|
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._lig3. |
|
20
|
|
|
|
|
21
|
|
|
LIG3 similarity |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from ._distance import _Distance |
|
32
|
1 |
|
from ._levenshtein import Levenshtein |
|
33
|
|
|
|
|
34
|
1 |
|
__all__ = ['LIG3'] |
|
35
|
|
|
|
|
36
|
|
|
|
|
37
|
1 |
|
class LIG3(_Distance): |
|
38
|
|
|
r"""LIG3 similarity. |
|
39
|
|
|
|
|
40
|
|
|
:cite:`Snae:2002` proposes three Levenshtein-ISG-Guth hybrid similarity |
|
41
|
|
|
measures: LIG1, LIG2, and LIG3. Of these, LIG1 is identical to ISG and LIG2 |
|
42
|
|
|
is identical to normalized Levenshtein similarity. Only LIG3 is a novel |
|
43
|
|
|
measure, defined as: |
|
44
|
|
|
|
|
45
|
|
|
.. math:: |
|
46
|
|
|
|
|
47
|
|
|
sim_{LIG3}(X, Y) = \frac{2I}{2I+C} |
|
48
|
|
|
|
|
49
|
|
|
Here, I is the number of exact matches between the two words, truncated to |
|
50
|
|
|
the length of the shorter word, and C is the Levenshtein distance between |
|
51
|
|
|
the two words. |
|
52
|
|
|
|
|
53
|
|
|
.. versionadded:: 0.4.1 |
|
54
|
|
|
""" |
|
55
|
|
|
|
|
56
|
1 |
|
_lev = Levenshtein() |
|
57
|
|
|
|
|
58
|
1 |
|
def sim(self, src, tar): |
|
59
|
|
|
"""Return the LIG3 similarity of two words. |
|
60
|
|
|
|
|
61
|
|
|
Parameters |
|
62
|
|
|
---------- |
|
63
|
|
|
src : str |
|
64
|
|
|
Source string for comparison |
|
65
|
|
|
tar : str |
|
66
|
|
|
Target string for comparison |
|
67
|
|
|
|
|
68
|
|
|
Returns |
|
69
|
|
|
------- |
|
70
|
|
|
float |
|
71
|
|
|
The LIG3 similarity |
|
72
|
|
|
|
|
73
|
|
|
Examples |
|
74
|
|
|
-------- |
|
75
|
|
|
>>> cmp = LIG3() |
|
76
|
|
|
>>> cmp.sim('cat', 'hat') |
|
77
|
|
|
0.8 |
|
78
|
|
|
>>> cmp.sim('Niall', 'Neil') |
|
79
|
|
|
0.5714285714285714 |
|
80
|
|
|
>>> cmp.sim('aluminum', 'Catalan') |
|
81
|
|
|
0.0 |
|
82
|
|
|
>>> cmp.sim('ATCG', 'TAGC') |
|
83
|
|
|
0.0 |
|
84
|
|
|
|
|
85
|
|
|
|
|
86
|
|
|
.. versionadded:: 0.4.1 |
|
87
|
|
|
|
|
88
|
|
|
""" |
|
89
|
1 |
|
if src == tar: |
|
90
|
1 |
|
return 1.0 |
|
91
|
|
|
|
|
92
|
1 |
|
matches = 2 * sum( |
|
93
|
|
|
src[pos] == tar[pos] for pos in range(min(len(src), len(tar))) |
|
94
|
|
|
) |
|
95
|
1 |
|
cost = self._lev.dist_abs(src, tar) |
|
96
|
|
|
|
|
97
|
1 |
|
return matches / (matches + cost) |
|
98
|
|
|
|
|
99
|
|
|
|
|
100
|
|
|
if __name__ == '__main__': |
|
101
|
|
|
import doctest |
|
102
|
|
|
|
|
103
|
|
|
doctest.testmod() |
|
104
|
|
|
|
chrislit /
abydos
