abydos.distance._minkowski.sim_minkowski() - Code Metrics - Inspection of "Merge pull request #149 from chrislit/0.3.6" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( f43547...71985b )

by Chris

created 2018-11-17 08:52 UTC

abydos.distance._minkowski.sim_minkowski() A

↳ Parent: abydos.distance._minkowski

Complexity

Conditions

Size

Total Lines	36
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
cc	1
eloc	2
nop	5
dl	0
loc	36
ccs	2
cts	2
cp	1
crap	1
rs	10
c	0
b	0
f	0

# -*- coding: utf-8 -*-

# Copyright 2018 by Christopher C. Little.
# This file is part of Abydos.
#
# Abydos is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Abydos is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Abydos. If not, see <http://www.gnu.org/licenses/>.

"""abydos.distance._minkowski.

Minkowski distance & similarity
"""

from __future__ import (
    absolute_import,
    division,
    print_function,
    unicode_literals,
)

from numbers import Number

from ._token_distance import _TokenDistance

__all__ = ['Minkowski', 'dist_minkowski', 'minkowski', 'sim_minkowski']


class Minkowski(_TokenDistance):

    """Minkowski distance.

    The Minkowski distance :cite:`Minkowski:1910` is a distance metric in
    :math:`L^p-space`.
    """

    def dist_abs(

        self, src, tar, qval=2, pval=1, normalized=False, alphabet=None

    ):
        """Return the Minkowski distance (:math:`L^p`-norm) of two strings.

        Parameters
        ----------
        src : str
            Source string (or QGrams/Counter objects) for comparison
        tar : str
            Target string (or QGrams/Counter objects) for comparison
        qval : int
            The length of each q-gram; 0 for non-q-gram version
        pval : int or float
            The :math:`p`-value of the :math:`L^p`-space
        normalized : bool
            Normalizes to [0, 1] if True
        alphabet : collection or int
            The values or size of the alphabet

        Returns
        -------
        float
            The Minkowski distance

        Examples
        --------
        >>> cmp = Minkowski()
        >>> cmp.dist_abs('cat', 'hat')
        4.0
        >>> cmp.dist_abs('Niall', 'Neil')
        7.0
        >>> cmp.dist_abs('Colin', 'Cuilen')
        9.0
        >>> cmp.dist_abs('ATCG', 'TAGC')
        10.0

        """
        q_src, q_tar = self._get_qgrams(src, tar, qval)
        diffs = ((q_src - q_tar) + (q_tar - q_src)).values()

        normalizer = 1
        if normalized:
            totals = (q_src + q_tar).values()
            if alphabet is not None:
                # noinspection PyTypeChecker
                normalizer = (
                    alphabet if isinstance(alphabet, Number) else len(alphabet)
                )
            elif pval == 0:
                normalizer = len(totals)
            else:
                normalizer = sum(_ ** pval for _ in totals) ** (1 / pval)

        if len(diffs) == 0:

            return 0.0
        if pval == float('inf'):
            # Chebyshev distance
            return max(diffs) / normalizer
        if pval == 0:
            # This is the l_0 "norm" as developed by David Donoho
            return len(diffs) / normalizer
        return sum(_ ** pval for _ in diffs) ** (1 / pval) / normalizer

    def dist(self, src, tar, qval=2, pval=1, alphabet=None):

        """Return normalized Minkowski distance of two strings.

        The normalized Minkowski distance :cite:`Minkowski:1910` is a distance
        metric in :math:`L^p`-space, normalized to [0, 1].

        Parameters
        ----------
        src : str
            Source string (or QGrams/Counter objects) for comparison
        tar : str
            Target string (or QGrams/Counter objects) for comparison
        qval : int
            The length of each q-gram; 0 for non-q-gram version
        pval : int or float
            The :math:`p`-value of the :math:`L^p`-space
        alphabet : collection or int
            The values or size of the alphabet

        Returns
        -------
        float
            The normalized Minkowski distance

        Examples
        --------
        >>> cmp = Minkowski()
        >>> cmp.dist('cat', 'hat')
        0.5
        >>> round(cmp.dist('Niall', 'Neil'), 12)
        0.636363636364
        >>> round(cmp.dist('Colin', 'Cuilen'), 12)
        0.692307692308
        >>> cmp.dist('ATCG', 'TAGC')
        1.0

        """
        return self.dist_abs(src, tar, qval, pval, True, alphabet)


def minkowski(src, tar, qval=2, pval=1, normalized=False, alphabet=None):

    """Return the Minkowski distance (:math:`L^p`-norm) of two strings.

