Package jsat.linear.vectorcollection

Interface Summary

Interface	Description
BaseCaseDT
DualTree<V extends Vec>
IncrementalCollection<V extends Vec>	This interface is for Vector Collections that support incremental construction.
IndexNode<N extends IndexNode>
ScoreDT
ScoreDTLazy
VectorCollection<V extends Vec>	A Vector Collection is a collection of vectors that is meant to be used to obtain a subset of the collection via a query vector.

Class Summary

Class	Description
BallTree<V extends Vec>	This class implements the Ball Tree algorithm for accelerating nearest neighbor queries.
CoverTree<V extends Vec>	This class implements the Cover-tree algorithm for answering nearest neighbor queries.
DefaultVectorCollection<V extends Vec>	This class is a generic wrapper for the Vector Collection objects within JSAT.
DualTree.DualTreeTraversalAction
DualTree.SelfAsChildNode<N extends IndexNode<N>>	This class is used as a helper class to deal with Dual Trees which may contain points in branching nodes.
IndexDistPair	This class exists as a helper method for use with nearest neighbor implementations.
IndexTuple
KDTree<V extends Vec>	Standard KDTree implementation.
RandomBallCover<V extends Vec>	An implementation of the exact search for the Random Ball Cover algorithm.
RandomBallCoverOneShot<V extends Vec>	An implementation of the on shot search for the Random Ball Cover algorithm.
RTree<V extends Vec>
SVPTree<V extends Vec>	Provides a simplified implementation of Vantage Point Trees, as described in "Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces" by Peter N.
VectorArray<V extends Vec>	This is the naive implementation of a Vector collection.
VectorCollectionUtils	A collection of common utility methods to perform on a VectorCollection
VPTree<V extends Vec>	Provides an implementation of Vantage Point Trees, as described in "Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces" by Peter N.
VPTreeMV<V extends Vec>	The VPTreeMV is an extension of the VPTree, the MV meaning "of Minimum Variance".

Enum Summary

Enum	Description
BallTree.ConstructionMethod
BallTree.PivotSelection
KDTree.PivotSelection	KDTree uses an index of the vector at each stage to use as a pivot, dividing the remaining elements into two sets.
VPTree.VPSelection