예제 #1
0
    def test_trigram(self):
        unigrams = NGramSpace(3)

        x = unigrams.parse("This is a sentence")
        y = unigrams.parse("This is another sentence")

        self.assertEqual([1, 2], x)
        self.assertEqual([3, 4], y)

        self.assertEqual(0, overlap(x, y))
        self.assertEqual(0, overlap(y, x))

        self.assertEqual(0, jaccard(x, y))
        self.assertEqual(0, jaccard(y, x))
예제 #2
0
    def test_trigram(self):
        unigrams = NGramSpace(3)

        x = unigrams.parse('This is a sentence')
        y = unigrams.parse('This is another sentence')

        self.assertEqual([1, 2], x)
        self.assertEqual([3, 4], y)

        self.assertEqual(0, overlap(x, y))
        self.assertEqual(0, overlap(y, x))

        self.assertEqual(0, jaccard(x, y))
        self.assertEqual(0, jaccard(y, x))
예제 #3
0
    def test_bigram(self):
        unigrams = NGramSpace(2)

        x = unigrams.parse("This is a sentence")
        y = unigrams.parse("This is another sentence")

        self.assertEqual([1, 2, 3], x)
        self.assertEqual([1, 4, 5], y)

        self.assertEqual(1, overlap(x, y))
        self.assertEqual(1, overlap(y, x))

        self.assertEqual(1.0 / 5.0, jaccard(x, y))
        self.assertEqual(1.0 / 5.0, jaccard(y, x))
예제 #4
0
    def test_bigram(self):
        unigrams = NGramSpace(2)

        x = unigrams.parse('This is a sentence')
        y = unigrams.parse('This is another sentence')

        self.assertEqual([1, 2, 3], x)
        self.assertEqual([1, 4, 5], y)

        self.assertEqual(1, overlap(x, y))
        self.assertEqual(1, overlap(y, x))

        self.assertEqual(1.0 / 5.0, jaccard(x, y))
        self.assertEqual(1.0 / 5.0, jaccard(y, x))