Uses of Interface
elki.index.tree.betula.features.ClusterFeature

Packages that use ClusterFeature

Package	Description
elki.clustering.em	Expectation-Maximization clustering algorithm for Gaussian Mixture Modeling (GMM).
elki.clustering.em.models
elki.clustering.kmeans	K-means clustering and variations.
elki.clustering.kmeans.initialization.betula	Initialization methods for BIRCH-based k-means and EM clustering.
elki.index.tree.betula	BETULA clustering by aggregating the data into cluster features.
elki.index.tree.betula.distance	Distance functions for BETULA and BIRCH.
elki.index.tree.betula.features	Different variants of Betula and BIRCH cluster features.

Uses of ClusterFeature in elki.clustering.em

Method parameters in elki.clustering.em with type arguments of type ClusterFeature

Modifier and Type	Method	Description
double	BetulaGMM.assignProbabilitiesToInstances(java.util.ArrayList<? extends ClusterFeature> cfs, java.util.List<? extends BetulaClusterModel> models, java.util.Map<ClusterFeature,double[]> probClusterIGivenX)	Assigns the current probability values to the instances in the database and compute the expectation value of the current mixture of distributions.
double	BetulaGMM.assignProbabilitiesToInstances(java.util.ArrayList<? extends ClusterFeature> cfs, java.util.List<? extends BetulaClusterModel> models, java.util.Map<ClusterFeature,double[]> probClusterIGivenX)	Assigns the current probability values to the instances in the database and compute the expectation value of the current mixture of distributions.
double	BetulaGMMWeighted.assignProbabilitiesToInstances(java.util.ArrayList<? extends ClusterFeature> cfs, java.util.List<? extends BetulaClusterModel> models, java.util.Map<ClusterFeature,double[]> probClusterIGivenX)
double	BetulaGMMWeighted.assignProbabilitiesToInstances(java.util.ArrayList<? extends ClusterFeature> cfs, java.util.List<? extends BetulaClusterModel> models, java.util.Map<ClusterFeature,double[]> probClusterIGivenX)
void	BetulaGMM.recomputeCovarianceMatrices(java.util.ArrayList<? extends ClusterFeature> cfs, java.util.Map<ClusterFeature,double[]> probClusterIGivenX, java.util.List<? extends BetulaClusterModel> models, double prior, int n)	Recompute the covariance matrixes.
void	BetulaGMM.recomputeCovarianceMatrices(java.util.ArrayList<? extends ClusterFeature> cfs, java.util.Map<ClusterFeature,double[]> probClusterIGivenX, java.util.List<? extends BetulaClusterModel> models, double prior, int n)	Recompute the covariance matrixes.

Uses of ClusterFeature in elki.clustering.em.models

Methods in elki.clustering.em.models with parameters of type ClusterFeature

Modifier and Type	Method	Description
double	BetulaClusterModel.estimateLogDensity(ClusterFeature cf)	Estimate the log likelihood of a clustering feature.
double	DiagonalGaussianModel.estimateLogDensity(ClusterFeature cf)
double	MultivariateGaussianModel.estimateLogDensity(ClusterFeature cf)
double	SphericalGaussianModel.estimateLogDensity(ClusterFeature cf)
void	BetulaClusterModel.updateE(ClusterFeature cf, double prob)	Process one clustering feature in the E step.
void	DiagonalGaussianModel.updateE(ClusterFeature cf, double wei)
void	MultivariateGaussianModel.updateE(ClusterFeature cf, double wei)
void	SphericalGaussianModel.updateE(ClusterFeature cf, double wei)

Method parameters in elki.clustering.em.models with type arguments of type ClusterFeature

Modifier and Type	Method	Description
java.util.List<M>	BetulaClusterModelFactory.buildInitialModels(java.util.List<? extends ClusterFeature> cfs, int k, CFTree<?> tree)	Build the initial models.
java.util.List<DiagonalGaussianModel>	BetulaDiagonalGaussianModelFactory.buildInitialModels(java.util.List<? extends ClusterFeature> cfs, int k, CFTree<?> tree)
java.util.List<MultivariateGaussianModel>	BetulaMultivariateGaussianModelFactory.buildInitialModels(java.util.List<? extends ClusterFeature> cfs, int k, CFTree<?> tree)
java.util.List<SphericalGaussianModel>	BetulaSphericalGaussianModelFactory.buildInitialModels(java.util.List<? extends ClusterFeature> cfs, int k, CFTree<?> tree)

Uses of ClusterFeature in elki.clustering.kmeans

Method parameters in elki.clustering.kmeans with type arguments of type ClusterFeature

Modifier and Type	Method	Description
private int	BetulaLloydKMeans.assignToNearestCluster(int[] assignment, double[][] means, java.util.ArrayList<? extends ClusterFeature> cfs, int[] weights)	Assign each element to nearest cluster.
protected double[]	BetulaLloydKMeans.calculateVariances(int[] assignment, double[][] means, java.util.ArrayList<? extends ClusterFeature> cfs, int[] weights)	Calculate variance of clusters based on clustering features.
private double[][]	BetulaLloydKMeans.kmeans(java.util.ArrayList<? extends ClusterFeature> cfs, int[] assignment, int[] weights, CFTree<?> tree)	Perform k-means clustering.
private double[][]	BetulaLloydKMeans.means(int[] assignment, double[][] means, java.util.ArrayList<? extends ClusterFeature> cfs, int[] weights)	Calculate means of clusters.

