Source code for abydos.distance._yule_q

# 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._yule_q.

Yule's Q correlation
"""

from ._token_distance import _TokenDistance

__all__ = ['YuleQ']


[docs]class YuleQ(_TokenDistance): r"""Yule's Q correlation. For two sets X and Y and a population N, Yule's Q correlation :cite:`Yule:1912` is .. math:: corr_{Yule_Q}(X, Y) = \frac{|X \cap Y| \cdot |(N \setminus X) \setminus Y| - |X \setminus Y| \cdot |Y \setminus X|} {|X \cap Y| \cdot |(N \setminus X) \setminus Y| + |X \setminus Y| \cdot |Y \setminus X|} Yule himself terms this the coefficient of association. In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n, this is .. math:: corr_{Yule_Q} = \frac{ad-bc}{ad+bc} .. versionadded:: 0.4.0 """ def __init__( self, alphabet=None, tokenizer=None, intersection_type='crisp', **kwargs ): """Initialize YuleQ 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(YuleQ, self).__init__( alphabet=alphabet, tokenizer=tokenizer, intersection_type=intersection_type, **kwargs )
[docs] def corr(self, src, tar): """Return Yule's Q 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 Yule's Q correlation Examples -------- >>> cmp = YuleQ() >>> cmp.corr('cat', 'hat') 0.9948717948717949 >>> cmp.corr('Niall', 'Neil') 0.9846350832266325 >>> cmp.corr('aluminum', 'Catalan') 0.8642424242424243 >>> cmp.corr('ATCG', 'TAGC') -1.0 .. 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() admbc = a * d - b * c if admbc: return admbc / (a * d + b * c) return 0.0
[docs] def sim(self, src, tar): """Return Yule's Q 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 Yule's Q similarity Examples -------- >>> cmp = YuleQ() >>> cmp.sim('cat', 'hat') 0.9974358974358974 >>> cmp.sim('Niall', 'Neil') 0.9923175416133163 >>> cmp.sim('aluminum', 'Catalan') 0.9321212121212121 >>> 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()