precluster.py 文件源码

def _find_optimal_clustering(self,clusterings):

        max_score = float('-inf')
        max_clustering = None

        for clustering in clusterings:
            labeled_vectors = [(node.vector,cluster_idx) for cluster_idx in range(len(clustering)) for node in _get_cluster_nodes(clustering[cluster_idx][1]) ]
            vectors,labels = [np.array(x) for x in zip(*labeled_vectors)]
            if np.in1d([1],labels)[0]:
                score = silhouette_score(vectors,labels,metric='cosine')
            else:
                continue # silhouette doesn't work with just one cluster
            if score > max_score:
                max_score = score
                max_clustering = clustering

        return zip(*max_clustering)[1] if max_clustering else zip(*clusterings[0])[1]