def setUp(self): data_dir = 'test_data/tiny_def' self.gen = partial(generator.read_lines, f'{data_dir}/valid.txt', token_split=' ', part_split='\t', part_indices=[0, -1]) self.enc_vocab = Vocabulary.from_vocab_file( f'{data_dir}/enc_vocab.txt') self.dec_vocab = Vocabulary.from_vocab_file( f'{data_dir}/dec_vocab.txt') self.char_vocab = Vocabulary.from_vocab_file( f'{data_dir}/char_vocab.txt') self.num_lines = 1000 self.num_tokens = 5465
def setUpClass(cls): super(TestRun, cls).setUpClass() data_dir = 'test_data/tiny_single' cls.vocab = Vocabulary.from_vocab_file(f'{data_dir}/vocab.txt') cls.gen = partial(generator.read_lines, f'{data_dir}/valid.txt', token_split=' ') cls.num_lines = 1000 cls.num_tokens = 5606
def setUp(self): data_dir = 'test_data/tiny_single' self.gen = partial(generator.read_lines, f'{data_dir}/valid.txt', token_split=' ') self.vocab = Vocabulary.from_vocab_file(f'{data_dir}/vocab.txt') self.num_lines = 1000 self.num_tokens = 5606
def setUpClass(cls): super(TestSamplingRun, cls).setUpClass() data_dir = 'test_data/tiny_copy' cls.vocab = Vocabulary.from_vocab_file(f'{data_dir}/vocab.txt') cls.gen = partial(generator.read_lines, f'{data_dir}/valid.txt', token_split=' ', part_split='\t')