Source code for abydos.distance._baulieu_ii

# 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
# 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 <>.


Baulieu II similarity

from ._token_distance import _TokenDistance

__all__ = ['BaulieuII']

[docs]class BaulieuII(_TokenDistance): r"""Baulieu II similarity. For two sets X and Y and a population N, Baulieu II similarity :cite:`Baulieu:1989` is .. math:: sim_{BaulieuII}(X, Y) = \frac{|X \cap Y|^2 \cdot |(N \setminus X) \setminus Y|^2} {|X| \cdot |Y| \cdot |N \setminus X| \cdot |N \setminus Y|} This is based on Baulieu's 13th dissimilarity coefficient. In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n, this is .. math:: sim_{BaulieuII} = \frac{a^2d^2}{(a+b)(a+c)(b+d)(c+d)} .. versionadded:: 0.4.0 """ def __init__( self, alphabet=None, tokenizer=None, intersection_type='crisp', **kwargs ): """Initialize BaulieuII 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(BaulieuII, self).__init__( alphabet=alphabet, tokenizer=tokenizer, intersection_type=intersection_type, **kwargs )
[docs] def sim(self, src, tar): """Return the Baulieu II 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 Baulieu II similarity Examples -------- >>> cmp = BaulieuII() >>> cmp.sim('cat', 'hat') 0.24871959237343852 >>> cmp.sim('Niall', 'Neil') 0.13213719608444902 >>> cmp.sim('aluminum', 'Catalan') 0.013621892326789235 >>> cmp.sim('ATCG', 'TAGC') 0.0 .. 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() num = a * a * d * d if num == 0: return 0.0 return num / ((a + b) * (a + c) * (b + d) * (c + d))
if __name__ == '__main__': import doctest doctest.testmod()