Trees
mlpack includes a number of space partitioning trees and other trees for its geometric techniques. These trees are built on data matrices where each column in the matrix is a point in the tree. Trees are organized such that “nearby” points (with respect to a given distance metric) are generally grouped in the same node or branch of the tree.
All trees in mlpack implement the same API, allowing easy plug-and-play usage of different trees. The following tree types are available in mlpack:
KDTreeMeanSplitKDTreeBallTreeMeanSplitBallTreeRPTreeMaxRPTreeBinarySpaceTreeUBTreeCoverTreeOctreeRTreeRStarTreeXTreeRPlusTreeRPlusPlusTreeHilbertRTreeRectangleTree
Note: this documentation is a work in progress. Not all trees are documented yet.
In general, it is not necessary to create an mlpack tree directly, but instead to simply specify the type of tree a particular algorithm should use via a template parameter. For instance, all of the algorithms below use mlpack trees and can have the type of tree specified via template parameters:
NeighborSearch(for k-nearest-neighbor and k-furthest-neighbor)RangeSearchKDEFastMKSDTB(for computing Euclidean minimum spanning trees)KRANN
Note: if you are looking for documentation on decision trees, see the
documentation for the DecisionTree class.