Categories &

Functions List

Class Definition: SilhouetteEvaluation

Function File: obj = evalclusters (x, clust, silhouette)
Function File: obj = evalclusters (…, Name, Value)

A silhouette object to evaluate clustering solutions.

A SilhouetteEvaluation object is a ClusterCriterion object used to evaluate clustering solutions using the silhouette criterion.

List of public properties specific to SilhouetteEvaluation:

Distance

a valid distance metric name, or a function handle or a numeric array as generated by the pdist function.

ClusterPriors

a valid name for the evaluation of silhouette values: empirical (default) or equal.

ClusterSilhouettes

a cell array with the silhouette values of each data point for each cluster number.

The best solution according to the silhouette criterion is the one that scores the highest average silhouette value.

See also: evalclusters, ClusterCriterion, CalinskiHarabaszEvaluation, DaviesBouldinEvaluation, GapEvaluation

Source Code: SilhouetteEvaluation

Properties

SilhouetteEvaluation.Distance is not documented.
SilhouetteEvaluation.ClusterPriors is not documented.
SilhouetteEvaluation.ClusterSilhouettes is not documented.

Methods

SilhouetteEvaluation: obj = addK (obj, K)

Add a new cluster array to inspect the SilhouetteEvaluation object.

SilhouetteEvaluation: plot (obj)
SilhouetteEvaluation: h = plot (obj)

Plot the evaluation results.

Plot the CriterionValues against InspectedK from the SilhouetteEvaluation ClusterCriterion, obj, to the current plot. It can also return a handle to the current plot.

SilhouetteEvaluation: obj = compact (obj)

Return a compact SilhouetteEvaluation object (not implemented yet).