    This is a wrapper for :py:meth:`Minkowski.dist_abs`.

    Parameters
    ----------
    src : str
        Source string (or QGrams/Counter objects) for comparison
    tar : str
        Target string (or QGrams/Counter objects) for comparison
    qval : int
        The length of each q-gram; 0 for non-q-gram version
    pval : int or float
        The :math:`p`-value of the :math:`L^p`-space
    normalized : bool
        Normalizes to [0, 1] if True
    alphabet : collection or int
        The values or size of the alphabet

    Returns
    -------
    float
        The Minkowski distance

    Examples
    --------
    >>> minkowski('cat', 'hat')
    4.0
    >>> minkowski('Niall', 'Neil')
    7.0
    >>> minkowski('Colin', 'Cuilen')
    9.0
    >>> minkowski('ATCG', 'TAGC')
    10.0

    """
    return Minkowski().dist_abs(src, tar, qval, pval, normalized, alphabet)


def dist_minkowski(src, tar, qval=2, pval=1, alphabet=None):
    """Return normalized Minkowski distance of two strings.

    This is a wrapper for :py:meth:`Minkowski.dist`.

    Parameters
    ----------
    src : str
        Source string (or QGrams/Counter objects) for comparison
    tar : str
        Target string (or QGrams/Counter objects) for comparison
    qval : int
        The length of each q-gram; 0 for non-q-gram version
    pval : int or float
        The :math:`p`-value of the :math:`L^p`-space
    alphabet : collection or int
        The values or size of the alphabet

    Returns
    -------
    float
        The normalized Minkowski distance

    Examples
    --------
    >>> dist_minkowski('cat', 'hat')
    0.5
    >>> round(dist_minkowski('Niall', 'Neil'), 12)
    0.636363636364
    >>> round(dist_minkowski('Colin', 'Cuilen'), 12)
    0.692307692308
    >>> dist_minkowski('ATCG', 'TAGC')
    1.0

    """
    return Minkowski().dist(src, tar, qval, pval, alphabet)


def sim_minkowski(src, tar, qval=2, pval=1, alphabet=None):
    """Return normalized Minkowski similarity of two strings.

    This is a wrapper for :py:meth:`Minkowski.sim`.

    Parameters
    ----------
    src : str
        Source string (or QGrams/Counter objects) for comparison
    tar : str
        Target string (or QGrams/Counter objects) for comparison
    qval : int
        The length of each q-gram; 0 for non-q-gram version
    pval : int or float
        The :math:`p`-value of the :math:`L^p`-space
    alphabet : collection or int
        The values or size of the alphabet

    Returns
    -------
    float
        The normalized Minkowski similarity

    Examples
    --------
    >>> sim_minkowski('cat', 'hat')
    0.5
    >>> round(sim_minkowski('Niall', 'Neil'), 12)
    0.363636363636
    >>> round(sim_minkowski('Colin', 'Cuilen'), 12)
    0.307692307692
    >>> sim_minkowski('ATCG', 'TAGC')
    0.0

    """
    return Minkowski().sim(src, tar, qval, pval, alphabet)


if __name__ == '__main__':
    import doctest

    doctest.testmod()


