|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Copyright 2014-2018 by Christopher C. Little. |
|
4
|
|
|
# This file is part of Abydos. |
|
5
|
|
|
# |
|
6
|
|
|
# Abydos is free software: you can redistribute it and/or modify |
|
7
|
|
|
# it under the terms of the GNU General Public License as published by |
|
8
|
|
|
# the Free Software Foundation, either version 3 of the License, or |
|
9
|
|
|
# (at your option) any later version. |
|
10
|
|
|
# |
|
11
|
|
|
# Abydos is distributed in the hope that it will be useful, |
|
12
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
13
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
14
|
|
|
# GNU General Public License for more details. |
|
15
|
|
|
# |
|
16
|
|
|
# You should have received a copy of the GNU General Public License |
|
17
|
|
|
# along with Abydos. If not, see <http://www.gnu.org/licenses/>. |
|
18
|
|
|
|
|
19
|
|
|
"""abydos.tests.test_clustering. |
|
20
|
|
|
|
|
21
|
|
|
This module contains unit tests for abydos.clustering |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
|
|
from __future__ import unicode_literals |
|
25
|
|
|
|
|
26
|
|
|
import unittest |
|
27
|
|
|
|
|
28
|
|
|
import abydos.stats as stats |
|
29
|
|
|
from abydos.clustering import mean_pairwise_similarity |
|
30
|
|
|
|
|
31
|
|
|
|
|
32
|
|
|
NIALL = ('Niall', 'Neal', 'Neil', 'Njall', 'Njáll', 'Nigel', 'Neel', 'Nele', |
|
33
|
|
|
'Nigelli', 'Nel', 'Kneale', 'Uí Néill', 'O\'Neill', 'MacNeil', |
|
34
|
|
|
'MacNele', 'Niall Noígíallach') |
|
35
|
|
|
|
|
36
|
|
|
NIALL_1WORD = ('Niall', 'Neal', 'Neil', 'Njall', 'Njáll', 'Nigel', 'Neel', |
|
37
|
|
|
'Nele', 'Nigelli', 'Nel', 'Kneale', 'O\'Neill', 'MacNeil', |
|
38
|
|
|
'MacNele') |
|
39
|
|
|
|
|
40
|
|
|
|
|
41
|
|
|
class MPSTestCases(unittest.TestCase): |
|
42
|
|
|
"""Test mean pairwise similarity functions. |
|
43
|
|
|
|
|
44
|
|
|
abydos.clustering.mean_pairwise_similarity |
|
45
|
|
|
""" |
|
46
|
|
|
|
|
47
|
|
|
def test_mean_pairwise_similarity(self): |
|
48
|
|
|
"""Test abydos.clustering.mean_pairwise_similarity.""" |
|
49
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL), 0.29362587170180671) |
|
50
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, symmetric=True), |
|
51
|
|
|
0.2936258717018066) |
|
52
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, meanfunc=stats.hmean), |
|
53
|
|
|
0.29362587170180671) |
|
54
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, meanfunc=stats.hmean, |
|
55
|
|
|
symmetric=True), |
|
56
|
|
|
0.2936258717018066) |
|
57
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, meanfunc=stats.gmean), |
|
58
|
|
|
0.33747245800668441) |
|
59
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, meanfunc=stats.gmean, |
|
60
|
|
|
symmetric=True), |
|
61
|
|
|
0.33747245800668441) |
|
62
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, meanfunc=stats.amean), |
|
63
|
|
|
0.38009278711484601) |
|
64
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, meanfunc=stats.amean, |
|
65
|
|
|
symmetric=True), |
|
66
|
|
|
0.38009278711484623) |
|
67
|
|
|
|
|
68
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD), |
|
69
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD))) |
|
70
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD, symmetric=True), |
|
71
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD), |
|
72
|
|
|
symmetric=True)) |
|
73
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD, |
|
74
|
|
|
meanfunc=stats.gmean), |
|
75
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD), |
|
76
|
|
|
meanfunc=stats.gmean)) |
|
77
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD, |
|
78
|
|
|
meanfunc=stats.amean), |
|
79
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD), |
|
80
|
|
|
meanfunc=stats.amean)) |
|
81
|
|
|
|
|
82
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, ['a b c']) |
|
83
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, 'abc') |
|
84
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, 0) |
|
85
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, NIALL, |
|
86
|
|
|
meanfunc='imaginary') |
|
87
|
|
|
|
|
88
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL), |
|
89
|
|
|
mean_pairwise_similarity(tuple(NIALL))) |
|
90
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL), |
|
91
|
|
|
mean_pairwise_similarity(list(NIALL))) |
|
92
|
|
|
self.assertAlmostEqual(mean_pairwise_similarity(NIALL), |
|
93
|
|
|
mean_pairwise_similarity(sorted(NIALL))) |
|
94
|
|
|
self.assertAlmostEqual(mean_pairwise_similarity(NIALL), |
|
95
|
|
|
mean_pairwise_similarity(set(NIALL))) |
|
96
|
|
|
|
|
97
|
|
|
|
|
98
|
|
|
if __name__ == '__main__': |
|
99
|
|
|
unittest.main() |
|
100
|
|
|
|
chrislit /
abydos
