clusters.py 文件源码

def internal_silhouette(self, idea_id, base_labels=None):
        labels = self.labels_for_idea(idea_id, True, False, base_labels)
        self.remove_singletons(labels, idea_id)
        idea_post_ids = self.get_posts_of_idea(idea_id)
        if base_labels:
            idea_post_ids = set(idea_post_ids)
            idea_post_ids.update(list(base_labels.keys()))
            idea_post_ids = np.array(list(idea_post_ids))
            idea_post_ids.sort()
        idea_post_ids = np.array(idea_post_ids)
        idea_post_nums = self.post_ids.searchsorted(idea_post_ids)
        # slicing one axis of a time
        # because simultaneous slice interpreted as diagonal
        distances = self.distance_matrix
        sub_distance = distances[idea_post_nums][:, idea_post_nums]
        sub_labels = labels[idea_post_nums]
        if len(set(sub_labels)) < 2:
            return 0
        return metrics.silhouette_score(sub_distance, sub_labels, 'precomputed')