1		# -- coding: utf-8 --
2
3		# Copyright 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._minkowski.
20
21		Minkowski distance & similarity
22		"""
23
24	1	from __future__ import (
25		absolute_import,
26		division,
27		print_function,
28		unicode_literals,
29		)
30
31	1	from numbers import Number
32
33	1	from ._token_distance import _TokenDistance
34
35	1	__all__ = ['Minkowski', 'dist_minkowski', 'minkowski', 'sim_minkowski']
36
37
38	1	class Minkowski(_TokenDistance):
		0 ignored issues – show Unused Code introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report The variable `__class__` seems to be unused. Loading history...
39		"""Minkowski distance.
40
41		The Minkowski distance :cite:`Minkowski:1910` is a distance metric in
42		:math:`L^p-space`.
43		"""
44
45	1	def dist_abs(
		0 ignored issues – show best-practice introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Too many arguments (7/5) Loading history... Bug introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Parameters differ from overridden 'dist_abs' method Loading history...
46		self, src, tar, qval=2, pval=1, normalized=False, alphabet=None
		0 ignored issues – show Coding Style introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Wrong hanging indentation before block (add 4 spaces). Loading history...
47		):
48		"""Return the Minkowski distance (:math:`L^p`-norm) of two strings.
49
50		Parameters
51		----------
52		src : str
53		Source string (or QGrams/Counter objects) for comparison
54		tar : str
55		Target string (or QGrams/Counter objects) for comparison
56		qval : int
57		The length of each q-gram; 0 for non-q-gram version
58		pval : int or float
59		The :math:`p`-value of the :math:`L^p`-space
60		normalized : bool
61		Normalizes to [0, 1] if True
62		alphabet : collection or int
63		The values or size of the alphabet
64
65		Returns
66		-------
67		float
68		The Minkowski distance
69
70		Examples
71		--------
72		>>> cmp = Minkowski()
73		>>> cmp.dist_abs('cat', 'hat')
74		4.0
75		>>> cmp.dist_abs('Niall', 'Neil')
76		7.0
77		>>> cmp.dist_abs('Colin', 'Cuilen')
78		9.0
79		>>> cmp.dist_abs('ATCG', 'TAGC')
80		10.0
81
82		"""
83	1	q_src, q_tar = self._get_qgrams(src, tar, qval)
84	1	diffs = ((q_src - q_tar) + (q_tar - q_src)).values()
85
86	1	normalizer = 1
87	1	if normalized:
88	1	totals = (q_src + q_tar).values()
89	1	if alphabet is not None:
90		# noinspection PyTypeChecker
91	1	normalizer = (
92		alphabet if isinstance(alphabet, Number) else len(alphabet)
93		)
94	1	elif pval == 0:
95	1	normalizer = len(totals)
96		else:
97	1	normalizer = sum(_ pval for _ in totals) (1 / pval)
98
99	1	if len(diffs) == 0:
		0 ignored issues – show Unused Code introduced 2018-10-23 05:52 UTC by Report Bug Copy Issue Report Do not use `len(SEQUENCE)` as condition value Loading history...
100	1	return 0.0
101	1	if pval == float('inf'):
102		# Chebyshev distance
103	1	return max(diffs) / normalizer
104	1	if pval == 0:
105		# This is the l_0 "norm" as developed by David Donoho
106	1	return len(diffs) / normalizer
107	1	return sum(_ pval for _ in diffs) (1 / pval) / normalizer
108
109	1	def dist(self, src, tar, qval=2, pval=1, alphabet=None):
		0 ignored issues – show best-practice introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Too many arguments (6/5) Loading history... Bug introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Parameters differ from overridden 'dist' method Loading history...
110		"""Return normalized Minkowski distance of two strings.
111
112		The normalized Minkowski distance :cite:`Minkowski:1910` is a distance
113		metric in :math:`L^p`-space, normalized to [0, 1].
114
115		Parameters
116		----------
117		src : str
118		Source string (or QGrams/Counter objects) for comparison
119		tar : str
120		Target string (or QGrams/Counter objects) for comparison
121		qval : int
122		The length of each q-gram; 0 for non-q-gram version
123		pval : int or float
124		The :math:`p`-value of the :math:`L^p`-space
125		alphabet : collection or int
