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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
|
"""!
@brief Unit-tests for K-Means algorithm.
@authors Andrei Novikov (pyclustering@yandex.ru)
@date 2014-2020
@copyright BSD-3-Clause
"""
import unittest
import math
import numpy
# Generate images without having a window appear.
import matplotlib
matplotlib.use('Agg')
from pyclustering.cluster.tests.kmeans_templates import KmeansTestTemplates
from pyclustering.cluster.kmeans import kmeans
from pyclustering.samples.definitions import SIMPLE_SAMPLES
from pyclustering.utils import read_sample
from pyclustering.utils.metric import distance_metric, type_metric
class KmeansUnitTest(unittest.TestCase):
def testClusterAllocationSampleSimple1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False)
def testClusterOneAllocationSampleSimple1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[1.0, 2.5]], [10], False)
def testClusterAllocationSampleSimple1Euclidean(self):
metric = distance_metric(type_metric.EUCLIDEAN)
KmeansTestTemplates.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)
KmeansTestTemplates.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)
KmeansTestTemplates.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)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Minkowski01(self):
metric = distance_metric(type_metric.MINKOWSKI, degree=2)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Minkowski02(self):
metric = distance_metric(type_metric.MINKOWSKI, degree=4)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Gower(self):
metric = distance_metric(type_metric.GOWER, data=read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1))
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined1(self):
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined2(self):
metric = distance_metric(type_metric.USER_DEFINED, func=lambda p1, p2: (p1[0] - p2[0])**2 + (p1[1] - p2[1])**2)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined3(self):
metric = distance_metric(type_metric.USER_DEFINED, func=lambda p1, p2: abs(p1[0] - p2[0]) + abs(p1[1] - p2[1]))
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefinedInfitityProcessing(self):
metric = distance_metric(type_metric.USER_DEFINED, func=lambda p1, p2: p1[0] + p2[0] + 2)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [10], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined(self):
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined1NumPy(self):
data = numpy.array(read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1))
centers = numpy.array([[3.7, 5.5], [6.7, 7.5]])
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmeansTestTemplates.templateLengthProcessData(data, centers, [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1UserDefined2NumPy(self):
data = numpy.array(read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE1))
centers = numpy.array([[3.7, 5.5], [6.7, 7.5]])
def simple_2d_euclidean_distance(point_a, point_b):
return math.sqrt((point_a[0] - point_b[0]) ** 2 + (point_a[1] - point_b[1]) ** 2)
metric = distance_metric(type_metric.USER_DEFINED, func=simple_2d_euclidean_distance)
KmeansTestTemplates.templateLengthProcessData(data, centers, [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1Canberra(self):
metric = distance_metric(type_metric.CANBERRA)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple1ChiSquare(self):
metric = distance_metric(type_metric.CHI_SQUARE)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, metric=metric)
def testClusterAllocationSampleSimple2(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False)
def testClusterOneAllocationSampleSimple2(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[0.5, 0.2]], [23], False)
def testClusterAllocationSampleSimple2Canberra(self):
metric = distance_metric(type_metric.CANBERRA)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False, metric=metric)
def testClusterAllocationSampleSimple2ChiSquare(self):
metric = distance_metric(type_metric.CHI_SQUARE)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False, metric=metric)
def testClusterAllocationSampleSimple2UserDefined(self):
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False, metric=metric)
def testClusterAllocationSampleSimple2UserDefinedNumPy(self):
data = numpy.array(read_sample(SIMPLE_SAMPLES.SAMPLE_SIMPLE2))
centers = numpy.array([[3.5, 4.8], [6.9, 7], [7.5, 0.5]])
metric = distance_metric(type_metric.USER_DEFINED, func=distance_metric(type_metric.EUCLIDEAN))
KmeansTestTemplates.templateLengthProcessData(data, centers, [10, 5, 8], False, metric=metric)
def testClusterAllocationSampleSimple3(self):
