Ejemplo n.º 1
0
    def test_titles_from_list(self):
        domain = Domain([],
                        metas=[StringVariable("title"),
                               StringVariable("a")])
        corpus = Corpus.from_list(domain, [["title1", "a"], ["title2", "b"]])
        assert_array_equal(["Document 1", "Document 2"], corpus.titles)

        domain["title"].attributes["title"] = True
        corpus = Corpus.from_list(domain, [["title1", "a"], ["title2", "b"]])
        assert_array_equal(["title1", "title2"], corpus.titles)
Ejemplo n.º 2
0
 def test_corpus_from_list(self):
     domain = Domain([],
                     metas=[StringVariable("title"),
                            StringVariable("a")])
     corpus = Corpus.from_list(domain, [["title1", "a"], ["title2", "b"]])
     self.assertEqual(2, len(corpus))
     assert_array_equal(["Document 1", "Document 2"], corpus.titles)
     self.assertListEqual([StringVariable("title")], corpus.text_features)
     self.assertIsNone(corpus._tokens)
     self.assertListEqual([], corpus.used_preprocessor.preprocessors)