Uses of ClusterFeature in elki.clustering.kmeans.initialization.betula

Methods in elki.clustering.kmeans.initialization.betula that return ClusterFeature

Modifier and Type	Method	Description
private ClusterFeature	CFKPlusPlusLeaves.sampleFirst(ClusterFeature root, java.util.List<? extends AsClusterFeature> cfs, java.util.Random rnd)	Sample the first cluster center.

Methods in elki.clustering.kmeans.initialization.betula with parameters of type ClusterFeature

Modifier and Type	Method	Description
private double	CFKPlusPlusLeaves.initialWeights(ClusterFeature first, java.util.List<? extends AsClusterFeature> cfs, double[] weights)	Initialize the weight list.
private ClusterFeature	CFKPlusPlusLeaves.sampleFirst(ClusterFeature root, java.util.List<? extends AsClusterFeature> cfs, java.util.Random rnd)	Sample the first cluster center.
double	CFInitWeight.squaredWeight(ClusterFeature exist, ClusterFeature cand)	Distance between two clustering features.
double	InterclusterWeight.squaredWeight(ClusterFeature existing, ClusterFeature candidate)
double	SquaredEuclideanWeight.squaredWeight(ClusterFeature c1, ClusterFeature c2)
double	VarianceWeight.squaredWeight(ClusterFeature existing, ClusterFeature candidate)
private double	CFKPlusPlusLeaves.updateWeights(ClusterFeature latest, java.util.List<? extends AsClusterFeature> cfs, double[] weights)	Update the weight list.

Method parameters in elki.clustering.kmeans.initialization.betula with type arguments of type ClusterFeature

Modifier and Type	Method	Description
abstract double[][]	AbstractCFKMeansInitialization.chooseInitialMeans(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)	Build the initial models.
double[][]	CFKPlusPlusLeaves.chooseInitialMeans(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)
double[][]	CFKPlusPlusTree.chooseInitialMeans(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)
double[][]	CFKPlusPlusTrunk.chooseInitialMeans(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)
double[][]	CFRandomlyChosen.chooseInitialMeans(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)
double[][]	CFWeightedRandomlyChosen.chooseInitialMeans(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)
private AsClusterFeature	CFKPlusPlusTree.chooseNextNode(CFNode<?> current, java.util.List<? extends ClusterFeature> ccs, java.util.Random rnd)	Choose a child of the current node.
double[][]	CFKPlusPlusLeaves.run(CFTree<?> tree, java.util.List<? extends ClusterFeature> cfs, int k)	Perform k-means++ initialization.

Uses of ClusterFeature in elki.index.tree.betula

Classes in elki.index.tree.betula with type parameters of type ClusterFeature

Modifier and Type	Class	Description
class	CFNode<L extends ClusterFeature>	Interface for TreeNode
class	CFTree<L extends ClusterFeature>	Partial implementation of the CFTree as used by BIRCH and BETULA.
static class	CFTree.Factory<L extends ClusterFeature>	CF-Tree Factory.
static class	CFTree.Factory.Par<L extends ClusterFeature>	Parameterization class for CFTrees.
static class	CFTree.LeafIterator<L extends ClusterFeature>	Iterator over leaf nodes.

Fields in elki.index.tree.betula declared as ClusterFeature

Modifier and Type	Field	Description
private L	CFNode.cf	Cluster feature
(package private) ClusterFeature[]	CFDistanceMatrix.cfs	Cluster features
private L	CFTree.LeafIterator.current	Current leaf entry.

Fields in elki.index.tree.betula with type parameters of type ClusterFeature

Modifier and Type	Field	Description
(package private) java.util.Map<ClusterFeature,ArrayModifiableDBIDs>	CFTree.idmap	Stored leaf entry to dbid relation

Methods in elki.index.tree.betula with parameters of type ClusterFeature

Modifier and Type	Method	Description
DBIDs	CFTree.getDBIDs(ClusterFeature cf)	Get the DBIDs of a cluster feature (if stored).
protected static java.lang.StringBuilder	CFTree.printDebug(java.lang.StringBuilder buf, ClusterFeature n, int d)	Utility function for debugging.
private double	CFTree.sqabsorption(NumberVector nv, ClusterFeature cf)	Updates statistics and calculates distance between a Number Vector and a Cluster Feature based on selected criteria.
private double	CFTree.sqabsorption(ClusterFeature cf1, ClusterFeature cf2)	Updates statistics and calculates distance between two Cluster Features based on selected criteria.
private double	CFTree.sqdistance(NumberVector nv, ClusterFeature cf)	Updates statistics and calculates distance between a Number Vector and a Cluster Feature based on selected criteria.
private double	CFTree.sqdistance(ClusterFeature cf1, ClusterFeature cf2)	Updates statistics and calculates distance between two Cluster Features based on selected criteria.

