knn: k-Nearest-Neighbors Search

In mlpack: 'Rcpp' Integration for the 'mlpack' Library

k-Nearest-Neighbors Search

Description

An implementation of k-nearest-neighbor search using single-tree and dual-tree algorithms. Given a set of reference points and query points, this can find the k nearest neighbors in the reference set of each query point using trees; trees that are built can be saved for future use.

Usage

knn(
  algorithm = NA,
  epsilon = NA,
  input_model = NA,
  k = NA,
  leaf_size = NA,
  query = NA,
  random_basis = FALSE,
  reference = NA,
  rho = NA,
  seed = NA,
  tau = NA,
  tree_type = NA,
  true_distances = NA,
  true_neighbors = NA,
  verbose = getOption("mlpack.verbose", FALSE)
)

Arguments

algorithm	Type of neighbor search: 'naive', 'single_tree', 'dual_tree', 'greedy'. Default value "dual_tree" (character).
epsilon	If specified, will do approximate nearest neighbor search with given relative error. Default value "0" (numeric).
input_model	Pre-trained kNN model (KNNModel).
k	Number of nearest neighbors to find. Default value "0" (integer).
leaf_size	Leaf size for tree building (used for kd-trees, vp trees, random projection trees, UB trees, R trees, R* trees, X trees, Hilbert R trees, R+ trees, R++ trees, spill trees, and octrees). Default value "20" (integer).
query	Matrix containing query points (optional) (numeric matrix).
random_basis	Before tree-building, project the data onto a random orthogonal basis. Default value "FALSE" (logical).
reference	Matrix containing the reference dataset (numeric matrix).
rho	Balance threshold (only valid for spill trees). Default value "0.7" (numeric).
seed	Random seed (if 0, std::time(NULL) is used). Default value "0" (integer).
tau	Overlapping size (only valid for spill trees). Default value "0" (numeric).
tree_type	Type of tree to use: 'kd', 'vp', 'rp', 'max-rp', 'ub', 'cover', 'r', 'r-star', 'x', 'ball', 'hilbert-r', 'r-plus', 'r-plus-plus', 'spill', 'oct'. Default value "kd" (character).
true_distances	Matrix of true distances to compute the effective error (average relative error) (it is printed when -v is specified) (numeric matrix).
true_neighbors	Matrix of true neighbors to compute the recall (it is printed when -v is specified) (integer matrix).
verbose	Display informational messages and the full list of parameters and timers at the end of execution. Default value "getOption("mlpack.verbose", FALSE)" (logical).

Details

This program will calculate the k-nearest-neighbors of a set of points using kd-trees or cover trees (cover tree support is experimental and may be slow). You may specify a separate set of reference points and query points, or just a reference set which will be used as both the reference and query set.

Value

A list with several components:

distances	Matrix to output distances into (numeric matrix).
neighbors	Matrix to output neighbors into (integer matrix).
output_model	If specified, the kNN model will be output here (KNNModel).

Author(s)

mlpack developers

Examples

# For example, the following command will calculate the 5 nearest neighbors
# of each point in "input" and store the distances in "distances" and the
# neighbors in "neighbors": 

## Not run: 
output <- knn(k=5, reference=input)
neighbors <- output$neighbors
distances <- output$distances

## End(Not run)

# The output is organized such that row i and column j in the neighbors
# output matrix corresponds to the index of the point in the reference set
# which is the j'th nearest neighbor from the point in the query set with
# index i.  Row j and column i in the distances output matrix corresponds to
# the distance between those two points.

mlpack documentation built on Oct. 5, 2024, 9:08 a.m.