Package gov.sandia.cognition.learning.algorithm.clustering

Provides clustering algorithms.

See: Description

Interface Summary

Interface	Description
BatchClusterer<DataType,ClusterType extends Cluster<DataType>>	The BatchClusterer interface defines the functionality of a batch clustering algorithm.

Class Summary

Class	Description
AffinityPropagation<DataType>	The AffinityPropagation algorithm requires three parameters: a divergence function, a value to use for self-divergence, and a damping factor (called lambda in the paper; 0.5 is the default).
AgglomerativeClusterer<DataType,ClusterType extends Cluster<DataType>>	The AgglomerativeClusterer implements an agglomerative clustering algorithm, which is a type of hierarchical clustering algorithm.
AgglomerativeClusterer.HierarchyNode<DataType,ClusterType extends Cluster<DataType>>	Holds the hierarchy information for the agglomerative clusterer.
DBSCANClusterer<DataType extends Vectorizable,ClusterType extends Cluster<DataType>>	The DBSCAN algorithm requires three parameters: a distance metric, a value for neighborhood radius, and a value for the minimum number of surrounding neighbors for a point to be considered non-noise.
DirichletProcessClustering	Clustering algorithm that wraps Dirichlet Process Mixture Model.
KMeansClusterer<DataType,ClusterType extends Cluster<DataType>>	The KMeansClusterer class implements the standard k-means (k-centroids) clustering algorithm.
KMeansClustererWithRemoval<DataType,ClusterType extends Cluster<DataType>>	Creates a k-means clustering algorithm that removes clusters that do not have sufficient membership to pass a simple statistical significance test.
KMeansFactory	Creates a parallelized version of the k-means clustering algorithm for the typical use: clustering vector data with a Euclidean distance metric.
MiniBatchKMeansClusterer<DataType extends Vector>	Approximates k-means clustering by working on random subsets of the data.
MiniBatchKMeansClusterer.Builder<DataType extends Vector>	Can be used to create custom MiniBatchKMeansClusterers without using the big constructor.
OptimizedKMeansClusterer<DataType>	This class implements an optimized version of the k-means algorithm that makes use of the triangle inequality to compute the same answer as k-means while using less distance calculations.
ParallelizedKMeansClusterer<DataType,ClusterType extends Cluster<DataType>>	This is a parallel implementation of the k-means clustering algorithm.
PartitionalClusterer<DataType,ClusterType extends Cluster<DataType>>	The PartitionalClusterer implements a partitional clustering algorithm, which is a type of hierarchical clustering algorithm.

Package gov.sandia.cognition.learning.algorithm.clustering Description

Provides clustering algorithms. Clustering algorithms are a type of unsupervised learning that attempts to find appropriate groupings from given data.

Since:

2.0

Author:

Justin Basilico