abydos.distance._damerau_levenshtein.sim_damerau() - Code Metrics - Inspection of "0.3.6" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#141)

by Chris

created 2018-11-10 03:25 UTC

abydos.distance._damerau_levenshtein.sim_damerau() A

↳ Parent: abydos.distance._damerau_levenshtein

Complexity

Conditions

Size

Total Lines	27
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
cc	1
eloc	2
nop	3
dl	0
loc	27
ccs	2
cts	2
cp	1
crap	1
rs	10
c	0
b	0
f	0

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

# Copyright 2014-2018 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._damerau_levenshtein.

Damerau-Levenshtein distance
"""

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

from sys import maxsize

from numpy import int as np_int
from numpy import zeros as np_zeros

from six.moves import range

from ._distance import _Distance

__all__ = [
    'DamerauLevenshtein',
    'damerau_levenshtein',
    'dist_damerau',
    'sim_damerau',
]


class DamerauLevenshtein(_Distance):

    """Damerau-Levenshtein distance.

    This computes the Damerau-Levenshtein distance :cite:`Damerau:1964`.
    Damerau-Levenshtein code is based on Java code by Kevin L. Stern
    :cite:`Stern:2014`, under the MIT license:
    https://github.com/KevinStern/software-and-algorithms/blob/master/src/main/java/blogspot/software_and_algorithms/stern_library/string/DamerauLevenshteinAlgorithm.java
    """

    def dist_abs(self, src, tar, cost=(1, 1, 1, 1)):

        """Return the Damerau-Levenshtein distance between two strings.

        Args:
            src (str): Source string for comparison
            tar (str): Target string for comparison
            cost (tuple): a 4-tuple representing the cost of the four possible
                edits: inserts, deletes, substitutions, and transpositions,
                respectively (by default: (1, 1, 1, 1))

        Returns:
            int (may return a float if cost has float values): The
                Damerau-Levenshtein distance between src & tar

        Raises:
            ValueError: Unsupported cost assignment; the cost of two
                transpositions must not be less than the cost of an insert plus
                a delete.

        Examples:
            >>> cmp = DamerauLevenshtein()
            >>> cmp.dist_abs('cat', 'hat')
            1
            >>> cmp.dist_abs('Niall', 'Neil')
            3
            >>> cmp.dist_abs('aluminum', 'Catalan')
            7
            >>> cmp.dist_abs('ATCG', 'TAGC')
            2

        """
        ins_cost, del_cost, sub_cost, trans_cost = cost

        if src == tar:
            return 0
        if not src:
            return len(tar) * ins_cost
        if not tar:
            return len(src) * del_cost

        if 2 * trans_cost < ins_cost + del_cost:
            raise ValueError(
                'Unsupported cost assignment; the cost of two transpositions '
                + 'must not be less than the cost of an insert plus a delete.'
            )

        d_mat = np_zeros((len(src)) * (len(tar)), dtype=np_int).reshape(
            (len(src), len(tar))
        )

        if src[0] != tar[0]:
            d_mat[0, 0] = min(sub_cost, ins_cost + del_cost)

        src_index_by_character = {src[0]: 0}
        for i in range(1, len(src)):
            del_distance = d_mat[i - 1, 0] + del_cost
            ins_distance = (i + 1) * del_cost + ins_cost
            match_distance = i * del_cost + (
                0 if src[i] == tar[0] else sub_cost
            )
            d_mat[i, 0] = min(del_distance, ins_distance, match_distance)

        for j in range(1, len(tar)):
            del_distance = (j + 1) * ins_cost + del_cost
            ins_distance = d_mat[0, j - 1] + ins_cost
            match_distance = j * ins_cost + (
                0 if src[0] == tar[j] else sub_cost
            )
            d_mat[0, j] = min(del_distance, ins_distance, match_distance)

