|
1
|
|
|
# Copyright 2019-2020 by Christopher C. Little. |
|
2
|
|
|
# This file is part of Abydos. |
|
3
|
|
|
# |
|
4
|
|
|
# Abydos is free software: you can redistribute it and/or modify |
|
5
|
|
|
# it under the terms of the GNU General Public License as published by |
|
6
|
|
|
# the Free Software Foundation, either version 3 of the License, or |
|
7
|
|
|
# (at your option) any later version. |
|
8
|
|
|
# |
|
9
|
|
|
# Abydos is distributed in the hope that it will be useful, |
|
10
|
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
11
|
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
12
|
|
|
# GNU General Public License for more details. |
|
13
|
|
|
# |
|
14
|
|
|
# You should have received a copy of the GNU General Public License |
|
15
|
|
|
# along with Abydos. If not, see <http://www.gnu.org/licenses/>. |
|
16
|
|
|
|
|
17
|
|
|
"""abydos.distance._fuzzywuzzy_partial_string. |
|
18
|
|
|
|
|
19
|
1 |
|
FuzzyWuzzy Partial String similarity |
|
20
|
|
|
""" |
|
21
|
|
|
|
|
22
|
|
|
from difflib import SequenceMatcher |
|
23
|
|
|
|
|
24
|
1 |
|
from ._distance import _Distance |
|
25
|
|
|
|
|
26
|
|
|
__all__ = ['FuzzyWuzzyPartialString'] |
|
27
|
|
|
|
|
28
|
|
|
|
|
29
|
|
|
class FuzzyWuzzyPartialString(_Distance): |
|
30
|
|
|
"""FuzzyWuzzy Partial String similarity. |
|
31
|
1 |
|
|
|
32
|
|
|
This follows the FuzzyWuzzy Partial String similarity algorithm |
|
33
|
1 |
|
:cite:`Cohen:2011`. Rather than returning an integer in the range [0, 100], |
|
34
|
|
|
as demonstrated in the blog post, this implementation returns a float in |
|
35
|
1 |
|
the range [0.0, 1.0]. |
|
36
|
|
|
|
|
37
|
|
|
.. versionadded:: 0.4.0 |
|
38
|
1 |
|
""" |
|
39
|
|
|
|
|
40
|
|
|
def sim(self, src: str, tar: str) -> float: |
|
41
|
|
|
"""Return the FuzzyWuzzy Partial String similarity of two strings. |
|
42
|
|
|
|
|
43
|
|
|
Parameters |
|
44
|
|
|
---------- |
|
45
|
|
|
src : str |
|
46
|
|
|
Source string for comparison |
|
47
|
|
|
tar : str |
|
48
|
|
|
Target string for comparison |
|
49
|
1 |
|
|
|
50
|
|
|
Returns |
|
51
|
|
|
------- |
|
52
|
|
|
float |
|
53
|
|
|
FuzzyWuzzy Partial String similarity |
|
54
|
|
|
|
|
55
|
|
|
Examples |
|
56
|
|
|
-------- |
|
57
|
|
|
>>> cmp = FuzzyWuzzyPartialString() |
|
58
|
|
|
>>> round(cmp.sim('cat', 'hat'), 12) |
|
59
|
|
|
0.666666666667 |
|
60
|
|
|
>>> round(cmp.sim('Niall', 'Neil'), 12) |
|
61
|
|
|
0.75 |
|
62
|
|
|
>>> round(cmp.sim('aluminum', 'Catalan'), 12) |
|
63
|
|
|
0.428571428571 |
|
64
|
|
|
>>> cmp.sim('ATCG', 'TAGC') |
|
65
|
|
|
0.5 |
|
66
|
|
|
|
|
67
|
|
|
|
|
68
|
|
|
.. versionadded:: 0.4.0 |
|
69
|
|
|
|
|
70
|
|
|
""" |
|
71
|
|
|
max_sim = 0.0 |
|
72
|
|
|
start_pos = 0 |
|
73
|
|
|
|
|
74
|
|
|
if len(src) > len(tar): |
|
75
|
|
|
src, tar = tar, src |
|
76
|
|
|
|
|
77
|
|
|
src_len = len(src) |
|
78
|
|
|
|
|
79
|
|
|
while max_sim < 1.0 and start_pos < len(tar) - src_len + 1: |
|
80
|
1 |
|
max_sim = max( |
|
81
|
1 |
|
max_sim, |
|
82
|
|
|
SequenceMatcher( |
|
83
|
1 |
|
None, src, tar[start_pos : start_pos + src_len] |
|
84
|
1 |
|
).ratio(), |
|
85
|
|
|
) |
|
86
|
1 |
|
start_pos += 1 |
|
87
|
|
|
|
|
88
|
1 |
|
return max_sim |
|
89
|
1 |
|
|
|
90
|
|
|
|
|
91
|
|
|
if __name__ == '__main__': |
|
92
|
|
|
import doctest |
|
93
|
|
|
|
|
94
|
|
|
doctest.testmod() |
|
95
|
|
|
|
chrislit /
abydos
