Source code for abydos.distance._braun_blanquet

# 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._braun_blanquet.

Braun-Blanquet similarity
"""

from ._token_distance import _TokenDistance

__all__ = ['BraunBlanquet']


[docs]class BraunBlanquet(_TokenDistance): r"""Braun-Blanquet similarity. For two sets X and Y and a population N, the Braun-Blanquet similarity :cite:`BraunBlanquet:1932` is .. math:: sim_{BraunBlanquet}(X, Y) = \frac{|X \cap Y|}{max(|X|, |Y|)} In :ref:`2x2 confusion table terms <confusion_table>`, where a+b+c+d=n, this is .. math:: sim_{BraunBlanquet} = \frac{a}{max(a+b, a+c)} .. versionadded:: 0.4.0 """ def __init__( self, alphabet=None, tokenizer=None, intersection_type='crisp', **kwargs ): """Initialize BraunBlanquet 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(BraunBlanquet, self).__init__( alphabet=alphabet, tokenizer=tokenizer, intersection_type=intersection_type, **kwargs )
[docs] def sim(self, src, tar): """Return the Braun-Blanquet 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 Braun-Blanquet similarity Examples -------- >>> cmp = BraunBlanquet() >>> cmp.sim('cat', 'hat') 0.5 >>> cmp.sim('Niall', 'Neil') 0.3333333333333333 >>> cmp.sim('aluminum', 'Catalan') 0.1111111111111111 >>> cmp.sim('ATCG', 'TAGC') 0.0 .. versionadded:: 0.4.0 """ if src == tar: return 1.0 self._tokenize(src, tar) return self._intersection_card() / max( self._src_card(), self._tar_card() )
if __name__ == '__main__': import doctest doctest.testmod()