cluster_manager.py 文件源码

def _cluster_documents(self):

        method = self.params['cluster_method']
        n_clusters = int(self.params['cluster_n_clusters'])

        n_samples = len(self.document_vectors)

        if n_clusters > n_samples:
            n_clusters = n_samples

        if method == 'kmeans':
            clusterer = KMeans(n_clusters=n_clusters, init='k-means++', max_iter=100, n_init=1)
        else:
            clusterer = AgglomerativeClustering(n_clusters=n_clusters, linkage='complete', affinity='cosine')

        clustering = clusterer.fit(self.document_vectors)
        cluster_labels = clustering.labels_

        clustering_dict = clustering.__dict__
        cluster_centers = clustering_dict['cluster_centers_']

        clusters = {}

        for document_id,cluster_label in enumerate(cluster_labels):
            if cluster_label not in clusters:
                clusters[cluster_label] = []
            clusters[cluster_label].append(document_id)

        return clusters,cluster_centers