abydos.distance._flexmetric.FlexMetric.__init__() - Code Metrics - Inspection of "0.6.0b" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#257)

by Chris

created 2020-02-09 23:29 UTC

abydos.distance._flexmetric.FlexMetric.init() B

↳ Parent: abydos.distance._flexmetric

Complexity

Conditions

Size

Total Lines	71
Code Lines	37

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	10
CRAP Score	3

Importance

Changes

Metric	Value
eloc	37
dl	0
loc	71
ccs	10
cts	10
cp	1
rs	8.9919
c	0
b	0
f	0
cc	3
nop	5
crap	3

How to fix Long Method

# Copyright 2019-2020 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._flexmetric.

FlexMetric distance
"""

from typing import Any, Callable, Collection, List, Optional, Tuple, cast

from numpy import float_ as np_float
from numpy import zeros as np_zeros

from ._distance import _Distance

__all__ = ['FlexMetric']


class FlexMetric(_Distance):
    r"""FlexMetric distance.

    FlexMetric distance :cite:`Kempken:2005`

    .. versionadded:: 0.4.0
    """

    def __init__(
        self,
        normalizer: Callable[[List[float]], float] = max,
        indel_costs: Optional[List[Tuple[Collection[str], float]]] = None,
        subst_costs: Optional[List[Tuple[Collection[str], float]]] = None,
        **kwargs: Any
    ) -> None:
        """Initialize FlexMetric instance.

        Parameters
        ----------
        normalizer : function
            A function that takes an list and computes a normalization term
            by which the edit distance is divided (max by default). Another
            good option is the sum function.
        indel_costs : list of tuples
            A list of insertion and deletion costs. Each list element should
            be a tuple consisting of an iterable (sets are best) and a float
            value. The iterable consists of those letters whose insertion
            or deletion has a cost equal to the float value.
        subst_costs : list of tuples
            A list of substitution costs. Each list element should
            be a tuple consisting of an iterable (sets are best) and a float
            value. The iterable consists of the letters in each letter class,
            which may be substituted for each other at cost equal to the float
            value.
        **kwargs
            Arbitrary keyword arguments


        .. versionadded:: 0.4.0

        """
        super(FlexMetric, self).__init__(**kwargs)
        self._normalizer = normalizer

        def _get_second(s: Tuple[Collection[str], float]) -> float:
            return s[1]

        if indel_costs is None:
            self._indel_costs = [
                (frozenset('dtch'), 0.4),
                (frozenset('e'), 0.5),
                (frozenset('u'), 0.9),
                (frozenset('rpn'), 0.95),
            ]  # type: List[Tuple[Collection[str], float]]
        else:
            self._indel_costs = sorted(indel_costs, key=_get_second)

        if subst_costs is None:
            self._subst_costs = [
                (frozenset('szß'), 0.1),
                (frozenset('dt'), 0.1),
                (frozenset('iy'), 0.1),
                (frozenset('ckq'), 0.1),
                (frozenset('eä'), 0.1),
                (frozenset('uüv'), 0.1),
                (frozenset('iü'), 0.1),
                (frozenset('fv'), 0.1),
                (frozenset('zc'), 0.1),
                (frozenset('ij'), 0.1),
                (frozenset('bp'), 0.1),
                (frozenset('eoö'), 0.2),
                (frozenset('aä'), 0.2),
                (frozenset('mbp'), 0.4),
                (frozenset('uw'), 0.4),
                (frozenset('uo'), 0.8),
                (frozenset('aeiouy'), 0.9),
            ]  # type: List[Tuple[Collection[str], float]]
        else:
            self._subst_costs = sorted(subst_costs, key=_get_second)

