TermDocMatrix.py 文件源码

def _get_fisher_scores_from_counts(self, cat_word_counts, not_cat_word_counts):
        cat_not_word_counts = cat_word_counts.sum() - cat_word_counts
        not_cat_not_word_counts = not_cat_word_counts.sum() - not_cat_word_counts

        def do_fisher_exact(x):
            return fisher_exact([[x[0], x[1]], [x[2], x[3]]], alternative='greater')

        odds_ratio, p_values = np.apply_along_axis(
            do_fisher_exact,
            0,
            np.array([cat_word_counts, cat_not_word_counts, not_cat_word_counts, not_cat_not_word_counts]))
        return odds_ratio, p_values