abydos.distance._pearson_chi_squared.PearsonChiSquared.sim() - Code Metrics - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

PearsonChiSquared.sim() A
last analyzed 2020-12-31 20:10 UTC

↳ Parent: abydos.distance._pearson_chi_squared

Complexity

Conditions

Size

Total Lines	32
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	3
CRAP Score	1

Importance

Changes

Metric	Value
eloc	2
dl	0
loc	32
ccs	3
cts	3
cp	1
rs	10
c	0
b	0
f	0
cc	1
nop	3
crap	1

# Copyright 2018-2020 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._pearson_chi_squared.

Pearson's Chi-Squared similarity
"""

from math import copysign
from typing import Any, Counter as TCounter, Optional, Sequence, Set, Union

from ._token_distance import _TokenDistance
from ..tokenizer import _Tokenizer

__all__ = ['PearsonChiSquared']


class PearsonChiSquared(_TokenDistance):
    r"""Pearson's Chi-Squared similarity.

    For two sets X and Y and a population N, the Pearson's :math:`\chi^2`
    similarity :cite:`Pearson:1913` is

        .. math::

            sim_{PearsonChiSquared}(X, Y) =
            \frac{|N| \cdot (|X \cap Y| \cdot |(N \setminus X) \setminus Y| -
            |X \setminus Y| \cdot |Y \setminus X|)^2}
            {|X| \cdot |Y| \cdot |N \setminus X| \cdot |N \setminus Y|}

    This is also Pearson I similarity.

    In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n,
    this is

        .. math::

            sim_{PearsonChiSquared} =
            \frac{n(ad-bc)^2}{(a+b)(a+c)(b+d)(c+d)}

    .. versionadded:: 0.4.0
    """

    def __init__(
        self,
        alphabet: Optional[
            Union[TCounter[str], Sequence[str], Set[str], int]
        ] = None,
        tokenizer: Optional[_Tokenizer] = None,
        intersection_type: str = 'crisp',
        **kwargs: Any
    ) -> None:
        """Initialize PearsonChiSquared instance.

        Parameters
        ----------
        alphabet : Counter, collection, int, or None
            This represents the alphabet of possible tokens.
            See :ref:`alphabet <alphabet>` description in
            :py:class:`_TokenDistance` for details.
        tokenizer : _Tokenizer
            A tokenizer instance from the :py:mod:`abydos.tokenizer` package
        intersection_type : str
            Specifies the intersection type, and set type as a result:
            See :ref:`intersection_type <intersection_type>` description in
            :py:class:`_TokenDistance` for details.
        **kwargs
            Arbitrary keyword arguments

        Other Parameters
        ----------------
        qval : int
            The length of each q-gram. Using this parameter and tokenizer=None
            will cause the instance to use the QGram tokenizer with this
            q value.
        metric : _Distance
            A string distance measure class for use in the ``soft`` and
            ``fuzzy`` variants.
        threshold : float
            A threshold value, similarities above which are counted as
            members of the intersection for the ``fuzzy`` variant.


        .. versionadded:: 0.4.0

        """
        super(PearsonChiSquared, self).__init__(
            alphabet=alphabet,
            tokenizer=tokenizer,
            intersection_type=intersection_type,
            **kwargs
        )

    def sim_score(self, src: str, tar: str) -> float:

        """Return Pearson's Chi-Squared similarity of two strings.

        Parameters
        ----------
        src : str
            Source string (or QGrams/Counter objects) for comparison
        tar : str
            Target string (or QGrams/Counter objects) for comparison

        Returns
        -------
        float
            Pearson's Chi-Squared similarity

        Examples
        --------
        >>> cmp = PearsonChiSquared()
        >>> cmp.sim_score('cat', 'hat')
        193.99489809335964
        >>> cmp.sim_score('Niall', 'Neil')
        101.99771068526542
        >>> cmp.sim_score('aluminum', 'Catalan')
        9.19249664336649
        >>> cmp.sim_score('ATCG', 'TAGC')
        0.032298410951138765


        .. versionadded:: 0.4.0

        """
        self._tokenize(src, tar)

        a = self._intersection_card()
        b = self._src_only_card()
        c = self._tar_only_card()
        d = self._total_complement_card()
        n = self._population_unique_card()
        ab = self._src_card()
        ac = self._tar_card()

        if src == tar:
            return float(n)
        if not src or not tar:
            return 0.0
        num = n * (a * d - b * c) ** 2
        if num:
            return num / (ab * ac * (b + d) * (c + d))
        return 0.0

    def corr(self, src: str, tar: str) -> float:
        """Return Pearson's Chi-Squared correlation of two strings.

