sklearn.cluster.cluster_optics_dbscan

sklearn.cluster.cluster_optics_dbscan(*, reachability, core_distances, ordering, eps)

Perform DBSCAN extraction for an arbitrary epsilon.

Extracting the clusters runs in linear time. Note that this results in labels_ which are close to a DBSCAN with similar settings and eps, only if eps is close to max_eps.

Parameters:

reachabilityndarray of shape (n_samples,)

Reachability distances calculated by OPTICS (reachability_).

core_distancesndarray of shape (n_samples,)

Distances at which points become core (core_distances_).

orderingndarray of shape (n_samples,)

OPTICS ordered point indices (ordering_).

epsfloat

DBSCAN eps parameter. Must be set to < max_eps. Results will be close to DBSCAN algorithm if eps and max_eps are close to one another.

Returns:

labels_array of shape (n_samples,)

The estimated labels.

Examples

>>> import numpy as np
>>> from sklearn.cluster import cluster_optics_dbscan, compute_optics_graph
>>> X = np.array([[1, 2], [2, 5], [3, 6],
...               [8, 7], [8, 8], [7, 3]])
>>> ordering, core_distances, reachability, predecessor = compute_optics_graph(
...     X,
...     min_samples=2,
...     max_eps=np.inf,
...     metric="minkowski",
...     p=2,
...     metric_params=None,
...     algorithm="auto",
...     leaf_size=30,
...     n_jobs=None,
... )
>>> eps = 4.5
>>> labels = cluster_optics_dbscan(
...     reachability=reachability,
...     core_distances=core_distances,
...     ordering=ordering,
...     eps=eps,
... )
>>> labels
array([0, 0, 0, 1, 1, 1])

Examples using sklearn.cluster.cluster_optics_dbscan

Demo of OPTICS clustering algorithm

Demo of OPTICS clustering algorithm