    def _cost(self, src: str, s_pos: int, tar: str, t_pos: int) -> float:
        if s_pos == -1:
            if t_pos > 0 and tar[t_pos - 1] == tar[t_pos]:
                return 0.0
            for letter_set in self._indel_costs:
                if tar[t_pos] in letter_set[0]:
                    return letter_set[1]
            else:
                return 1.0
        elif t_pos == -1:
            if s_pos > 0 and src[s_pos - 1] == src[s_pos]:
                return 0.0
            for letter_set in self._indel_costs:
                if src[s_pos] in letter_set[0]:
                    return letter_set[1]
            else:
                return 1.0
        for letter_set in self._subst_costs:
            if src[s_pos] in letter_set[0] and tar[t_pos] in letter_set[0]:
                return letter_set[1]
        else:
            return 1.0

    def dist_abs(self, src: str, tar: str) -> float:
        """Return the FlexMetric distance of two strings.

        Parameters
        ----------
        src : str
            Source string for comparison
        tar : str
            Target string for comparison

        Returns
        -------
        float
            FlexMetric distance

        Examples
        --------
        >>> cmp = FlexMetric()
        >>> cmp.dist_abs('cat', 'hat')
        0.8
        >>> cmp.dist_abs('Niall', 'Neil')
        1.5
        >>> cmp.dist_abs('aluminum', 'Catalan')
        6.7
        >>> cmp.dist_abs('ATCG', 'TAGC')
        2.1999999999999997


        .. versionadded:: 0.4.0

        """
        src_len = len(src)
        tar_len = len(tar)

        if src == tar:
            return 0
        if not src:
            return sum(self._cost('', -1, tar, j) for j in range(len(tar)))
        if not tar:
            return sum(self._cost(src, i, '', -1) for i in range(len(src)))

        d_mat = np_zeros((src_len + 1, tar_len + 1), dtype=np_float)
        for i in range(1, src_len + 1):
            d_mat[i, 0] = d_mat[i - 1, 0] + self._cost(src, i - 1, '', -1)
        for j in range(1, tar_len + 1):
            d_mat[0, j] = d_mat[0, j - 1] + self._cost('', -1, tar, j - 1)

        src_lc = src.lower()
        tar_lc = tar.lower()

        for i in range(src_len):
            for j in range(tar_len):
                d_mat[i + 1, j + 1] = min(
                    d_mat[i + 1, j] + self._cost('', -1, tar_lc, j),  # ins
                    d_mat[i, j + 1] + self._cost(src_lc, i, '', -1),  # del
                    d_mat[i, j]
                    + (
                        self._cost(src_lc, i, tar_lc, j)
                        if src[i] != tar[j]
                        else 0
                    ),  # sub/==
                )

        return cast(float, d_mat[src_len, tar_len])

    def dist(self, src: str, tar: str) -> float:
        """Return the normalized FlexMetric distance of two strings.

        Parameters
        ----------
        src : str
            Source string for comparison
        tar : str
            Target string for comparison

        Returns
        -------
        float
            Normalized FlexMetric distance

        Examples
        --------
        >>> cmp = FlexMetric()
        >>> cmp.dist('cat', 'hat')
        0.26666666666666666
        >>> cmp.dist('Niall', 'Neil')
        0.3
        >>> cmp.dist('aluminum', 'Catalan')
        0.8375
        >>> cmp.dist('ATCG', 'TAGC')
        0.5499999999999999


        .. versionadded:: 0.4.0

        """
        score = self.dist_abs(src, tar)
        if score:
            return score / self._normalizer([len(src), len(tar)])
        return 0.0


if __name__ == '__main__':
    import doctest

    doctest.testmod()