        Parameters
        ----------
        src : str
            Source string (or QGrams/Counter objects) for comparison
        tar : str
            Target string (or QGrams/Counter objects) for comparison

        Returns
        -------
        float
            Pearson's Chi-Squared correlation

        Examples
        --------
        >>> cmp = PearsonChiSquared()
        >>> cmp.corr('cat', 'hat')
        0.2474424720578567
        >>> cmp.corr('Niall', 'Neil')
        0.1300991207720222
        >>> cmp.corr('aluminum', 'Catalan')
        0.011710186806836291
        >>> cmp.corr('ATCG', 'TAGC')
        -4.1196952743799446e-05


        .. versionadded:: 0.4.0

        """
        if src == tar:
            return 1.0

        score = self.sim_score(src, tar)

        a = self._intersection_card()
        b = self._src_only_card()
        c = self._tar_only_card()
        d = self._total_complement_card()

        score /= a + b + c + d

        return copysign(score, a * d - b * c)

    def sim(self, src: str, tar: str) -> float:
        """Return Pearson's normalized Chi-Squared similarity of two strings.

        Parameters
        ----------
        src : str
            Source string (or QGrams/Counter objects) for comparison
        tar : str
            Target string (or QGrams/Counter objects) for comparison

        Returns
        -------
        float
            Normalized Pearson's Chi-Squared similarity

        Examples
        --------
        >>> cmp = PearsonChiSquared()
        >>> cmp.corr('cat', 'hat')
        0.2474424720578567
        >>> cmp.corr('Niall', 'Neil')
        0.1300991207720222
        >>> cmp.corr('aluminum', 'Catalan')
        0.011710186806836291
        >>> cmp.corr('ATCG', 'TAGC')
        -4.1196952743799446e-05


        .. versionadded:: 0.4.0

        """
        return (1.0 + self.corr(src, tar)) / 2.0


if __name__ == '__main__':
    import doctest

    doctest.testmod()


