def test_count_2gram(self):
model = AddOneNGram(2, self.sents)
counts = {
('<s>', ): 2,
('el', ): 1,
('gato', ): 1,
('come', ): 2,
('pescado', ): 1,
('.', ): 2,
('la', ): 1,
('gata', ): 1,
('salmón', ): 1,
('<s>', 'el'): 1,
('el', 'gato'): 1,
('gato', 'come'): 1,
('come', 'pescado'): 1,
('pescado', '.'): 1,
('.', '</s>'): 2,
('<s>', 'la'): 1,
('la', 'gata'): 1,
('gata', 'come'): 1,
('come', 'salmón'): 1,
('salmón', '.'): 1,
}
for gram, c in counts.items():
self.assertEqual(model.count(gram), c, gram)
# size of the vocabulary
self.assertEqual(model.V(), 9)
def test_count_3_addone_ngram(self):
sents_group = [self.sents2, self.sents]
i = 0
for sents_chosen in sents_group:
model = AddOneNGram(3, sents_chosen)
# sent2 vocab size = 8 and sent vocab size = 9
# (this explains use of i)
self.assertEqual(model.V(), 8+i)
i += 1
