imikolov_test.py 1.7 KB
Newer Older
1 2 3
import paddle.v2.dataset.imikolov
import unittest

4 5
WORD_DICT = paddle.v2.dataset.imikolov.build_dict()

6 7 8 9 10 11 12 13

class TestMikolov(unittest.TestCase):
    def check_reader(self, reader, n):
        for l in reader():
            self.assertEqual(len(l), n)

    def test_train(self):
        n = 5
14
        self.check_reader(paddle.v2.dataset.imikolov.train(WORD_DICT, n), n)
15

16 17 18 19 20 21 22 23 24 25 26 27 28 29
        first_line = 'aer banknote berlitz calloway centrust cluett fromstein '\
            'gitano guterman hydro-quebec ipo kia memotec mlx nahb punts '\
            'rake regatta rubens sim snack-food ssangyong swapo wachter'
        first_line = [
            WORD_DICT.get(ch, WORD_DICT['<unk>'])
            for ch in first_line.split(' ')
        ]
        for l in paddle.v2.dataset.imikolov.train(
                WORD_DICT, n=-1,
                data_type=paddle.v2.dataset.imikolov.DataType.SEQ)():
            read_line = l[0][1:]
            break
        self.assertEqual(first_line, read_line)

30 31
    def test_test(self):
        n = 5
32 33
        self.check_reader(paddle.v2.dataset.imikolov.test(WORD_DICT, n), n)

34 35 36 37 38 39 40 41 42 43 44 45 46
        first_line = 'consumers may want to move their telephones a little '\
                'closer to the tv set'
        first_line = [
            WORD_DICT.get(ch, WORD_DICT['<unk>'])
            for ch in first_line.split(' ')
        ]
        for l in paddle.v2.dataset.imikolov.test(
                WORD_DICT, n=-1,
                data_type=paddle.v2.dataset.imikolov.DataType.SEQ)():
            read_line = l[0][1:]
            break
        self.assertEqual(first_line, read_line)

47 48 49
    def test_total(self):
        _, idx = zip(*WORD_DICT.items())
        self.assertEqual(sorted(idx)[-1], len(WORD_DICT) - 1)
50 51 52 53


if __name__ == '__main__':
    unittest.main()