|
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
|
|
|
from abydos.distance.token import sim_tanimoto |
|
29
|
|
|
from abydos.stats.mean import amean, gmean, hmean |
|
30
|
|
|
from abydos.stats.pairwise import mean_pairwise_similarity, \ |
|
31
|
|
|
pairwise_similarity_statistics |
|
32
|
|
|
|
|
33
|
|
|
NIALL = ('Niall', 'Neal', 'Neil', 'Njall', 'Njáll', 'Nigel', 'Neel', 'Nele', |
|
34
|
|
|
'Nigelli', 'Nel', 'Kneale', 'Uí Néill', 'O\'Neill', 'MacNeil', |
|
35
|
|
|
'MacNele', 'Niall Noígíallach') |
|
36
|
|
|
|
|
37
|
|
|
NIALL_1WORD = ('Niall', 'Neal', 'Neil', 'Njall', 'Njáll', 'Nigel', 'Neel', |
|
38
|
|
|
'Nele', 'Nigelli', 'Nel', 'Kneale', 'O\'Neill', 'MacNeil', |
|
39
|
|
|
'MacNele') |
|
40
|
|
|
|
|
41
|
|
|
|
|
42
|
|
|
class MPSTestCases(unittest.TestCase): |
|
43
|
|
|
"""Test mean pairwise similarity functions. |
|
44
|
|
|
|
|
45
|
|
|
abydos.stats.pairwise.mean_pairwise_similarity |
|
46
|
|
|
""" |
|
47
|
|
|
|
|
48
|
|
|
def test_mean_pairwise_similarity(self): |
|
49
|
|
|
"""Test abydos.stats.pairwise.mean_pairwise_similarity.""" |
|
50
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL), 0.29362587170180671) |
|
51
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, symmetric=True), |
|
52
|
|
|
0.2936258717018066) |
|
53
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, mean_func=hmean), |
|
54
|
|
|
0.29362587170180671) |
|
55
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, mean_func=hmean, |
|
56
|
|
|
symmetric=True), |
|
57
|
|
|
0.2936258717018066) |
|
58
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, |
|
59
|
|
|
mean_func=gmean), |
|
60
|
|
|
0.33747245800668441) |
|
61
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, mean_func=gmean, |
|
62
|
|
|
symmetric=True), |
|
63
|
|
|
0.33747245800668441) |
|
64
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, |
|
65
|
|
|
mean_func=amean), |
|
66
|
|
|
0.38009278711484601) |
|
67
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL, mean_func=amean, |
|
68
|
|
|
symmetric=True), |
|
69
|
|
|
0.38009278711484623) |
|
70
|
|
|
|
|
71
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD), |
|
72
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD))) |
|
73
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD, symmetric=True), |
|
74
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD), |
|
75
|
|
|
symmetric=True)) |
|
76
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD, |
|
77
|
|
|
mean_func=gmean), |
|
78
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD), |
|
79
|
|
|
mean_func=gmean)) |
|
80
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL_1WORD, |
|
81
|
|
|
mean_func=amean), |
|
82
|
|
|
mean_pairwise_similarity(' '.join(NIALL_1WORD), |
|
83
|
|
|
mean_func=amean)) |
|
84
|
|
|
|
|
85
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, ['a b c']) |
|
86
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, 'abc') |
|
87
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, 0) |
|
88
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, NIALL, |
|
89
|
|
|
mean_func='imaginary') |
|
90
|
|
|
self.assertRaises(ValueError, mean_pairwise_similarity, NIALL, |
|
91
|
|
|
metric='imaginary') |
|
92
|
|
|
|
|
93
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL), |
|
94
|
|
|
mean_pairwise_similarity(tuple(NIALL))) |
|
95
|
|
|
self.assertEqual(mean_pairwise_similarity(NIALL), |
|
96
|
|
|
mean_pairwise_similarity(list(NIALL))) |
|
97
|
|
|
self.assertAlmostEqual(mean_pairwise_similarity(NIALL), |
|
98
|
|
|
mean_pairwise_similarity(sorted(NIALL))) |
|
99
|
|
|
self.assertAlmostEqual(mean_pairwise_similarity(NIALL), |
|
100
|
|
|
mean_pairwise_similarity(set(NIALL))) |
|
101
|
|
|
|
|
102
|
|
|
|
|
103
|
|
|
class PSSTestCases(unittest.TestCase): |
|
104
|
|
|
"""Test pairwise similarity statistics functions. |
|
105
|
|
|
|
|
106
|
|
|
abydos.stats.pairwise.pairwise_similarity_statistics |
|
107
|
|
|
""" |
|
108
|
|
|
|
|
109
|
|
|
