Package ai.libs.jaicore.ml.core.filter.sampling.inmemory.stratified.sampling

Class KMeansStratifier

java.lang.Object

ai.libs.jaicore.ml.core.filter.sampling.inmemory.stratified.sampling.ClusterStratiAssigner

ai.libs.jaicore.ml.core.filter.sampling.inmemory.stratified.sampling.KMeansStratifier

All Implemented Interfaces:

IStratifier, org.api4.java.common.control.IParallelizable

public class KMeansStratifier
extends ClusterStratiAssigner

Cluster the data set with k-means into k Clusters, where each cluster stands for one stratum. The datapoint assignment is performed with a lookup in the clusters.

Field Summary

Fields inherited from class ai.libs.jaicore.ml.core.filter.sampling.inmemory.stratified.sampling.ClusterStratiAssigner

distanceMeasure, randomSeed

Constructor Summary

Constructors

Constructor	Description
KMeansStratifier(int numberOfStrati, org.apache.commons.math3.ml.distance.DistanceMeasure distanceMeasure, int randomSeed)	Constructor for KMeansStratiAssigner.

Method Summary

Modifier and Type	Method	Description
int	createStrati(org.api4.java.ai.ml.core.dataset.IDataset<?> dataset)	Prepares the stratification technique but does not assign instances to strati.

Methods inherited from class ai.libs.jaicore.ml.core.filter.sampling.inmemory.stratified.sampling.ClusterStratiAssigner

getClusters, getNumCPUs, getStratum, setClusters, setDataset, setNumCPUs

Methods inherited from class java.lang.Object

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

Constructor Detail

KMeansStratifier

public KMeansStratifier(int numberOfStrati,
                        org.apache.commons.math3.ml.distance.DistanceMeasure distanceMeasure,
                        int randomSeed)

Constructor for KMeansStratiAssigner.

Parameters:

distanceMeasure - Distance measure for datapoints, for example Manhattan or Euclidian.

randomSeed - Seed for random numbers.

Method Detail

createStrati

public int createStrati(org.api4.java.ai.ml.core.dataset.IDataset<?> dataset)

Description copied from interface: IStratifier

Prepares the stratification technique but does not assign instances to strati.

Returns:

The number of strati for the given dataset