milia.cluster.models.minibatch#

Mini-batch k-means, for large populations.

Classes

MiniBatch([n_clusters, n_init, batch_size, ...])

k-means fitted on mini-batches (Sculley, 2010).

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

Validated hyperparameters of the mini-batch k-means clusterer.

class milia.cluster.models.minibatch.MiniBatch(n_clusters=3, n_init=10, batch_size=1024, random_state=0)#

Bases: BaseClusterer

k-means fitted on mini-batches (Sculley, 2010).

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

  • n_init (int) – Restarts.

  • batch_size (int) – Rows per mini-batch.

  • random_state (int | None) – Seed.

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)
... )
>>> MiniBatch(n_clusters=3).fit(X).n_clusters_
3
class milia.cluster.models.minibatch.MiniBatchConfig(*, name='minibatch', kind='clusterer', space=SearchSpace(n_clusters=(2, 12)), n_clusters=3, n_init=10, batch_size=1024, random_state=0)#

Bases: BaseModelConfig

Validated hyperparameters of the mini-batch k-means clusterer.

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

Examples

>>> MiniBatchConfig().name
'minibatch'