C# Class Encog.ML.Kmeans.KMeansClustering

This class performs a basic K-Means clustering. This class can be used on either supervised or unsupervised data. For supervised data, the ideal values will be ignored. http://en.wikipedia.org/wiki/Kmeans

Inheritance: IMLClustering

Show file Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method	Description
CalculateEuclideanDistance ( Centroid c, IMLData data ) : double	Calculate the euclidean distance between a centroid and data.
Iteration ( ) : void	Perform a single training iteration.
Iteration ( int count ) : void	The number of iterations to perform.
KMeansClustering ( int k, IMLDataSet theSet ) : System	Construct the K-Means object.
NumClusters ( ) : int

Private Methods

Method	Description
CalcWcss ( ) : void	Calculate the within-cluster sum of squares (WCSS).
GetMaxValue ( int index ) : double	Get the maximum, over all the data, for the specified index.
GetMinValue ( int index ) : double	Get the minimum, over all the data, for the specified index.
SetInitialCentroids ( ) : void	Setup the initial centroids.

Method Details

CalculateEuclideanDistance() public static method

Calculate the euclidean distance between a centroid and data.

public static CalculateEuclideanDistance ( Centroid c, IMLData data ) : double
c	Centroid	The centroid to use.
data	IMLData	The data to use.
return	double

Iteration() public method

Perform a single training iteration.

public Iteration ( ) : void
return	void

Iteration() public method

The number of iterations to perform.

public Iteration ( int count ) : void
count	int
return	void

KMeansClustering() public method

Construct the K-Means object.

public KMeansClustering ( int k, IMLDataSet theSet ) : System
k	int	The number of clusters to use.
theSet	IMLDataSet	The dataset to cluster.
return	System

NumClusters() public method

public NumClusters ( ) : int
return	int