Completed
Push — master ( 643512...2b6b3e )
by Chris
20:40 queued 10:36
created

abydos.distance._morisita.Morisita.dist()   A

Complexity

Conditions 1

Size

Total Lines 20
Code Lines 2

Duplication

Lines 0
Ratio 0 %

Code Coverage

Tests 2
CRAP Score 1

Importance

Changes 0
Metric Value
eloc 2
dl 0
loc 20
ccs 2
cts 2
cp 1
rs 10
c 0
b 0
f 0
cc 1
nop 3
crap 1
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._morisita.
20
21
Morisita index of overlap
22
"""
23
24 1
from __future__ import (
25
    absolute_import,
26
    division,
27
    print_function,
28
    unicode_literals,
29
)
30
31 1
from ._token_distance import _TokenDistance
32
33 1
__all__ = ['Morisita']
34
35
36 1
class Morisita(_TokenDistance):
37
    r"""Morisita index of overlap.
38
39
    Morisita index of overlap :cite:`Morisita:1959`, following the description
40
    of :cite:`Horn:1966`, given two populations X and Y drawn from S species,
41
    is:
42
43
    .. math::
44
45
        sim_{Morisita}(X, Y) =
46
        C_{\lambda} = \frac{2\sum_{i=1}^S x_i y_i}{(\lambda_x + \lambda_y)XY}
47
48
    where
49
50
    .. math::
51
52
        X = \sum_{i=1}^S x_i  ~~;~~  Y = \sum_{i=1}^S y_i
53
54
    .. math::
55
56
        \lambda_x = \frac{\sum_{i=1}^S x_i(x_i-1)}{X(X-1)} ~~;~~
57
        \lambda_y = \frac{\sum_{i=1}^S y_i(y_i-1)}{Y(Y-1)}
58
59
    .. versionadded:: 0.4.1
60
    """
61
62 1
    def __init__(self, **kwargs):
63
        """Initialize Morisita instance.
64
65
        Parameters
66
        ----------
67
        **kwargs
68
            Arbitrary keyword arguments
69
70
71
        .. versionadded:: 0.4.1
72
73
        """
74 1
        super(Morisita, self).__init__(**kwargs)
75
76 1
    def sim_score(self, src, tar):
77
        """Return the Morisita similarity of two strings.
78
79
        Parameters
80
        ----------
81
        src : str
82
            Source string for comparison
83
        tar : str
84
            Target string for comparison
85
86
        Returns
87
        -------
88
        float
89
            Morisita similarity
90
91
        Examples
92
        --------
93
        >>> cmp = Morisita()
94
        >>> cmp.sim_score('cat', 'hat')
95
        0.25
96
        >>> cmp.sim_score('Niall', 'Neil')
97
        0.13333333333333333
98
        >>> cmp.sim_score('aluminum', 'Catalan')
99
        1.0
100
        >>> cmp.sim_score('ATCG', 'TAGC')
101
        0.0
102
103
104
        .. versionadded:: 0.4.1
105
106
        """
107 1
        self._tokenize(src, tar)
108
109 1
        intersection = self._intersection()
110
111 1
        src_card = self._src_card()
112 1
        tar_card = self._tar_card()
113
114 1
        src_lambda = 0
115 1
        tar_lambda = 0
116 1
        for val in self._src_tokens.values():
117 1
            src_lambda += val * (val - 1)
118 1
        if src_lambda:
119 1
            src_lambda /= src_card * (src_card - 1)
120 1
        for val in self._tar_tokens.values():
121 1
            tar_lambda += val * (val - 1)
122 1
        if tar_lambda:
123 1
            tar_lambda /= tar_card * (tar_card - 1)
124
125 1
        sim = 0
126 1
        for symbol in intersection.keys():
127 1
            sim += self._src_tokens[symbol] * self._tar_tokens[symbol]
128 1
        sim *= 2
129 1
        if src_card:
130 1
            sim /= src_card
131 1
        if tar_card:
132 1
            sim /= tar_card
133 1
        if src_lambda + tar_lambda:
134 1
            sim /= src_lambda + tar_lambda
135
136 1
        return sim
137
138 1
    def sim(self, *args, **kwargs):
139
        """Raise exception when called.
140
141
        Parameters
142
        ----------
143
        *args
144
            Variable length argument list
145
        **kwargs
146
            Arbitrary keyword arguments
147
148
        Raises
149
        ------
150
        NotImplementedError
151
            Method disabled for Morisita similarity.
152
153
154
        .. versionadded:: 0.3.6
155
156
        """
157 1
        raise NotImplementedError('Method disabled for Morisita similarity.')
158
159 1
    def dist(self, *args, **kwargs):
160
        """Raise exception when called.
161
162
        Parameters
163
        ----------
164
        *args
165
            Variable length argument list
166
        **kwargs
167
            Arbitrary keyword arguments
168
169
        Raises
170
        ------
171
        NotImplementedError
172
            Method disabled for Morisita similarity.
173
174
175
        .. versionadded:: 0.3.6
176
177
        """
178 1
        raise NotImplementedError('Method disabled for Morisita similarity.')
179
180
181
if __name__ == '__main__':
182
    import doctest
183
184
    doctest.testmod()
185