def save_graphclust_h5(f, labels):
clustering_key = cr_clustering.format_clustering_key(
cr_clustering.CLUSTER_TYPE_GRAPHCLUST, 0)
clustering = cr_clustering.create_clustering(
clusters=labels,
num_clusters=max(labels),
cluster_score=0,
clustering_type=cr_clustering.CLUSTER_TYPE_GRAPHCLUST,
global_sort_key=float('-inf'), # always first
description=cr_clustering.humanify_clustering_key(clustering_key))
group = f.create_group(f.root, cr_constants.ANALYSIS_H5_CLUSTERING_GROUP)
cr_io.save_h5(f, group, clustering_key, clustering)
def run_kmedoids(transformed_matrix, n_clusters, random_state=None, metric='euclidean'):
if random_state is None:
random_state=analysis_constants.RANDOM_STATE
kmedoids = KMedoids(n_clusters=n_clusters, random_state=random_state, metric=metric)
clusters = kmedoids.fit_predict(transformed_matrix) + 1
cluster_score = compute_silhouette_index(transformed_matrix, kmedoids, metric)
clusters = cr_clustering.relabel_by_size(clusters)
clustering_key = cr_clustering.format_clustering_key(cr_clustering.CLUSTER_TYPE_KMEDOIDS, n_clusters)
return cr_clustering.create_clustering(clusters=clusters,
num_clusters=n_clusters,
cluster_score=cluster_score,
clustering_type=cr_clustering.CLUSTER_TYPE_KMEDOIDS,
global_sort_key=n_clusters,
description=cr_clustering.humanify_clustering_key(clustering_key))
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))