|
1
|
|
|
# -*- coding: utf-8 -*- |
|
2
|
|
|
|
|
3
|
|
|
# Copyright 2019 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
|
1 |
|
"""abydos.distance._vps. |
|
20
|
|
|
|
|
21
|
|
|
Victorian Panel Study (VPS) score |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from collections import defaultdict |
|
32
|
|
|
|
|
33
|
1 |
|
from ._distance import _Distance |
|
34
|
|
|
|
|
35
|
1 |
|
__all__ = ['VPS'] |
|
36
|
|
|
|
|
37
|
|
|
|
|
38
|
1 |
|
class VPS(_Distance): |
|
39
|
|
|
"""Victorian Panel Study (VPS) score. |
|
40
|
|
|
|
|
41
|
|
|
VPS score is presented in :cite:`Shurer:2007`. |
|
42
|
|
|
|
|
43
|
|
|
.. versionadded:: 0.4.1 |
|
44
|
|
|
""" |
|
45
|
|
|
|
|
46
|
1 |
|
def sim(self, src, tar): |
|
47
|
|
|
"""Return the Victorian Panel Study score of two words. |
|
48
|
|
|
|
|
49
|
|
|
Parameters |
|
50
|
|
|
---------- |
|
51
|
|
|
src : str |
|
52
|
|
|
Source string for comparison |
|
53
|
|
|
tar : str |
|
54
|
|
|
Target string for comparison |
|
55
|
|
|
|
|
56
|
|
|
Returns |
|
57
|
|
|
------- |
|
58
|
|
|
float |
|
59
|
|
|
The VPS score |
|
60
|
|
|
|
|
61
|
|
|
Examples |
|
62
|
|
|
-------- |
|
63
|
|
|
>>> cmp = VPS() |
|
64
|
|
|
>>> cmp.sim('cat', 'hat') |
|
65
|
|
|
0.5 |
|
66
|
|
|
>>> cmp.sim('Niall', 'Neil') |
|
67
|
|
|
0.3 |
|
68
|
|
|
>>> cmp.sim('aluminum', 'Catalan') |
|
69
|
|
|
0.14285714285714285 |
|
70
|
|
|
>>> cmp.sim('ATCG', 'TAGC') |
|
71
|
|
|
0.3333333333333333 |
|
72
|
|
|
|
|
73
|
|
|
|
|
74
|
|
|
.. versionadded:: 0.4.1 |
|
75
|
|
|
|
|
76
|
|
|
""" |
|
77
|
1 |
|
if src == tar: |
|
78
|
1 |
|
return 1.0 |
|
79
|
1 |
|
if len(src) < len(tar): |
|
80
|
1 |
|
src, tar = tar, src |
|
81
|
|
|
|
|
82
|
1 |
|
score = 0 |
|
83
|
1 |
|
discount = 0 |
|
84
|
|
|
|
|
85
|
1 |
|
src_tokens = defaultdict(set) |
|
86
|
1 |
|
tar_tokens = defaultdict(set) |
|
87
|
1 |
|
for slen in range(1, 4): |
|
88
|
1 |
|
for i in range(len(src) - slen + 1): |
|
89
|
1 |
|
src_tokens[src[i : i + slen]].add(i) |
|
90
|
1 |
|
for i in range(len(tar) - slen + 1): |
|
91
|
1 |
|
tar_tokens[tar[i : i + slen]].add(i) |
|
92
|
|
|
|
|
93
|
1 |
|
for token in src_tokens.keys(): |
|
94
|
1 |
|
if token in tar_tokens: |
|
95
|
1 |
|
for src_pos in src_tokens[token]: |
|
96
|
1 |
|
score += 1 |
|
97
|
1 |
|
if src_pos not in tar_tokens[token]: |
|
98
|
1 |
|
discount += min( |
|
99
|
|
|
abs(src_pos - tar_pos) |
|
100
|
|
|
for tar_pos in tar_tokens[token] |
|
101
|
|
|
) |
|
102
|
|
|
|
|
103
|
1 |
|
score -= discount / max(len(src), len(tar)) |
|
104
|
1 |
|
if score: |
|
105
|
1 |
|
score /= 3 * len(src) - 3 |
|
106
|
|
|
|
|
107
|
1 |
|
return score |
|
108
|
|
|
|
|
109
|
|
|
|
|
110
|
|
|
if __name__ == '__main__': |
|
111
|
|
|
import doctest |
|
112
|
|
|
|
|
113
|
|
|
doctest.testmod() |
|
114
|
|
|
|
chrislit /
abydos