1			# Copyright 2018-2020 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._pearson_chi_squared.
18
19	1		Pearson's Chi-Squared similarity
20			"""
21
22			from math import copysign
23			from typing import Any, Counter as TCounter, Optional, Sequence, Set, Union
24	1
25			from ._token_distance import _TokenDistance
26			from ..tokenizer import _Tokenizer
27
28			__all__ = ['PearsonChiSquared']
29
30
31	1		class PearsonChiSquared(_TokenDistance):
32			r"""Pearson's Chi-Squared similarity.
33	1
34			For two sets X and Y and a population N, the Pearson's :math:`\chi^2`
35	1		similarity :cite:`Pearson:1913` is
36
37			.. math::
38	1
39			sim_{PearsonChiSquared}(X, Y) =
40			\frac{\|N\| \cdot (\|X \cap Y\| \cdot \|(N \setminus X) \setminus Y\| -
41			\|X \setminus Y\| \cdot \|Y \setminus X\|)^2}
42			{\|X\| \cdot \|Y\| \cdot \|N \setminus X\| \cdot \|N \setminus Y\|}
43
44			This is also Pearson I similarity.
45
46			In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n,
47			this is
48
49			.. math::
50
51			sim_{PearsonChiSquared} =
52			\frac{n(ad-bc)^2}{(a+b)(a+c)(b+d)(c+d)}
53
54			.. versionadded:: 0.4.0
55			"""
56
57			def __init__(
58			self,
59			alphabet: Optional[
60			Union[TCounter[str], Sequence[str], Set[str], int]
61			] = None,
62			tokenizer: Optional[_Tokenizer] = None,
63			intersection_type: str = 'crisp',
64	1		**kwargs: Any
65			) -> None:
66			"""Initialize PearsonChiSquared instance.
67
68			Parameters
69			----------
70			alphabet : Counter, collection, int, or None
71			This represents the alphabet of possible tokens.
72			See :ref:`alphabet <alphabet>` description in
73			:py:class:`_TokenDistance` for details.
74			tokenizer : _Tokenizer
75			A tokenizer instance from the :py:mod:`abydos.tokenizer` package
76			intersection_type : str
77			Specifies the intersection type, and set type as a result:
78			See :ref:`intersection_type <intersection_type>` description in
79			:py:class:`_TokenDistance` for details.
80			**kwargs
81			Arbitrary keyword arguments
82
83			Other Parameters
84			----------------
85			qval : int
86			The length of each q-gram. Using this parameter and tokenizer=None
87			will cause the instance to use the QGram tokenizer with this
88			q value.
89			metric : _Distance
90			A string distance measure class for use in the ``soft`` and
91			``fuzzy`` variants.
92			threshold : float
93			A threshold value, similarities above which are counted as
94			members of the intersection for the ``fuzzy`` variant.
95
96
97			.. versionadded:: 0.4.0
98
99			"""
100			super(PearsonChiSquared, self).__init__(
101			alphabet=alphabet,
102			tokenizer=tokenizer,
103			intersection_type=intersection_type,
104			**kwargs
105	1		)
106
107		View Code Duplication	def sim_score(self, src: str, tar: str) -> float:
			0 ignored issues – show Duplication introduced 2020-02-09 23:37 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
108			"""Return Pearson's Chi-Squared similarity of two strings.
109
110			Parameters
111			----------
112	1		src : str
113			Source string (or QGrams/Counter objects) for comparison
114			tar : str
115			Target string (or QGrams/Counter objects) for comparison
116
117			Returns
118			-------
119			float
120			Pearson's Chi-Squared similarity
121
122			Examples
123			--------
124			>>> cmp = PearsonChiSquared()
125			>>> cmp.sim_score('cat', 'hat')
126			193.99489809335964
127			>>> cmp.sim_score('Niall', 'Neil')
128			101.99771068526542
129			>>> cmp.sim_score('aluminum', 'Catalan')
130			9.19249664336649
131			>>> cmp.sim_score('ATCG', 'TAGC')
132			0.032298410951138765
133
134
135			.. versionadded:: 0.4.0
136
137			"""
138			self._tokenize(src, tar)
139
140			a = self._intersection_card()
141			b = self._src_only_card()
142			c = self._tar_only_card()
143	1		d = self._total_complement_card()
144			n = self._population_unique_card()
145	1		ab = self._src_card()
146	1		ac = self._tar_card()
147	1
148	1		if src == tar:
149	1		return float(n)
150	1		if not src or not tar:
151	1		return 0.0
152			num = n * (a * d - b * c) ** 2
153	1		if num:
154	1		return num / (ab * ac * (b + d) * (c + d))
155	1		return 0.0
156	1
157	1		def corr(self, src: str, tar: str) -> float:
158	1		"""Return Pearson's Chi-Squared correlation of two strings.
159	1
160			Parameters
161			----------
162	1		src : str
163			Source string (or QGrams/Counter objects) for comparison
164			tar : str
165			Target string (or QGrams/Counter objects) for comparison
166
167			Returns
168			-------
169			float
170			Pearson's Chi-Squared correlation
171
172			Examples
173			--------
174			>>> cmp = PearsonChiSquared()
175			>>> cmp.corr('cat', 'hat')
176			0.2474424720578567
177			>>> cmp.corr('Niall', 'Neil')
178			0.1300991207720222
179			>>> cmp.corr('aluminum', 'Catalan')
180			0.011710186806836291
181			>>> cmp.corr('ATCG', 'TAGC')
182			-4.1196952743799446e-05
183
184
185			.. versionadded:: 0.4.0
186
187			"""
188			if src == tar:
189			return 1.0
190
191			score = self.sim_score(src, tar)
192
193	1		a = self._intersection_card()
194	1		b = self._src_only_card()
195			c = self._tar_only_card()
196	1		d = self._total_complement_card()
197
198	1		score /= a + b + c + d
199	1
200	1		return copysign(score, a * d - b * c)
201	1
202			def sim(self, src: str, tar: str) -> float:
203	1		"""Return Pearson's normalized Chi-Squared similarity of two strings.
204
205	1		Parameters
206			----------
207	1		src : str
208			Source string (or QGrams/Counter objects) for comparison
209			tar : str
210			Target string (or QGrams/Counter objects) for comparison
211
212			Returns
213			-------
214			float
215			Normalized Pearson's Chi-Squared similarity
216
217			Examples
218			--------
219			>>> cmp = PearsonChiSquared()
220			>>> cmp.corr('cat', 'hat')
221			0.2474424720578567
222			>>> cmp.corr('Niall', 'Neil')
223			0.1300991207720222
224			>>> cmp.corr('aluminum', 'Catalan')
225			0.011710186806836291
226			>>> cmp.corr('ATCG', 'TAGC')
227			-4.1196952743799446e-05
228
229
230			.. versionadded:: 0.4.0
231
232			"""
233			return (1.0 + self.corr(src, tar)) / 2.0
234
235
236			if __name__ == '__main__':
237			import doctest
238	1
239			doctest.testmod()
240

chrislit / abydos

PearsonChiSquared.sim() A last analyzed 2020-12-31 20:10 UTC

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like

PearsonChiSquared.sim() A
last analyzed 2020-12-31 20:10 UTC