|
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
|
1 |
|
"""abydos.distance._mra. |
|
20
|
|
|
|
|
21
|
|
|
The Match Rating Algorithm's distance measure |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from six.moves import range |
|
32
|
|
|
|
|
33
|
1 |
|
from ._distance import _Distance |
|
34
|
1 |
|
from ..phonetic import mra |
|
35
|
|
|
|
|
36
|
1 |
|
__all__ = ['MRA', 'dist_mra', 'mra_compare', 'sim_mra'] |
|
37
|
|
|
|
|
38
|
|
|
|
|
39
|
1 |
|
class MRA(_Distance): |
|
|
|
|
|
|
40
|
|
|
"""Match Rating Algorithm comparison rating. |
|
41
|
|
|
|
|
42
|
|
|
The Western Airlines Surname Match Rating Algorithm comparison rating, as |
|
43
|
|
|
presented on page 18 of :cite:`Moore:1977`. |
|
44
|
|
|
""" |
|
45
|
|
|
|
|
46
|
1 |
|
def dist_abs(self, src, tar): |
|
|
|
|
|
|
47
|
|
|
"""Return the MRA comparison rating of two strings. |
|
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
|
|
|
int |
|
59
|
|
|
MRA comparison rating |
|
60
|
|
|
|
|
61
|
|
|
Examples |
|
62
|
|
|
-------- |
|
63
|
|
|
>>> cmp = MRA() |
|
64
|
|
|
>>> cmp.dist_abs('cat', 'hat') |
|
65
|
|
|
5 |
|
66
|
|
|
>>> cmp.dist_abs('Niall', 'Neil') |
|
67
|
|
|
6 |
|
68
|
|
|
>>> cmp.dist_abs('aluminum', 'Catalan') |
|
69
|
|
|
0 |
|
70
|
|
|
>>> cmp.dist_abs('ATCG', 'TAGC') |
|
71
|
|
|
5 |
|
72
|
|
|
|
|
73
|
|
|
""" |
|
74
|
1 |
|
if src == tar: |
|
75
|
1 |
|
return 6 |
|
76
|
1 |
|
if src == '' or tar == '': |
|
77
|
1 |
|
return 0 |
|
78
|
1 |
|
src = list(mra(src)) |
|
79
|
1 |
|
tar = list(mra(tar)) |
|
80
|
|
|
|
|
81
|
1 |
|
if abs(len(src) - len(tar)) > 2: |
|
82
|
1 |
|
return 0 |
|
83
|
|
|
|
|
84
|
1 |
|
length_sum = len(src) + len(tar) |
|
85
|
1 |
|
if length_sum < 5: |
|
86
|
1 |
|
min_rating = 5 |
|
87
|
1 |
|
elif length_sum < 8: |
|
88
|
1 |
|
min_rating = 4 |
|
89
|
1 |
|
elif length_sum < 12: |
|
90
|
1 |
|
min_rating = 3 |
|
91
|
|
|
else: |
|
92
|
1 |
|
min_rating = 2 |
|
93
|
|
|
|
|
94
|
1 |
|
for _ in range(2): |
|
95
|
1 |
|
new_src = [] |
|
96
|
1 |
|
new_tar = [] |
|
97
|
1 |
|
minlen = min(len(src), len(tar)) |
|
98
|
1 |
|
for i in range(minlen): |
|
99
|
1 |
|
if src[i] != tar[i]: |
|
100
|
1 |
|
new_src.append(src[i]) |
|
101
|
1 |
|
new_tar.append(tar[i]) |
|
102
|
1 |
|
src = new_src + src[minlen:] |
|
103
|
1 |
|
tar = new_tar + tar[minlen:] |
|
104
|
1 |
|
src.reverse() |
|
105
|
1 |
|
tar.reverse() |
|
106
|
|
|
|
|
107
|
1 |
|
similarity = 6 - max(len(src), len(tar)) |
|
108
|
|
|
|
|
109
|
1 |
|
if similarity >= min_rating: |
|
110
|
1 |
|
return similarity |
|
111
|
1 |
|
return 0 |
|
112
|
|
|
|
|
113
|
1 |
|
def sim(self, src, tar): |
|
|
|
|
|
|
114
|
|
|
"""Return the normalized MRA similarity of two strings. |
|
115
|
|
|
|
|
116
|
|
|
This is the MRA normalized to :math:`[0, 1]`, given that MRA itself is |
|
117
|
|
|
constrained to the range :math:`[0, 6]`. |
|
118
|
|
|
|
|
119
|
|
|
Parameters |
|
120
|
|
|
---------- |
|
121
|
|
|
src : str |
|
122
|
|
|
Source string for comparison |
|
123
|
|
|
tar : str |
|
124
|
|
|
Target string for comparison |
|
125
|
|
|
|
|
126
|
|
|
Returns |
|
127
|
|
|
------- |
|
128
|
|
|
float |
|
129
|
|
|
Normalized MRA similarity |
|
130
|
|
|
|
|
131
|
|
|
Examples |
|
132
|
|
|
-------- |
|
133
|
|
|
>>> cmp = MRA() |
|
134
|
|
|
>>> cmp.sim('cat', 'hat') |
|
