def load(self, path): ds = DataSet.read_csv(path, headers=("raw_sentence", "label"), sep="\t") ds.set_input("raw_sentence") ds.set_target("label") return ds
def test_apply2(self): def split_sent(ins): return ins['raw_sentence'].split() dataset = DataSet.read_csv( 'test/data_for_tests/tutorial_sample_dataset.csv', headers=('raw_sentence', 'label'), sep='\t') dataset.drop(lambda x: len(x['raw_sentence'].split()) == 0) dataset.apply(split_sent, new_field_name='words', is_input=True)