Back to FabImage Studio website

You are here: Start » Filter Reference » Data Classification » Clustering » ClusterData_KMeans

ClusterData_KMeans


Module: FoundationPro

Clusters data using KMeans algorithm.

Name Type Range Description
Input value inData RealArrayArray Data set, array of examples
Input value inClusters Integer 2 - + Number of clusters to extract
Input value inMaxIterations Integer 10 - 1000 Maximal number of procedure iterations
Input value inSeed Integer 0 - Seed to init random engine
Input value inTerminationFactor Real 1.0 - 2.0 Additional factor of procedure stop
Input value inClusteringMethod KMeansClusteringMethod KMeans variant to use
Output value outCentroids Matrix Resulting centroid points in feature space
Output value outPointToClusterAssignment IntegerArray Array of input point assignments to generated clusters
Output value outDistanceSum Real Sum of squared distances from points to its respective cluster centroids

Errors

This filter can throw an exception to report error. Read how to deal with errors in Error Handling.

List of possible exceptions:

Error type Description
DomainError Cannot make more clusters than there is data in input dataset in ClusterData_KMeans.
DomainError Empty dataset on input in ClusterData_KMeans.
DomainError Inconsistent number of data coordinates in input dataset in ClusterData_KMeans.

Complexity Level

This filter is available on Expert Complexity Level.