Constructors in elki.index.tree.betula with parameters of type ClusterFeature

Constructor	Description
CFDistanceMatrix(ClusterFeature[] cfs)	Constructor.

Uses of ClusterFeature in elki.index.tree.betula.distance

Methods in elki.index.tree.betula.distance with parameters of type ClusterFeature

Modifier and Type	Method	Description
double	AverageIntraclusterDistance.matSelfInit(ClusterFeature cf)
default double	CFDistance.matSelfInit(ClusterFeature cf)	Initialization for self measure for new Combinatorial clustering Methods (Podani 1989)
double	RadiusDistance.matSelfInit(ClusterFeature cf)
double	AverageInterclusterDistance.squaredDistance(NumberVector nv, ClusterFeature cf)
double	AverageInterclusterDistance.squaredDistance(ClusterFeature cf1, ClusterFeature cf2)
double	AverageIntraclusterDistance.squaredDistance(NumberVector nv, ClusterFeature cf1)
double	AverageIntraclusterDistance.squaredDistance(ClusterFeature cf1, ClusterFeature cf2)
double	BIRCHAverageInterclusterDistance.squaredDistance(NumberVector v, ClusterFeature ocf)
double	BIRCHAverageInterclusterDistance.squaredDistance(ClusterFeature ocf1, ClusterFeature ocf2)
double	BIRCHAverageIntraclusterDistance.squaredDistance(NumberVector v, ClusterFeature ocf)
double	BIRCHAverageIntraclusterDistance.squaredDistance(ClusterFeature ocf1, ClusterFeature ocf2)
double	BIRCHRadiusDistance.squaredDistance(NumberVector n, ClusterFeature ocf)
double	BIRCHRadiusDistance.squaredDistance(ClusterFeature ocf1, ClusterFeature ocf2)
double	BIRCHVarianceIncreaseDistance.squaredDistance(NumberVector v, ClusterFeature ocf)
double	BIRCHVarianceIncreaseDistance.squaredDistance(ClusterFeature ocf1, ClusterFeature ocf2)
double	CentroidEuclideanDistance.squaredDistance(NumberVector v, ClusterFeature cf)
double	CentroidEuclideanDistance.squaredDistance(ClusterFeature cf1, ClusterFeature cf2)
double	CentroidManhattanDistance.squaredDistance(NumberVector v, ClusterFeature cf)
double	CentroidManhattanDistance.squaredDistance(ClusterFeature cf1, ClusterFeature cf2)
double	CFDistance.squaredDistance(NumberVector v, ClusterFeature cf)	Distance of a vector to a clustering feature.
double	CFDistance.squaredDistance(ClusterFeature c1, ClusterFeature c2)	Distance between two clustering features.
double	RadiusDistance.squaredDistance(NumberVector nv, ClusterFeature cf1)
double	RadiusDistance.squaredDistance(ClusterFeature cf1, ClusterFeature cf2)
double	VarianceIncreaseDistance.squaredDistance(NumberVector nv, ClusterFeature cf)
double	VarianceIncreaseDistance.squaredDistance(ClusterFeature cf1, ClusterFeature cf2)

Uses of ClusterFeature in elki.index.tree.betula.features

Classes in elki.index.tree.betula.features with type parameters of type ClusterFeature

Modifier and Type	Interface	Description
static interface	ClusterFeature.Factory<F extends ClusterFeature>	Cluster feature factory

Classes in elki.index.tree.betula.features that implement ClusterFeature

Modifier and Type	Class	Description
class	BIRCHCF	Clustering Feature of BIRCH, only for comparison
class	VIIFeature	Clustering Feature of stable BIRCH with a single variance per cluster feature
class	VVIFeature	Clustering Feature of stable BIRCH with variance per dimension
class	VVVFeature	Clustering Feature of stable BIRCH with covariance instead of variance

Methods in elki.index.tree.betula.features that return ClusterFeature

Modifier and Type	Method	Description
ClusterFeature	AsClusterFeature.getCF()	Get as clustering feature.
default ClusterFeature	ClusterFeature.getCF()

Methods in elki.index.tree.betula.features with parameters of type ClusterFeature

Modifier and Type	Method	Description
void	BIRCHCF.addToStatistics(ClusterFeature other)
void	ClusterFeature.addToStatistics(ClusterFeature other)	Add other CF to CF
void	VIIFeature.addToStatistics(ClusterFeature other)
void	VVIFeature.addToStatistics(ClusterFeature other)
void	VVVFeature.addToStatistics(ClusterFeature other)