KmeansTestTemplates.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 testClusterAllocationSampleSimple3UserDefinedInfitityProcessing(self):
metric = distance_metric(type_metric.USER_DEFINED, func=lambda p1, p2: p1[0] + p2[0] + 2)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]], [60], False, metric=metric)
def testClusterOneAllocationSampleSimple3(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, [[0.2, 0.1]], [60], False)
def testClusterAllocationSampleSimple4(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE4, [[1.5, 0.0], [1.5, 2.0], [1.5, 4.0], [1.5, 6.0], [1.5, 8.0]], [15, 15, 15, 15, 15], False)
def testClusterOneAllocationSampleSimple4(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE4, [[2.0, 5.0]], [75], False)
def testClusterAllocationSampleSimple5(self):
KmeansTestTemplates.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):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[0.0, 0.0]], [60], False)
def testClusterAllocationSampleSimple5Canberra(self):
metric = distance_metric(type_metric.CANBERRA)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[0.0, 1.0], [0.0, 0.0], [1.0, 1.0], [1.0, 0.0]], [30, 30], False, metric=metric)
def testClusterAllocationSampleSimple5ChiSquare(self):
metric = distance_metric(type_metric.CHI_SQUARE)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[3.4, 2.6], [3.4, -3.2], [-3.4, -3.4], [-3.1, 3.3]], [15, 15, 15, 15], False, metric=metric)
def testClusterOneDimensionSampleSimple7(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE7, [[-3.0], [2.0]], [10, 10], False)
def testClusterAllocationSampleSimple7Canberra(self):
metric = distance_metric(type_metric.CANBERRA)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE7, [[-3.0], [2.0]], [10, 10], False, metric=metric)
def testClusterAllocationSampleSimple7ChiSquare(self):
metric = distance_metric(type_metric.CHI_SQUARE)
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE7, [[-3.0], [2.0]], [10, 10], False, metric=metric)
def testClusterOneDimensionSampleSimple8(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE8, [[-4.0], [3.1], [6.1], [12.0]], [15, 30, 20, 80], False)
def testWrongNumberOfCentersSimpleSample1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[2.0, 4.5], [3.3, 6.5], [5.0, 7.8]], None, False)
def testWrongNumberOfCentersSimpleSample2(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[1.3, 1.5], [5.2, 8.5], [5.0, 7.8], [11.0, -3.0]], None, False)
def testWrongNumberOfCentersSimpleSample3(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, [[4.5, 3.4], [-1.7, 4.3], [1.5, 1.0], [11.3, 1.2], [-4.6, -5.2]], None, False)
def testWrongNumberOfCentersSimpleSample4(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE4, [[2.4, -1.4], [-5.2, -8.5], [-5.0, 3.1], [6.2, 1.4], [7.9, 2.4]], None, False)
def testWrongNumberOfCentersSimpleSample5(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE5, [[-1.9, 3.2], [1.2, 34.5], [15.2, 34.8], [192, 234], [-32.3, -106]], None, False)
def testTheSameData1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE9, [ [4.0], [8.0] ], [10, 20], False)
def testTheSameData2(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE12, [ [1.0, 1.0], [2.5, 2.5], [4.0, 4.0] ], [5, 5, 5], False)
def testOneDimensionalData1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE8, [[-2.0], [3.0], [6.0], [12.0]], [15, 30, 20, 80], False)
def testOneDimensionalData2(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE9, [[4.5], [6.2]], [20, 10], False)
def testThreeDimensionalData1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE11, [[1.0, 0.6, 0.8], [4.1, 4.2, 4.3]], [10, 10], False)
def testDifferentDimensions(self):
kmeans_instance = kmeans([ [0, 1, 5], [0, 2, 3] ], [ [0, 3] ], ccore=False)
self.assertRaises(ValueError, kmeans_instance.process)
def testClusterAllocationOneDimensionData(self):
KmeansTestTemplates.templateClusterAllocationOneDimensionData(False)
def testPredictOnePoint(self):
centers = [[0.2, 0.1], [4.0, 1.0], [2.0, 2.0], [2.3, 3.9]]
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[0.3, 0.2]], [0], False)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[4.1, 1.1]], [1], False)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[2.1, 1.9]], [2], False)
KmeansTestTemplates.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))
KmeansTestTemplates.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]]
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, [[0.3, 0.2], [2.1, 1.9]], [0, 2], False)
KmeansTestTemplates.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))
KmeansTestTemplates.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]]
