Package org.apache.commons.math3.ml.neuralnet.twod.util

Class SmoothedDataHistogram

java.lang.Object

org.apache.commons.math3.ml.neuralnet.twod.util.SmoothedDataHistogram

All Implemented Interfaces:

MapDataVisualization

public class SmoothedDataHistogram
extends Object
implements MapDataVisualization

Visualization of high-dimensional data projection on a 2D-map. The method is described in Using Smoothed Data Histograms for Cluster Visualization in Self-Organizing Maps
by Elias Pampalk, Andreas Rauber and Dieter Merkl.

Since:

3.6

Constructor Summary

Constructors

Constructor	Description
SmoothedDataHistogram(int smoothingBins, DistanceMeasure distance)

Method Summary

Modifier and Type	Method	Description
double[][]	computeImage(NeuronSquareMesh2D map, Iterable<double[]> data)	Creates an image of the data metrics when represented by the map.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

SmoothedDataHistogram

public SmoothedDataHistogram(int smoothingBins,
 DistanceMeasure distance)

Parameters:

smoothingBins - Number of bins.

distance - Distance.

Method Details

computeImage

public double[][] computeImage(NeuronSquareMesh2D map,
 Iterable<double[]> data)

Creates an image of the data metrics when represented by the map.

Specified by:

computeImage in interface MapDataVisualization

Parameters:

map - Map.

data - Data.

Returns:

a 2D-array (in row major order) representing the metrics.

Throws:

NumberIsTooSmallException - if the size of the map is smaller than the number of smoothing bins.