def test_generate_sent_1gram(self):
ngram = NGram(1, self.sents)
generator = NGramGenerator(ngram)
voc = {'el', 'gato', 'come', 'pescado', '.', 'la', 'gata', 'salmón'}
for i in range(100):
sent = generator.generate_sent()
self.assertTrue(set(sent).issubset(voc))
def test_generate_sent_2gram(self):
ngram = NGram(2, self.sents)
generator = NGramGenerator(ngram)
# all the possible generated sentences for 2-grams:
sents = [
'el gato come pescado .',
'la gata come salmón .',
'el gato come salmón .',
'la gata come pescado .',
]
for i in range(100):
sent = generator.generate_sent()
self.assertTrue(' '.join(sent) in sents, sent)
generate.py -h | --help
Options:
-i <file> Language model file.
-n <n> Number of sentences to generate.
-h --help Show this screen.
"""
from docopt import docopt
import pickle
from languagemodeling.ngram_generator import NGramGenerator
if __name__ == '__main__':
opts = docopt(__doc__)
# load the model
filename = opts['-i']
f = open(filename, 'rb')
model = pickle.load(f)
f.close()
# build generator
generator = NGramGenerator(model)
# generate sentences
n = int(opts['-n'])
for i in range(n):
sent = generator.generate_sent()
print(' '.join(sent))