git_authorship.py 文件源码

def _compute_author_similarity(self, paired_authors):
        def row_similarity(row):
            same_email = row.author_email == row.author_email_other
            name_similarity = fuzz.token_set_ratio(row.author_name,
                                                   row.author_name_other)
            email_name_similarity = fuzz.ratio(row.email_name,
                                               row.email_name_other)
            name_to_email_similarity = fuzz.token_set_ratio(row.author_name,
                                                            row.name_from_email_other)
            return pd.Series(
                [same_email, name_similarity, email_name_similarity,
                 name_to_email_similarity])

        newcols = paired_authors.apply(row_similarity, axis=1)
        newcols.columns = ['same_email', 'name_similarity',
                           'email_name_similarity', 'name_to_email_similarity']
        newdf = paired_authors.join(newcols)
        return newdf