        for i in range(1, len(src)):
            max_src_letter_match_index = 0 if src[i] == tar[0] else -1
            for j in range(1, len(tar)):
                candidate_swap_index = (
                    -1
                    if tar[j] not in src_index_by_character
                    else src_index_by_character[tar[j]]
                )
                j_swap = max_src_letter_match_index
                del_distance = d_mat[i - 1, j] + del_cost
                ins_distance = d_mat[i, j - 1] + ins_cost
                match_distance = d_mat[i - 1, j - 1]
                if src[i] != tar[j]:
                    match_distance += sub_cost
                else:
                    max_src_letter_match_index = j

                if candidate_swap_index != -1 and j_swap != -1:
                    i_swap = candidate_swap_index

                    if i_swap == 0 and j_swap == 0:
                        pre_swap_cost = 0
                    else:
                        pre_swap_cost = d_mat[
                            max(0, i_swap - 1), max(0, j_swap - 1)
                        ]
                    swap_distance = (
                        pre_swap_cost
                        + (i - i_swap - 1) * del_cost
                        + (j - j_swap - 1) * ins_cost
                        + trans_cost
                    )
                else:
                    swap_distance = maxsize

                d_mat[i, j] = min(
                    del_distance, ins_distance, match_distance, swap_distance
                )
            src_index_by_character[src[i]] = i

        return d_mat[len(src) - 1, len(tar) - 1]

    def dist(self, src, tar, cost=(1, 1, 1, 1)):

        """Return the Damerau-Levenshtein similarity of two strings.

        Damerau-Levenshtein distance normalized to the interval [0, 1].

        The Damerau-Levenshtein distance is normalized by dividing the
        Damerau-Levenshtein distance by the greater of
        the number of characters in src times the cost of a delete and
        the number of characters in tar times the cost of an insert.
        For the case in which all operations have :math:`cost = 1`, this is
        equivalent to the greater of the length of the two strings src & tar.

        Args:
            src (str): Source string for comparison
            tar (str): Target string for comparison
            cost (tuple): a 4-tuple representing the cost of the four possible
                edits: inserts, deletes, substitutions, and transpositions,
                respectively (by default: (1, 1, 1, 1))

        Returns:
            float: The normalized Damerau-Levenshtein distance

        Examples:
            >>> cmp = DamerauLevenshtein()
            >>> round(cmp.dist('cat', 'hat'), 12)
            0.333333333333
            >>> round(cmp.dist('Niall', 'Neil'), 12)
            0.6
            >>> cmp.dist('aluminum', 'Catalan')
            0.875
            >>> cmp.dist('ATCG', 'TAGC')
            0.5

        """
        if src == tar:
            return 0.0
        ins_cost, del_cost = cost[:2]
        return self.dist_abs(src, tar, cost) / (
            max(len(src) * del_cost, len(tar) * ins_cost)
        )


def damerau_levenshtein(src, tar, cost=(1, 1, 1, 1)):
    """Return the Damerau-Levenshtein distance between two strings.

    This is a wrapper of :py:meth:`DamerauLevenshtein.dist_abs`.

    Args:
        src (str): Source string for comparison
        tar (str): Target string for comparison
        cost (tuple): a 4-tuple representing the cost of the four possible
            edits: inserts, deletes, substitutions, and transpositions,
            respectively (by default: (1, 1, 1, 1))

    Returns:
        int (may return a float if cost has float values): The
            Damerau-Levenshtein distance between src & tar

    Examples:
        >>> damerau_levenshtein('cat', 'hat')
        1
        >>> damerau_levenshtein('Niall', 'Neil')
        3
        >>> damerau_levenshtein('aluminum', 'Catalan')
        7
        >>> damerau_levenshtein('ATCG', 'TAGC')
        2

    """
    return DamerauLevenshtein().dist_abs(src, tar, cost)


def dist_damerau(src, tar, cost=(1, 1, 1, 1)):
    """Return the Damerau-Levenshtein similarity of two strings.

    This is a wrapper of :py:meth:`DamerauLevenshtein.dist`.