135
|
|
|
0.8333333333333334 |
|
136
|
|
|
>>> cmp.sim('Niall', 'Neil') |
|
137
|
|
|
1.0 |
|
138
|
|
|
>>> cmp.sim('aluminum', 'Catalan') |
|
139
|
|
|
0.0 |
|
140
|
|
|
>>> cmp.sim('ATCG', 'TAGC') |
|
141
|
|
|
0.8333333333333334 |
|
142
|
|
|
|
|
143
|
|
|
""" |
|
144
|
1 |
|
return mra_compare(src, tar) / 6 |
|
145
|
|
|
|
|
146
|
|
|
|
|
147
|
1 |
|
def mra_compare(src, tar): |
|
148
|
|
|
"""Return the MRA comparison rating of two strings. |
|
149
|
|
|
|
|
150
|
|
|
This is a wrapper for :py:meth:`MRA.dist_abs`. |
|
151
|
|
|
|
|
152
|
|
|
Parameters |
|
153
|
|
|
---------- |
|
154
|
|
|
src : str |
|
155
|
|
|
Source string for comparison |
|
156
|
|
|
tar : str |
|
157
|
|
|
Target string for comparison |
|
158
|
|
|
|
|
159
|
|
|
Returns |
|
160
|
|
|
------- |
|
161
|
|
|
int |
|
162
|
|
|
MRA comparison rating |
|
163
|
|
|
|
|
164
|
|
|
Examples |
|
165
|
|
|
-------- |
|
166
|
|
|
>>> mra_compare('cat', 'hat') |
|
167
|
|
|
5 |
|
168
|
|
|
>>> mra_compare('Niall', 'Neil') |
|
169
|
|
|
6 |
|
170
|
|
|
>>> mra_compare('aluminum', 'Catalan') |
|
171
|
|
|
0 |
|
172
|
|
|
>>> mra_compare('ATCG', 'TAGC') |
|
173
|
|
|
5 |
|
174
|
|
|
|
|
175
|
|
|
""" |
|
176
|
1 |
|
return MRA().dist_abs(src, tar) |
|
177
|
|
|
|
|
178
|
|
|
|
|
179
|
1 |
|
def sim_mra(src, tar): |
|
180
|
|
|
"""Return the normalized MRA similarity of two strings. |
|
181
|
|
|
|
|
182
|
|
|
This is a wrapper for :py:meth:`MRA.sim`. |
|
183
|
|
|
|
|
184
|
|
|
Parameters |
|
185
|
|
|
---------- |
|
186
|
|
|
src : str |
|
187
|
|
|
Source string for comparison |
|
188
|
|
|
tar : str |
|
189
|
|
|
Target string for comparison |
|
190
|
|
|
|
|
191
|
|
|
Returns |
|
192
|
|
|
------- |
|
193
|
|
|
float |
|
194
|
|
|
Normalized MRA similarity |
|
195
|
|
|
|
|
196
|
|
|
Examples |
|
197
|
|
|
-------- |
|
198
|
|
|
>>> sim_mra('cat', 'hat') |
|
199
|
|
|
0.8333333333333334 |
|
200
|
|
|
>>> sim_mra('Niall', 'Neil') |
|
201
|
|
|
1.0 |
|
202
|
|
|
>>> sim_mra('aluminum', 'Catalan') |
|
203
|
|
|
0.0 |
|
204
|
|
|
>>> sim_mra('ATCG', 'TAGC') |
|
205
|
|
|
0.8333333333333334 |
|
206
|
|
|
|
|
207
|
|
|
""" |
|
208
|
1 |
|
return MRA().sim(src, tar) |
|
209
|
|
|
|
|
210
|
|
|
|
|
211
|
1 |
|
def dist_mra(src, tar): |
|
212
|
|
|
"""Return the normalized MRA distance between two strings. |
|
213
|
|
|
|
|
214
|
|
|
This is a wrapper for :py:meth:`MRA.dist`. |
|
215
|
|
|
|
|
216
|
|
|
Parameters |
|
217
|
|
|
---------- |
|
218
|
|
|
src : str |
|
219
|
|
|
Source string for comparison |
|
220
|
|
|
tar : str |
|
221
|
|
|
Target string for comparison |
|
222
|
|
|
|
|
223
|
|
|
Returns |
|
224
|
|
|
------- |
|
225
|
|
|
float |
|
226
|
|
|
Normalized MRA distance |
|
227
|
|
|
|
|
228
|
|
|
Examples |
|
229
|
|
|
-------- |
|
230
|
|
|
>>> dist_mra('cat', 'hat') |
|
231
|
|
|
0.16666666666666663 |
|
232
|
|
|
>>> dist_mra('Niall', 'Neil') |
|
233
|
|
|
0.0 |
|
234
|
|
|
>>> dist_mra('aluminum', 'Catalan') |
|
235
|
|
|
1.0 |
|
236
|
|
|
>>> dist_mra('ATCG', 'TAGC') |
|
237
|
|
|
0.16666666666666663 |
|
238
|
|
|
|
|
239
|
|
|
""" |
|
240
|
1 |
|
return MRA().dist(src, tar) |
|
241
|
|
|
|
|
242
|
|
|
|
|
243
|
|
|
if __name__ == '__main__': |
|
244
|
|
|
import doctest |
|
245
|
|
|
|
|
246
|
|
|
doctest.testmod() |
|
247
|
|
|
|
chrislit /
abydos
Loading history...