abydos/distance/_goodall.py
# 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._goodall.
Goodall similarity
"""
from math import asin, pi
from typing import Any, Counter as TCounter, Optional, Sequence, Set, Union
from ._token_distance import _TokenDistance
from ..tokenizer import _Tokenizer
__all__ = ['Goodall']
class Goodall(_TokenDistance):
r"""Goodall similarity.
For two sets X and Y and a population N, Goodall similarity
:cite:`Goodall:1967,Austin:1977` is an angular transformation of Sokal
& Michener's simple matching coefficient
.. math::
sim_{Goodall}(X, Y) = \frac{2}{\pi} \sin^{-1}\Big(
\sqrt{\frac{|X \cap Y| + |(N \setminus X) \setminus Y|}{|N|}}
\Big)
In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n,
this is
.. math::
sim_{Goodall} =\frac{2}{\pi} \sin^{-1}\Big(
\sqrt{\frac{a + d}{n}}
\Big)
.. 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 Goodall 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(Goodall, self).__init__(
alphabet=alphabet,
tokenizer=tokenizer,
intersection_type=intersection_type,
**kwargs
)
def sim(self, src: str, tar: str) -> float:
"""Return the Goodall 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
Goodall similarity
Examples
--------
>>> cmp = Goodall()
>>> cmp.sim('cat', 'hat')
0.9544884026871964
>>> cmp.sim('Niall', 'Neil')
0.9397552079794624
>>> cmp.sim('aluminum', 'Catalan')
0.9117156301536503
>>> cmp.sim('ATCG', 'TAGC')
0.9279473952929225
.. versionadded:: 0.4.0
"""
if src == tar:
return 1.0
self._tokenize(src, tar)
a = self._intersection_card()
d = self._total_complement_card()
n = self._population_unique_card()
return 2 / pi * asin(((a + d) / n) ** 0.5)
if __name__ == '__main__':
import doctest
doctest.testmod()