    Args:
        src (str): Source string for comparison
        tar (str): Target string for comparison
        cost (tuple): a 4-tuple representing the cost of the four possible
            edits: inserts, deletes, substitutions, and transpositions,
            respectively (by default: (1, 1, 1, 1))

    Returns:
        float: The normalized Damerau-Levenshtein distance

    Examples:
        >>> round(dist_damerau('cat', 'hat'), 12)
        0.333333333333
        >>> round(dist_damerau('Niall', 'Neil'), 12)
        0.6
        >>> dist_damerau('aluminum', 'Catalan')
        0.875
        >>> dist_damerau('ATCG', 'TAGC')
        0.5

    """
    return DamerauLevenshtein().dist(src, tar, cost)


def sim_damerau(src, tar, cost=(1, 1, 1, 1)):
    """Return the Damerau-Levenshtein similarity of two strings.

    This is a wrapper of :py:meth:`DamerauLevenshtein.sim`.

    Args:
        src (str): Source string for comparison
        tar (str): Target string for comparison
        cost (tuple): a 4-tuple representing the cost of the four possible
            edits: inserts, deletes, substitutions, and transpositions,
            respectively (by default: (1, 1, 1, 1))

    Returns:
        float: The normalized Damerau-Levenshtein similarity

    Examples:
        >>> round(sim_damerau('cat', 'hat'), 12)
        0.666666666667
        >>> round(sim_damerau('Niall', 'Neil'), 12)
        0.4
        >>> sim_damerau('aluminum', 'Catalan')
        0.125
        >>> sim_damerau('ATCG', 'TAGC')
        0.5

    """
    return DamerauLevenshtein().sim(src, tar, cost)


if __name__ == '__main__':
    import doctest

    doctest.testmod()