126		The values or size of the alphabet
127
128		Returns
129		-------
130		float
131		The normalized Minkowski distance
132
133		Examples
134		--------
135		>>> cmp = Minkowski()
136		>>> cmp.dist('cat', 'hat')
137		0.5
138		>>> round(cmp.dist('Niall', 'Neil'), 12)
139		0.636363636364
140		>>> round(cmp.dist('Colin', 'Cuilen'), 12)
141		0.692307692308
142		>>> cmp.dist('ATCG', 'TAGC')
143		1.0
144
145		"""
146	1	return self.dist_abs(src, tar, qval, pval, True, alphabet)
147
148
149	1	def minkowski(src, tar, qval=2, pval=1, normalized=False, alphabet=None):
		0 ignored issues – show best-practice introduced 2018-10-05 08:54 UTC by Report Bug Copy Issue Report Too many arguments (6/5) Loading history...
150		"""Return the Minkowski distance (:math:`L^p`-norm) of two strings.
151
152		This is a wrapper for :py:meth:`Minkowski.dist_abs`.
153
154		Parameters
155		----------
156		src : str
157		Source string (or QGrams/Counter objects) for comparison
158		tar : str
159		Target string (or QGrams/Counter objects) for comparison
160		qval : int
161		The length of each q-gram; 0 for non-q-gram version
162		pval : int or float
163		The :math:`p`-value of the :math:`L^p`-space
164		normalized : bool
165		Normalizes to [0, 1] if True
166		alphabet : collection or int
167		The values or size of the alphabet
168
169		Returns
170		-------
171		float
172		The Minkowski distance
173
174		Examples
175		--------
176		>>> minkowski('cat', 'hat')
177		4.0
178		>>> minkowski('Niall', 'Neil')
179		7.0
180		>>> minkowski('Colin', 'Cuilen')
181		9.0
182		>>> minkowski('ATCG', 'TAGC')
183		10.0
184
185		"""
186	1	return Minkowski().dist_abs(src, tar, qval, pval, normalized, alphabet)
187
188
189	1	def dist_minkowski(src, tar, qval=2, pval=1, alphabet=None):
190		"""Return normalized Minkowski distance of two strings.
191
192		This is a wrapper for :py:meth:`Minkowski.dist`.
193
194		Parameters
195		----------
196		src : str
197		Source string (or QGrams/Counter objects) for comparison
198		tar : str
199		Target string (or QGrams/Counter objects) for comparison
200		qval : int
201		The length of each q-gram; 0 for non-q-gram version
202		pval : int or float
203		The :math:`p`-value of the :math:`L^p`-space
204		alphabet : collection or int
205		The values or size of the alphabet
206
207		Returns
208		-------
209		float
210		The normalized Minkowski distance
211
212		Examples
213		--------
214		>>> dist_minkowski('cat', 'hat')
215		0.5
216		>>> round(dist_minkowski('Niall', 'Neil'), 12)
217		0.636363636364
218		>>> round(dist_minkowski('Colin', 'Cuilen'), 12)
219		0.692307692308
220		>>> dist_minkowski('ATCG', 'TAGC')
221		1.0
222
223		"""
224	1	return Minkowski().dist(src, tar, qval, pval, alphabet)
225
226
227	1	def sim_minkowski(src, tar, qval=2, pval=1, alphabet=None):
228		"""Return normalized Minkowski similarity of two strings.
229
230		This is a wrapper for :py:meth:`Minkowski.sim`.
231
232		Parameters
233		----------
234		src : str
235		Source string (or QGrams/Counter objects) for comparison
236		tar : str
237		Target string (or QGrams/Counter objects) for comparison
238		qval : int
239		The length of each q-gram; 0 for non-q-gram version
240		pval : int or float
241		The :math:`p`-value of the :math:`L^p`-space
242		alphabet : collection or int
243		The values or size of the alphabet
244
245		Returns
246		-------
247		float
248		The normalized Minkowski similarity
249
250		Examples
251		--------
252		>>> sim_minkowski('cat', 'hat')
253		0.5
254		>>> round(sim_minkowski('Niall', 'Neil'), 12)
255		0.363636363636
256		>>> round(sim_minkowski('Colin', 'Cuilen'), 12)
257		0.307692307692
258		>>> sim_minkowski('ATCG', 'TAGC')
259		0.0
260
261		"""
262	1	return Minkowski().sim(src, tar, qval, pval, alphabet)
263
264
265		if __name__ == '__main__':
266		import doctest
267
268		doctest.testmod()
269

chrislit / abydos

Push — master ( f43547...71985b )

abydos.distance._minkowski.sim_minkowski() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like