milia.cluster.models.kmeans#

k-means.

Classes

KMeans([n_clusters, n_init, max_iter, ...])

Lloyd's k-means with several restarts.

KMeansConfig(*[, name, kind, space, ...])

Validated hyperparameters of the k-means clusterer.

class milia.cluster.models.kmeans.KMeans(n_clusters=3, n_init=20, max_iter=300, random_state=0)#

Bases: BaseClusterer

Lloyd’s k-means with several restarts.

Parameters:
  • n_clusters (int) – Number of clusters.

  • n_init (int) – Restarts; the lowest-inertia run is kept.

  • max_iter (int) – Iterations per run.

  • random_state (int | None) – Seed for initialisation.

Examples

>>> import numpy as np
>>> rng = np.random.default_rng(0)
>>> X = np.repeat(np.array([[0.0, 0.0], [6.0, 6.0], [0.0, 6.0]]), 20, axis=0) + rng.normal(
...     scale=0.4, size=(60, 2)
... )
>>> KMeans(n_clusters=3).fit(X).n_clusters_
3
distances(X)#

Distance of each row to every centroid.

Parameters:

X (ndarray) – Rows.

Return type:

ndarray

Returns:

Array of shape (n, n_clusters).

class milia.cluster.models.kmeans.KMeansConfig(*, name='kmeans', kind='clusterer', space=SearchSpace(n_clusters=(2, 12)), n_clusters=3, n_init=20, max_iter=300, random_state=0)#

Bases: BaseModelConfig

Validated hyperparameters of the k-means clusterer.

Fields mirror KMeans’s constructor; space is the default Optuna search space. Build the clusterer with make("clusterer", "kmeans", ...) or KMeans(**config.params()).

Examples

>>> KMeansConfig().name
'kmeans'