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._damerau_levenshtein.
20
21		Damerau-Levenshtein distance
22		"""
23
24	1	from __future__ import (
25		absolute_import,
26		division,
27		print_function,
28		unicode_literals,
29		)
30
31	1	from sys import maxsize
32
33	1	from numpy import int as np_int
34	1	from numpy import zeros as np_zeros
35
36	1	from six.moves import range
37
38	1	from ._distance import _Distance
39
40	1	__all__ = [
41		'DamerauLevenshtein',
42		'damerau_levenshtein',
43		'dist_damerau',
44		'sim_damerau',
45		]
46
47
48	1	class DamerauLevenshtein(_Distance):
		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...
49		"""Damerau-Levenshtein distance.
50
51		This computes the Damerau-Levenshtein distance :cite:`Damerau:1964`.
52		Damerau-Levenshtein code is based on Java code by Kevin L. Stern
53		:cite:`Stern:2014`, under the MIT license:
54		https://github.com/KevinStern/software-and-algorithms/blob/master/src/main/java/blogspot/software_and_algorithms/stern_library/string/DamerauLevenshteinAlgorithm.java
55		"""
56
57	1	def dist_abs(self, src, tar, cost=(1, 1, 1, 1)):
		0 ignored issues – show Comprehensibility introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report This function exceeds the maximum number of variables (22/15). 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...
58		"""Return the Damerau-Levenshtein distance between two strings.
59
60		Args:
61		src (str): Source string for comparison
62		tar (str): Target string for comparison
63		cost (tuple): a 4-tuple representing the cost of the four possible
64		edits: inserts, deletes, substitutions, and transpositions,
65		respectively (by default: (1, 1, 1, 1))
66
67		Returns:
68		int (may return a float if cost has float values): The
69		Damerau-Levenshtein distance between src & tar
70
71		Raises:
72		ValueError: Unsupported cost assignment; the cost of two
73		transpositions must not be less than the cost of an insert plus
74		a delete.
75
76		Examples:
77		>>> cmp = DamerauLevenshtein()
78		>>> cmp.dist_abs('cat', 'hat')
79		1
80		>>> cmp.dist_abs('Niall', 'Neil')
81		3
82		>>> cmp.dist_abs('aluminum', 'Catalan')
83		7
84		>>> cmp.dist_abs('ATCG', 'TAGC')
85		2
86
87		"""
88	1	ins_cost, del_cost, sub_cost, trans_cost = cost
89
90	1	if src == tar:
91	1	return 0
92	1	if not src:
93	1	return len(tar) * ins_cost
94	1	if not tar:
95	1	return len(src) * del_cost
96
97	1	if 2 * trans_cost < ins_cost + del_cost:
98	1	raise ValueError(
99		'Unsupported cost assignment; the cost of two transpositions '
100		+ 'must not be less than the cost of an insert plus a delete.'
101		)
102
103	1	d_mat = np_zeros((len(src)) * (len(tar)), dtype=np_int).reshape(
104		(len(src), len(tar))
105		)
106
107	1	if src[0] != tar[0]:
108	1	d_mat[0, 0] = min(sub_cost, ins_cost + del_cost)
109
110	1	src_index_by_character = {src[0]: 0}
111	1	for i in range(1, len(src)):
112	1	del_distance = d_mat[i - 1, 0] + del_cost
113	1	ins_distance = (i + 1) * del_cost + ins_cost
114	1	match_distance = i * del_cost + (
115		0 if src[i] == tar[0] else sub_cost
116		)
117	1	d_mat[i, 0] = min(del_distance, ins_distance, match_distance)
118
119	1	for j in range(1, len(tar)):
120	1	del_distance = (j + 1) * ins_cost + del_cost
121	1	ins_distance = d_mat[0, j - 1] + ins_cost
122	1	match_distance = j * ins_cost + (
123		0 if src[0] == tar[j] else sub_cost
124		)
125	1	d_mat[0, j] = min(del_distance, ins_distance, match_distance)
126
127	1	for i in range(1, len(src)):
128	1	max_src_letter_match_index = 0 if src[i] == tar[0] else -1
129	1	for j in range(1, len(tar)):
130	1	candidate_swap_index = (
131		-1
132		if tar[j] not in src_index_by_character
133		else src_index_by_character[tar[j]]
134		)
135	1	j_swap = max_src_letter_match_index
136	1	del_distance = d_mat[i - 1, j] + del_cost
137	1	ins_distance = d_mat[i, j - 1] + ins_cost
138	1	match_distance = d_mat[i - 1, j - 1]
139	1	if src[i] != tar[j]:
140	1	match_distance += sub_cost
141		else:
142	1	max_src_letter_match_index = j
143
144	1	if candidate_swap_index != -1 and j_swap != -1:
145	1	i_swap = candidate_swap_index
146
147	1	if i_swap == 0 and j_swap == 0:
148	1	pre_swap_cost = 0
149		else:
150	1	pre_swap_cost = d_mat[
151		max(0, i_swap - 1), max(0, j_swap - 1)
152		]
153	1	swap_distance = (
154		pre_swap_cost
155		+ (i - i_swap - 1) * del_cost
156		+ (j - j_swap - 1) * ins_cost
157		+ trans_cost
158		)
159		else:
160	1	swap_distance = maxsize
161
162	1	d_mat[i, j] = min(
163		del_distance, ins_distance, match_distance, swap_distance
164		)
165	1	src_index_by_character[src[i]] = i