KmeansTestTemplates.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]]
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False)
def testPredictFivePointsEuclideanDistance(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.EUCLIDEAN)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsEuclideanSquareDistance(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.EUCLIDEAN_SQUARE)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsManhattanDistance(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.MANHATTAN)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsChebyshevDistance(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.CHEBYSHEV)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsMinkowski2Distance(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.MINKOWSKI, degree=2)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsMinkowski4Distance(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.MINKOWSKI, degree=4)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsCanberraDistance(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.CANBERRA)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsChiSquareDistance(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.CHI_SQUARE)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testPredictFivePointsGowerDistance(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.GOWER, data=centers+to_predict)
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
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))
KmeansTestTemplates.templatePredict(SIMPLE_SAMPLES.SAMPLE_SIMPLE3, centers, to_predict, [0, 1, 1, 2, 3], False, metric=metric)
def testObserveSampleSimple1(self):
KmeansTestTemplates.templateCollectEvolution(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.5, 5.6], [6.8, 7.4]], [5, 5], False)
def testObserveSampleSimple1OneCluster(self):
KmeansTestTemplates.templateCollectEvolution(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.3, 5.4]], [10], False)
def testObserveSampleSimple2(self):
KmeansTestTemplates.templateCollectEvolution(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.4, 4.9], [6.8, 7.1], [7.6, 0.4]], [10, 5, 8], False)
def testItermax0(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [], False, itermax=0)
def testItermax1(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, itermax=1)
def testItermax10Simple01(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.7, 5.5], [6.7, 7.5]], [5, 5], False, itermax=10)
def testItermax10Simple02(self):
KmeansTestTemplates.templateLengthProcessData(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.5, 4.8], [6.9, 7], [7.5, 0.5]], [10, 5, 8], False, itermax=10)
def testEncoderProcedureSampleSimple4(self):
KmeansTestTemplates.templateEncoderProcedures(SIMPLE_SAMPLES.SAMPLE_SIMPLE4, [[1.5, 0.0], [1.5, 2.0], [1.5, 4.0], [1.5, 6.0], [1.5, 8.0]], 5, False)
def testShowResultsSampleSimple01(self):
KmeansTestTemplates.templateShowClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.5, 5.6], [6.8, 7.4]], False)
def testShowResultsSampleSimple02(self):
KmeansTestTemplates.templateShowClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.4, 4.9], [6.8, 7.1], [7.6, 0.4]], False)
def testShowResultsOneDimensionalData(self):
KmeansTestTemplates.templateShowClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE8, [[-2.0], [3.0], [6.0], [12.0]], False)
def testShowResultsThreeDimensionalData(self):
KmeansTestTemplates.templateShowClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE11, [[1.0, 0.6, 0.8], [4.1, 4.2, 4.3]], False)
def testAnimateResultsSampleSimple01(self):
KmeansTestTemplates.templateAnimateClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE1, [[3.5, 5.6], [6.8, 7.4]], False)
def testAnimateResultsSampleSimple02(self):
KmeansTestTemplates.templateAnimateClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE2, [[3.4, 4.9], [6.8, 7.1], [7.6, 0.4]], False)
def testAnimateResultsOneDimensionalData(self):
KmeansTestTemplates.templateAnimateClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE8, [[-2.0], [3.0], [6.0], [12.0]], False)
def testAnimateResultsThreeDimensionalData(self):
KmeansTestTemplates.templateAnimateClusteringResultNoFailure(SIMPLE_SAMPLES.SAMPLE_SIMPLE11, [[1.0, 0.6, 0.8], [4.1, 4.2, 4.3]], False)
def test_incorrect_data(self):
self.assertRaises(ValueError, kmeans, [], [[1]])
def test_incorrect_centers(self):
self.assertRaises(ValueError, kmeans, [[0], [1], [2]], [])
def test_incorrect_tolerance(self):
self.assertRaises(ValueError, kmeans, [[0], [1], [2]], [[1]], -1.0)
def test_incorrect_itermax(self):
self.assertRaises(ValueError, kmeans, [[0], [1], [2]], [[1]], itermax=-5)
|
