504410df92f74a6471247909d01f4ca4639b91d8,tests/test_readme.py,ReadmeTestCase,test_term_counting,#ReadmeTestCase#,221

Before Change

        bot = self.doc.as_bag_of_terms(weighting="tf", normalized=False,
                                       lemmatize="auto", ngram_range=(1, 1))
        // sort by term ascending, then count descending
        observed_2 = sorted([(self.doc.spacy_stringstore[term_id], count)
                             for term_id, count in bot.most_common(n=10)],
                            key=itemgetter(0), reverse=False)
        observed_2 = sorted(observed_2, key=itemgetter(1), reverse=True)
        expected_2 = [("nation", 6), ("incarceration", 4), ("world", 4),
                      ("drug", 3), ("lead", 3), ("mandatory", 3), ("minimum", 3),
                      ("people", 3), ("problem", 3), ("male", 2)]

After Change

        bot = self.doc.to_bag_of_terms(
            ngrams=1, normalize=False, lemmatize=True, as_strings=True)
        // sort by term ascending, then count descending
        observed_2 = sorted(bot.items(), key=itemgetter(1, 0), reverse=True)[:10]
        expected_2 = [
            ("nation", 6), ("world", 4), ("u.s.", 4), ("incarceration", 4),
            ("decade", 4), ("state", 3), ("record", 3), ("problem", 3),
            ("people", 3), ("minimum", 3)]

Instances