166
167	1	return d_mat[len(src) - 1, len(tar) - 1]
168
169	1	def dist(self, src, tar, cost=(1, 1, 1, 1)):
		0 ignored issues – show Bug introduced 2018-11-04 08:02 UTC by Report Bug Copy Issue Report Parameters differ from overridden 'dist' method Loading history...
170		"""Return the Damerau-Levenshtein similarity of two strings.
171
172		Damerau-Levenshtein distance normalized to the interval [0, 1].
173
174		The Damerau-Levenshtein distance is normalized by dividing the
175		Damerau-Levenshtein distance by the greater of
176		the number of characters in src times the cost of a delete and
177		the number of characters in tar times the cost of an insert.
178		For the case in which all operations have :math:`cost = 1`, this is
179		equivalent to the greater of the length of the two strings src & tar.
180
181		Args:
182		src (str): Source string for comparison
183		tar (str): Target string for comparison
184		cost (tuple): a 4-tuple representing the cost of the four possible
185		edits: inserts, deletes, substitutions, and transpositions,
186		respectively (by default: (1, 1, 1, 1))
187
188		Returns:
189		float: The normalized Damerau-Levenshtein distance
190
191		Examples:
192		>>> cmp = DamerauLevenshtein()
193		>>> round(cmp.dist('cat', 'hat'), 12)
194		0.333333333333
195		>>> round(cmp.dist('Niall', 'Neil'), 12)
196		0.6
197		>>> cmp.dist('aluminum', 'Catalan')
198		0.875
199		>>> cmp.dist('ATCG', 'TAGC')
200		0.5
201
202		"""
203	1	if src == tar:
204	1	return 0.0
205	1	ins_cost, del_cost = cost[:2]
206	1	return self.dist_abs(src, tar, cost) / (
207		max(len(src) * del_cost, len(tar) * ins_cost)
208		)
209
210
211	1	def damerau_levenshtein(src, tar, cost=(1, 1, 1, 1)):
212		"""Return the Damerau-Levenshtein distance between two strings.
213
214		This is a wrapper of :py:meth:`DamerauLevenshtein.dist_abs`.
215
216		Args:
217		src (str): Source string for comparison
218		tar (str): Target string for comparison
219		cost (tuple): a 4-tuple representing the cost of the four possible
220		edits: inserts, deletes, substitutions, and transpositions,
221		respectively (by default: (1, 1, 1, 1))
222
223		Returns:
224		int (may return a float if cost has float values): The
225		Damerau-Levenshtein distance between src & tar
226
227		Examples:
228		>>> damerau_levenshtein('cat', 'hat')
229		1
230		>>> damerau_levenshtein('Niall', 'Neil')
231		3
232		>>> damerau_levenshtein('aluminum', 'Catalan')
233		7
234		>>> damerau_levenshtein('ATCG', 'TAGC')
235		2
236
237		"""
238	1	return DamerauLevenshtein().dist_abs(src, tar, cost)
239
240
241	1	def dist_damerau(src, tar, cost=(1, 1, 1, 1)):
242		"""Return the Damerau-Levenshtein similarity of two strings.
243
244		This is a wrapper of :py:meth:`DamerauLevenshtein.dist`.
245
246		Args:
247		src (str): Source string for comparison
248		tar (str): Target string for comparison
249		cost (tuple): a 4-tuple representing the cost of the four possible
250		edits: inserts, deletes, substitutions, and transpositions,
251		respectively (by default: (1, 1, 1, 1))
252
253		Returns:
254		float: The normalized Damerau-Levenshtein distance
255
256		Examples:
257		>>> round(dist_damerau('cat', 'hat'), 12)
258		0.333333333333
259		>>> round(dist_damerau('Niall', 'Neil'), 12)
260		0.6
261		>>> dist_damerau('aluminum', 'Catalan')
262		0.875
263		>>> dist_damerau('ATCG', 'TAGC')
264		0.5
265
266		"""
267	1	return DamerauLevenshtein().dist(src, tar, cost)
268
269
270	1	def sim_damerau(src, tar, cost=(1, 1, 1, 1)):
271		"""Return the Damerau-Levenshtein similarity of two strings.
272
273		This is a wrapper of :py:meth:`DamerauLevenshtein.sim`.
274
275		Args:
276		src (str): Source string for comparison
277		tar (str): Target string for comparison
278		cost (tuple): a 4-tuple representing the cost of the four possible
279		edits: inserts, deletes, substitutions, and transpositions,
280		respectively (by default: (1, 1, 1, 1))
281
282		Returns:
283		float: The normalized Damerau-Levenshtein similarity
284
285		Examples:
286		>>> round(sim_damerau('cat', 'hat'), 12)
287		0.666666666667
288		>>> round(sim_damerau('Niall', 'Neil'), 12)
289		0.4
290		>>> sim_damerau('aluminum', 'Catalan')
291		0.125
292		>>> sim_damerau('ATCG', 'TAGC')
293		0.5
294
295		"""
296	1	return DamerauLevenshtein().sim(src, tar, cost)
297
298
299		if __name__ == '__main__':
300		import doctest
301
302		doctest.testmod()
303

chrislit / abydos

Pull Request — master (#141)

abydos.distance._damerau_levenshtein.sim_damerau() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like