1		# Copyright 2019-2020 by Christopher C. Little.
2		# This file is part of Abydos.
3		#
4		# Abydos is free software: you can redistribute it and/or modify
5		# it under the terms of the GNU General Public License as published by
6		# the Free Software Foundation, either version 3 of the License, or
7		# (at your option) any later version.
8		#
9		# Abydos is distributed in the hope that it will be useful,
10		# but WITHOUT ANY WARRANTY; without even the implied warranty of
11		# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12		# GNU General Public License for more details.
13		#
14		# You should have received a copy of the GNU General Public License
15		# along with Abydos. If not, see <http://www.gnu.org/licenses/>.
16
17		"""abydos.distance._flexmetric.
18
19	1	FlexMetric distance
20		"""
21
22		from typing import Any, Callable, Collection, List, Optional, Tuple, cast
23
24	1	from numpy import float_ as np_float
25		from numpy import zeros as np_zeros
26
27		from ._distance import _Distance
28
29		__all__ = ['FlexMetric']
30
31	1
32	1	class FlexMetric(_Distance):
33		r"""FlexMetric distance.
34	1
35		FlexMetric distance :cite:`Kempken:2005`
36	1
37		.. versionadded:: 0.4.0
38		"""
39	1
40		def __init__(
41		self,
42		normalizer: Callable[[List[float]], float] = max,
43		indel_costs: Optional[List[Tuple[Collection[str], float]]] = None,
44		subst_costs: Optional[List[Tuple[Collection[str], float]]] = None,
45		**kwargs: Any
46		) -> None:
47	1	"""Initialize FlexMetric instance.
48
49		Parameters
50		----------
51		normalizer : function
52		A function that takes an list and computes a normalization term
53		by which the edit distance is divided (max by default). Another
54		good option is the sum function.
55		indel_costs : list of tuples
56		A list of insertion and deletion costs. Each list element should
57		be a tuple consisting of an iterable (sets are best) and a float
58		value. The iterable consists of those letters whose insertion
59		or deletion has a cost equal to the float value.
60		subst_costs : list of tuples
61		A list of substitution costs. Each list element should
62		be a tuple consisting of an iterable (sets are best) and a float
63		value. The iterable consists of the letters in each letter class,
64		which may be substituted for each other at cost equal to the float
65		value.
66		**kwargs
67		Arbitrary keyword arguments
68
69
70		.. versionadded:: 0.4.0
71
72		"""
73		super(FlexMetric, self).__init__(**kwargs)
74		self._normalizer = normalizer
75
76	1	def _get_second(s: Tuple[Collection[str], float]) -> float:
77	1	return s[1]
78
79	1	if indel_costs is None:
80	1	self._indel_costs = [
81		(frozenset('dtch'), 0.4),
82		(frozenset('e'), 0.5),
83		(frozenset('u'), 0.9),
84		(frozenset('rpn'), 0.95),
85		] # type: List[Tuple[Collection[str], float]]
86		else:
87	1	self._indel_costs = sorted(indel_costs, key=_get_second)
88
89	1	if subst_costs is None:
90	1	self._subst_costs = [
91		(frozenset('szß'), 0.1),
92	1	(frozenset('dt'), 0.1),
93	1	(frozenset('iy'), 0.1),
94		(frozenset('ckq'), 0.1),
95		(frozenset('eä'), 0.1),
96		(frozenset('uüv'), 0.1),
97		(frozenset('iü'), 0.1),
98		(frozenset('fv'), 0.1),
99		(frozenset('zc'), 0.1),
100		(frozenset('ij'), 0.1),
101		(frozenset('bp'), 0.1),
102		(frozenset('eoö'), 0.2),
103		(frozenset('aä'), 0.2),
104		(frozenset('mbp'), 0.4),
105		(frozenset('uw'), 0.4),
106		(frozenset('uo'), 0.8),
107		(frozenset('aeiouy'), 0.9),
108		] # type: List[Tuple[Collection[str], float]]
