tomodrgn.analysis.cluster_kmeans

cluster_kmeans(z: ndarray, n_clusters: int, random_state: int | RandomState | None = None, on_data: bool = True, reorder: bool = True, **kwargs: Any) → tuple[ndarray, ndarray]

Cluster latent embeddings using k-means clustering. If reorder=True, reorders clusters according to agglomerative clustering of cluster centers

Parameters:

• z – array of latent embeddings, shape (nptcls, zdim)

• n_clusters – number of clusters to form, passed to sklearn.cluster.KMeans

• random_state – random state for reproducible runs, passed to sklearn.cluster.KMeans

• on_data – adjust cluster centers to nearest point on the data manifold z

• reorder – reorder clusters according to agglomerative clustering of cluster centers

• kwargs – additional key word arguments passed to sklearn.cluster.KMeans

Returns:

array of cluster labels shape (len(z)), array of cluster centers shape (n_clusters, zdim)