2.8, 9.5], [3.5, 6.6], [1.3, 4.0], [1.2, 4.5]], None, True)
def testClusterAllocationSample2WrongInitialNumberCentersCore(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, True)
def testClusterTheSameData1Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE9, [ [4.1], [7.3] ], [10, 20], True)
def testClusterTheSameData2Core(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE12, [ [1.1, 1.0], [3.0, 3.1], [5.0, 4.9] ], [5, 5, 5], True)
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, True, tolerance=10)
def testClusterAllocationOneDimensionDataCore(self):
KmediansTestTemplates.templateClusterAllocationOneDimensionData(True)
def testClusterAllocationTheSameObjectsOneInitialCenterCore(self):
KmediansTestTemplates.templateClusterAllocationTheSameObjects(20, 1, True)
def testClusterAllocationTheSameObjectsTwoInitialCentersCore(self):
KmediansTestTemplates.templateClusterAllocationTheSameObjects(15, 2, True)
def testClusterAllocationTheSameObjectsThreeInitialCentersCore(self):
KmediansTestTemplates.templateClusterAllocationTheSameObjects(25, 3, True)
def testClusterAllocationSampleRoughMediansSimple10ByCore(self):
initial_medians = [[0.0772944481804071, 0.05224990900863469], [1.6021689021213712, 1.0347579135245601], [2.3341008076636096, 1.280022869739064]]
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE10, initial_medians, None, True)
def testCoreInterfaceIntInputData(self):
kmedians_instance = kmedians([ [1], [2], [3], [20], [21], [22] ], [ [2], [21] ], ccore=True)
kmedians_instance.process()
assert len(kmedians_instance.get_clusters()) == 2
@remove_library
def testProcessingWhenLibraryCoreCorrupted(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True)
def testItermax0ByCore(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [], True, itermax=0)
def testItermax1ByCore(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True, itermax=1)
def testItermax10Simple01ByCore(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], True, itermax=10)
def testItermax10Simple02ByCore(self):
KmediansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], True, itermax=10)
|
