author Philippe Pepiot <philippe.pepiot@logilab.fr>
Tue, 03 Dec 2019 16:19:07 +0100
changeset 587 6a6bd2c128b6
parent 581 29125bda3eaa
permissions -rw-r--r--
Added tag 0.9.5, debian/0.9.5-1 for changeset b72ecde3b7cc

# -*- coding:utf-8 -*-
# copyright 2012 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
# contact http://www.logilab.fr -- mailto:contact@logilab.fr
# This program is free software: you can redistribute it and/or modify it under
# the terms of the GNU Lesser General Public License as published by the Free
# Software Foundation, either version 2.1 of the License, or (at your option)
# any later version.
# This program 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 Lesser General Public License for more
# details.
# You should have received a copy of the GNU Lesser General Public License along
# with this program. If not, see <http://www.gnu.org/licenses/>.
from __future__ import absolute_import
import sys
if sys.version_info >= (2, 7):
    import unittest
    import unittest2 as unittest
from functools import partial
from os import path
import random
from mock import patch

from nazca.utils.normalize import simplify
from nazca.utils.minhashing import Minlsh, count_vectorizer_func
from nazca.data import FRENCH_LEMMAS

TESTDIR = path.dirname(__file__)

class MinLSHTest(unittest.TestCase):

    def test_iter_wordgrams(self):
        sentence = 'nom de la rose'
        minlsh = Minlsh()
        results = list(minlsh._iter_wordgrams(sentence, 2))
        truth = ['nom de', 'nom', 'de la', 'de', 'la rose', 'la', 'rose']
        self.assertEqual(len(results), len(truth))
        self.assertEqual(set(results), set(truth))

    def test_iter_wordgrams_sklearn(self):
        sentences = ('nom de la rose', 'nom de la')
        tokenizer_func = partial(count_vectorizer_func, min_n=1, max_n=2)
        minlsh = Minlsh(tokenizer_func=tokenizer_func)
        rows, shape = list(minlsh._buildmatrixdocument(sentences, 2))
        self.assertEqual(shape, (2, 7))
        self.assertEqual(rows[0], [0, 1, 2, 3, 4, 5, 6])
        self.assertEqual(rows[1], [0, 1, 2, 4, 5])

    def test_all(self):
        sentences = [u"Un nuage flotta dans le grand ciel bleu.",
                     u"Des grands nuages noirs flottent dans le ciel.",
                     u"Je n'aime pas ce genre de bandes dessinées tristes.",
                     u"J'aime les bandes dessinées de genre comiques.",
                     u"Pour quelle occasion vous êtes-vous apprêtée ?",
                     u"Je les vis ensemble à plusieurs occasions.",
                     u"Je les ai vus ensemble à plusieurs occasions.",
        minlsh = Minlsh()

        # the minhashing function is based on a « hash » function. This hash
        # function is itself based on two integers randomly chosen in a
        # given interval. Different runs of this procedure will produce
        # different results because the hash function will be different.
        # This is the expected behaviour. Excepted in the tests, where we
        # need the result to be reproductible. Therefore we patch the
        # `random.randint` with a fixed-seed version.
        myrandom = random.Random("spam eggs bacon")
        with patch("nazca.utils.minhashing.randint", myrandom.randint):
                (simplify(s, FRENCH_LEMMAS, remove_stopwords=True) for s in sentences),
        self.assertEqual(set([(0, 1), (2, 3), (5, 6)]), minlsh.predict(0.4))

if __name__ == '__main__':