# 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._mcconnaughey.
McConnaughey correlation
"""
from ._token_distance import _TokenDistance
__all__ = ['McConnaughey']
[docs]class McConnaughey(_TokenDistance):
r"""McConnaughey correlation.
For two sets X and Y, McConnaughey correlation :cite:`McConnaughey:1964` is
.. math::
corr_{McConnaughey}(X, Y) =
\frac{|X \cap Y|^2 - |X \setminus Y| \cdot |Y \setminus X|}
{|X| \cdot |Y|}
In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n,
this is
.. math::
corr_{McConnaughey} =
\frac{a^2-bc}{(a+b)(a+c)}
.. versionadded:: 0.4.0
"""
def __init__(
self,
alphabet=None,
tokenizer=None,
intersection_type='crisp',
**kwargs
):
"""Initialize McConnaughey instance.
Parameters
----------
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(McConnaughey, self).__init__(
alphabet=alphabet,
tokenizer=tokenizer,
intersection_type=intersection_type,
**kwargs
)
[docs] def corr(self, src, tar):
"""Return the McConnaughey 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
McConnaughey correlation
Examples
--------
>>> cmp = McConnaughey()
>>> cmp.corr('cat', 'hat')
0.0
>>> cmp.corr('Niall', 'Neil')
-0.26666666666666666
>>> cmp.corr('aluminum', 'Catalan')
-0.7638888888888888
>>> cmp.corr('ATCG', 'TAGC')
-1.0
.. versionadded:: 0.4.0
"""
if src == tar:
return 1.0
self._tokenize(src, tar)
num = (
self._intersection_card() ** 2
- self._src_only_card() * self._tar_only_card()
)
if num:
return num / (self._src_card() * self._tar_card())
return 0.0
[docs] def sim(self, src, tar):
"""Return the McConnaughey 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
McConnaughey similarity
Examples
--------
>>> cmp = McConnaughey()
>>> cmp.sim('cat', 'hat')
0.5
>>> cmp.sim('Niall', 'Neil')
0.3666666666666667
>>> cmp.sim('aluminum', 'Catalan')
0.11805555555555558
>>> cmp.sim('ATCG', 'TAGC')
0.0
.. versionadded:: 0.4.0
"""
return (1.0 + self.corr(src, tar)) / 2.0
if __name__ == '__main__':
import doctest
doctest.testmod()