109		else:
110		self._subst_costs = sorted(subst_costs, key=_get_second)
111
112		def _cost(self, src: str, s_pos: int, tar: str, t_pos: int) -> float:
113	1	if s_pos == -1:
114		if t_pos > 0 and tar[t_pos - 1] == tar[t_pos]:
115	1	return 0.0
116	1	for letter_set in self._indel_costs:
117	1	if tar[t_pos] in letter_set[0]:
118	1	return letter_set[1]
119	1	else:
120	1	return 1.0
121	1	elif t_pos == -1:
122		if s_pos > 0 and src[s_pos - 1] == src[s_pos]:
123	1	return 0.0
124	1	for letter_set in self._indel_costs:
125	1	if src[s_pos] in letter_set[0]:
126	1	return letter_set[1]
127	1	else:
128	1	return 1.0
129	1	for letter_set in self._subst_costs:
130		if src[s_pos] in letter_set[0] and tar[t_pos] in letter_set[0]:
131	1	return letter_set[1]
132	1	else:
133	1	return 1.0
134	1
135		def dist_abs(self, src: str, tar: str) -> float:
136	1	"""Return the FlexMetric distance of two strings.
137
138	1	Parameters
139		----------
140		src : str
141		Source string for comparison
142		tar : str
143		Target string for comparison
144
145		Returns
146		-------
147		float
148		FlexMetric distance
149
150		Examples
151		--------
152		>>> cmp = FlexMetric()
153		>>> cmp.dist_abs('cat', 'hat')
154		0.8
155		>>> cmp.dist_abs('Niall', 'Neil')
156		1.5
157		>>> cmp.dist_abs('aluminum', 'Catalan')
158		6.7
159		>>> cmp.dist_abs('ATCG', 'TAGC')
160		2.1999999999999997
161
162
163		.. versionadded:: 0.4.0
164
165		"""
166		src_len = len(src)
167		tar_len = len(tar)
168
169	1	if src == tar:
170	1	return 0
171		if not src:
172	1	return sum(self._cost('', -1, tar, j) for j in range(len(tar)))
173	1	if not tar:
174	1	return sum(self._cost(src, i, '', -1) for i in range(len(src)))
175	1
176	1	d_mat = np_zeros((src_len + 1, tar_len + 1), dtype=np_float)
177	1	for i in range(1, src_len + 1):
178		d_mat[i, 0] = d_mat[i - 1, 0] + self._cost(src, i - 1, '', -1)
179	1	for j in range(1, tar_len + 1):
180	1	d_mat[0, j] = d_mat[0, j - 1] + self._cost('', -1, tar, j - 1)
181	1
182	1	src_lc = src.lower()
183	1	tar_lc = tar.lower()
184
185	1	for i in range(src_len):
186	1	for j in range(tar_len):
187		d_mat[i + 1, j + 1] = min(
188	1	d_mat[i + 1, j] + self._cost('', -1, tar_lc, j), # ins
189	1	d_mat[i, j + 1] + self._cost(src_lc, i, '', -1), # del
190	1	d_mat[i, j]
191		+ (
192		self._cost(src_lc, i, tar_lc, j)
193		if src[i] != tar[j]
194		else 0
195		), # sub/==
196		)
197
198		return cast(float, d_mat[src_len, tar_len])
199
200		def dist(self, src: str, tar: str) -> float:
201	1	"""Return the normalized FlexMetric distance of two strings.
202
203	1	Parameters
204		----------
205		src : str
206		Source string for comparison
207		tar : str
208		Target string for comparison
209
210		Returns
211		-------
212		float
213		Normalized FlexMetric distance
214
215		Examples
216		--------
217		>>> cmp = FlexMetric()
218		>>> cmp.dist('cat', 'hat')
219		0.26666666666666666
220		>>> cmp.dist('Niall', 'Neil')
221		0.3
222		>>> cmp.dist('aluminum', 'Catalan')
223		0.8375
224		>>> cmp.dist('ATCG', 'TAGC')
225		0.5499999999999999
226
227
228		.. versionadded:: 0.4.0
229
230		"""
231		score = self.dist_abs(src, tar)
232		if score:
233		return score / self._normalizer([len(src), len(tar)])
234	1	return 0.0
235	1
236	1
237	1	if __name__ == '__main__':
238		import doctest
239
240		doctest.testmod()
241

chrislit / abydos

Pull Request — master (#257)

abydos.distance._flexmetric.FlexMetric.__init__() B

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like

abydos.distance._flexmetric.FlexMetric.init() B