kmeans.py 文件源码

def run_kmeans(transformed_pca_matrix, n_clusters, random_state=None):
    if random_state is None:
        random_state=cr_constants.RANDOM_STATE

    kmeans = sk_cluster.KMeans(n_clusters=n_clusters, random_state=random_state)
    clusters = kmeans.fit_predict(transformed_pca_matrix) + 1

    cluster_score = compute_db_index(transformed_pca_matrix, kmeans)

    clusters = cr_clustering.relabel_by_size(clusters)

    clustering_key = cr_clustering.format_clustering_key(cr_clustering.CLUSTER_TYPE_KMEANS, n_clusters)

    return cr_clustering.create_clustering(clusters=clusters,
                                           num_clusters=n_clusters,
                                           cluster_score=cluster_score,
                                           clustering_type=cr_clustering.CLUSTER_TYPE_KMEANS,
                                           global_sort_key=n_clusters,
                                           description=cr_clustering.humanify_clustering_key(clustering_key))