def test_pairwise_similarity_statistics(self): |
|
110
|
|
|
"""Test abydos.stats.pairwise.pairwise_similarity_statistics.""" |
|
111
|
|
|
(pw_max, pw_min, pw_mean, |
|
112
|
|
|
pw_std) = pairwise_similarity_statistics(NIALL, NIALL) |
|
113
|
|
|
self.assertAlmostEqual(pw_max, 1.0) |
|
114
|
|
|
self.assertAlmostEqual(pw_min, 0.11764705882352944) |
|
115
|
|
|
self.assertAlmostEqual(pw_mean, 0.4188369879201684) |
|
116
|
|
|
self.assertAlmostEqual(pw_std, 0.2265099631340623) |
|
117
|
|
|
|
|
118
|
|
|
(pw_max, pw_min, pw_mean, |
|
119
|
|
|
pw_std) = pairwise_similarity_statistics(NIALL, ('Kneal',)) |
|
120
|
|
|
self.assertAlmostEqual(pw_max, 0.8333333333333334) |
|
121
|
|
|
self.assertAlmostEqual(pw_min, 0.11764705882352944) |
|
122
|
|
|
self.assertAlmostEqual(pw_mean, 0.30474877450980387) |
|
123
|
|
|
self.assertAlmostEqual(pw_std, 0.1842666797571549) |
|
124
|
|
|
|
|
125
|
|
|
# Test symmetric |
|
126
|
|
|
(pw_max, pw_min, pw_mean, |
|
127
|
|
|
pw_std) = pairwise_similarity_statistics(NIALL, NIALL, symmetric=True) |
|
128
|
|
|
self.assertAlmostEqual(pw_max, 1.0) |
|
129
|
|
|
self.assertAlmostEqual(pw_min, 0.11764705882352944) |
|
130
|
|
|
self.assertAlmostEqual(pw_mean, 0.4188369879201679) |
|
131
|
|
|
self.assertAlmostEqual(pw_std, 0.22650996313406255) |
|
132
|
|
|
|
|
133
|
|
|
(pw_max, pw_min, pw_mean, |
|
134
|
|
|
pw_std) = pairwise_similarity_statistics(NIALL, ('Kneal',), |
|
135
|
|
|
symmetric=True) |
|
136
|
|
|
self.assertAlmostEqual(pw_max, 0.8333333333333334) |
|
137
|
|
|
self.assertAlmostEqual(pw_min, 0.11764705882352944) |
|
138
|
|
|
self.assertAlmostEqual(pw_mean, 0.304748774509804) |
|
139
|
|
|
self.assertAlmostEqual(pw_std, 0.18426667975715486) |
|
140
|
|
|
|
|
141
|
|
|
# Test with splittable strings |
|
142
|
|
|
(pw_max, pw_min, pw_mean, |
|
143
|
|
|
pw_std) = pairwise_similarity_statistics('The quick brown fox', |
|
144
|
|
|
'jumped over the lazy dog.') |
|
145
|
|
|
self.assertAlmostEqual(pw_max, 0.6666666666666667) |
|
146
|
|
|
self.assertAlmostEqual(pw_min, 0.0) |
|
147
|
|
|
self.assertAlmostEqual(pw_mean, 0.08499999999999999) |
|
148
|
|
|
self.assertAlmostEqual(pw_std, 0.16132265804901677) |
|
149
|
|
|
|
|
150
|
|
|
(pw_max, pw_min, pw_mean, |
|
151
|
|
|
pw_std) = pairwise_similarity_statistics('The', 'jumped') |
|
152
|
|
|
self.assertAlmostEqual(pw_max, 0.16666666666666663) |
|
153
|
|
|
self.assertAlmostEqual(pw_min, 0.16666666666666663) |
|
154
|
|
|
self.assertAlmostEqual(pw_mean, 0.16666666666666663) |
|
155
|
|
|
self.assertAlmostEqual(pw_std, 0.0) |
|
156
|
|
|
|
|
157
|
|
|
# Test with a set metric |
|
158
|
|
|
(pw_max, pw_min, pw_mean, |
|
159
|
|
|
pw_std) = pairwise_similarity_statistics(NIALL, NIALL, |
|
160
|
|
|
metric=sim_tanimoto) |
|
161
|
|
|
self.assertAlmostEqual(pw_max, 1.0) |
|
162
|
|
|
self.assertAlmostEqual(pw_min, 0.0) |
|
163
|
|
|
self.assertAlmostEqual(pw_mean, 0.23226906681010506) |
|
164
|
|
|
self.assertAlmostEqual(pw_std, 0.24747101181262784) |
|
165
|
|
|
|
|
166
|
|
|
# Test using hmean' |
|
167
|
|
|
(pw_max, pw_min, pw_mean, |
|
168
|
|
|
pw_std) = pairwise_similarity_statistics(NIALL, NIALL, |
|
169
|
|
|
mean_func=hmean) |
|
170
|
|
|
self.assertAlmostEqual(pw_max, 1.0) |
|
171
|
|
|
self.assertAlmostEqual(pw_min, 0.11764705882352944) |
|
172
|
|
|
self.assertAlmostEqual(pw_mean, 0.30718771249150056) |
|
173
|
|
|
self.assertAlmostEqual(pw_std, 0.25253182790044676) |
|
174
|
|
|
|
|
175
|
|
|
# Test exceptions |
|
176
|
|
|
self.assertRaises(ValueError, pairwise_similarity_statistics, NIALL, |
|
177
|
|
|
NIALL, mean_func=None) |
|
178
|
|
|
self.assertRaises(ValueError, pairwise_similarity_statistics, NIALL, |
|
179
|
|
|
NIALL, metric=None) |
|
180
|
|
|
self.assertRaises(ValueError, pairwise_similarity_statistics, 5, NIALL) |
|
181
|
|
|
self.assertRaises(ValueError, pairwise_similarity_statistics, NIALL, 5) |
|
182
|
|
|
|
|
183
|
|
|
|
|
184
|
|
|
if __name__ == '__main__': |
|
185
|
|
|
unittest.main() |
|
186
|
|
|
|
chrislit /
abydos
