|
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._millar. |
|
20
|
|
|
|
|
21
|
|
|
Millar's binomial deviance dissimilarity |
|
22
|
|
|
""" |
|
23
|
|
|
|
|
24
|
1 |
|
from __future__ import ( |
|
25
|
|
|
absolute_import, |
|
26
|
|
|
division, |
|
27
|
|
|
print_function, |
|
28
|
|
|
unicode_literals, |
|
29
|
|
|
) |
|
30
|
|
|
|
|
31
|
1 |
|
from math import log |
|
32
|
|
|
|
|
33
|
1 |
|
from ._token_distance import _TokenDistance |
|
34
|
|
|
|
|
35
|
1 |
|
__all__ = ['Millar'] |
|
36
|
|
|
|
|
37
|
|
|
|
|
38
|
1 |
|
class Millar(_TokenDistance): |
|
39
|
|
|
r"""Millar's binomial deviance dissimilarity. |
|
40
|
|
|
|
|
41
|
|
|
For two sets X and Y drawn from a population S, Millar's binomial deviance |
|
42
|
|
|
dissimilarity :cite:`Anderson:2004` is: |
|
43
|
|
|
|
|
44
|
|
|
.. math:: |
|
45
|
|
|
|
|
46
|
|
|
dist_{Millar}(X, Y) = \sum_{i=0}^{|S|} \frac{1}{x_i+y_i} |
|
47
|
|
|
\bigg\{x_i log(\frac{x_i}{x_i+y_i}) + y_i log(\frac{y_i}{x_i+y_i}) |
|
48
|
|
|
- (x_i+y_i) log(\frac{1}{2})\bigg\} |
|
49
|
|
|
|
|
50
|
|
|
|
|
51
|
|
|
.. versionadded:: 0.4.1 |
|
52
|
|
|
""" |
|
53
|
|
|
|
|
54
|
1 |
|
def __init__(self, **kwargs): |
|
55
|
|
|
"""Initialize Millar instance. |
|
56
|
|
|
|
|
57
|
|
|
Parameters |
|
58
|
|
|
---------- |
|
59
|
|
|
**kwargs |
|
60
|
|
|
Arbitrary keyword arguments |
|
61
|
|
|
|
|
62
|
|
|
|
|
63
|
|
|
.. versionadded:: 0.4.1 |
|
64
|
|
|
|
|
65
|
|
|
""" |
|
66
|
1 |
|
super(Millar, self).__init__(**kwargs) |
|
67
|
|
|
|
|
68
|
1 |
|
def dist_abs(self, src, tar): |
|
69
|
|
|
"""Return Millar's binomial deviance dissimilarity of two strings. |
|
70
|
|
|
|
|
71
|
|
|
Parameters |
|
72
|
|
|
---------- |
|
73
|
|
|
src : str |
|
74
|
|
|
Source string for comparison |
|
75
|
|
|
tar : str |
|
76
|
|
|
Target string for comparison |
|
77
|
|
|
|
|
78
|
|
|
Returns |
|
79
|
|
|
------- |
|
80
|
|
|
float |
|
81
|
|
|
Millar's binomial deviance dissimilarity |
|
82
|
|
|
|
|
83
|
|
|
Examples |
|
84
|
|
|
-------- |
|
85
|
|
|
>>> cmp = Millar() |
|
86
|
|
|
>>> cmp.dist_abs('cat', 'hat') |
|
87
|
|
|
2.772588722239781 |
|
88
|
|
|
>>> cmp.dist_abs('Niall', 'Neil') |
|
89
|
|
|
4.852030263919617 |
|
90
|
|
|
>>> cmp.dist_abs('aluminum', 'Catalan') |
|
91
|
|
|
9.704060527839234 |
|
92
|
|
|
>>> cmp.dist_abs('ATCG', 'TAGC') |
|
93
|
|
|
6.931471805599453 |
|
94
|
|
|
|
|
95
|
|
|
|
|
96
|
|
|
.. versionadded:: 0.4.1 |
|
97
|
|
|
|
|
98
|
|
|
""" |
|
99
|
1 |
|
self._tokenize(src, tar) |
|
100
|
|
|
|
|
101
|
1 |
|
src_tok = self._src_tokens |
|
102
|
1 |
|
tar_tok = self._tar_tokens |
|
103
|
1 |
|
alphabet = set(set(src_tok.keys()) | set(tar_tok.keys())) |
|
104
|
|
|
|
|
105
|
1 |
|
log2 = log(2) |
|
106
|
1 |
|
score = 0 |
|
107
|
1 |
|
for tok in alphabet: |
|
108
|
1 |
|
n_k = src_tok[tok] + tar_tok[tok] |
|
109
|
|
|
|
|
110
|
1 |
|
src_val = 0 |
|
111
|
1 |
|
if src_tok[tok]: |
|
112
|
1 |
|
src_val = src_tok[tok] * log(src_tok[tok] / n_k) |
|
113
|
|
|
|
|
114
|
1 |
|
tar_val = 0 |
|
115
|
1 |
|
if tar_tok[tok]: |
|
116
|
1 |
|
tar_val = tar_tok[tok] * log(tar_tok[tok] / n_k) |
|
117
|
|
|
|
|
118
|
1 |
|
score += (src_val + tar_val + n_k * log2) / n_k |
|
119
|
|
|
|
|
120
|
1 |
|
if score > 0: |
|
121
|
1 |
|
return score |
|
122
|
1 |
|
return 0.0 |
|
123
|
|
|
|
|
124
|
1 |
|
def sim(self, *args, **kwargs): |
|
125
|
|
|
"""Raise exception when called. |
|
126
|
|
|
|
|
127
|
|
|
Parameters |
|
128
|
|
|
---------- |
|
129
|
|
|
*args |
|
130
|
|
|
Variable length argument list |
|
131
|
|
|
**kwargs |
|
132
|
|
|
Arbitrary keyword arguments |
|
133
|
|
|
|
|
134
|
|
|
Raises |
|
135
|
|
|
------ |
|
136
|
|
|
NotImplementedError |
|
137
|
|
|
Method disabled for Millar dissimilarity. |
|
138
|
|
|
|
|
139
|
|
|
|
|
140
|
|
|
.. versionadded:: 0.3.6 |
|
141
|
|
|
|
|
142
|
|
|
""" |
|
143
|
1 |
|
raise NotImplementedError('Method disabled for Millar dissimilarity.') |
|
144
|
|
|
|
|
145
|
1 |
|
def dist(self, *args, **kwargs): |
|
146
|
|
|
"""Raise exception when called. |
|
147
|
|
|
|
|
148
|
|
|
Parameters |
|
149
|
|
|
---------- |
|
150
|
|
|
*args |
|
151
|
|
|
Variable length argument list |
|
152
|
|
|
**kwargs |
|
153
|
|
|
Arbitrary keyword arguments |
|
154
|
|
|
|
|
155
|
|
|
Raises |
|
156
|
|
|
------ |
|
157
|
|
|
NotImplementedError |
|
158
|
|
|
Method disabled for Millar dissimilarity. |
|
159
|
|
|
|
|
160
|
|
|
|
|
161
|
|
|
.. versionadded:: 0.3.6 |
|
162
|
|
|
|
|
163
|
|
|
""" |
|
164
|
1 |
|
raise NotImplementedError('Method disabled for Millar dissimilarity.') |
|
165
|
|
|
|
|
166
|
|
|
|
|
167
|
|
|
if __name__ == '__main__': |
|
168
|
|
|
import doctest |
|
169
|
|
|
|
|
170
|
|
|
doctest.testmod() |
|
171
|
|
|
|
chrislit /
abydos
