knn.search: Search Nearest Neighbors

In ExactSampling: ExactSampling: risk evaluation using exact resampling methods for the k Nearest Neighbor algorithm.

Description

Return index and distance for the k nearest neighbors of each observation. Neighbors are obtained using the canonical Euclidian distance.

Usage

knn.search(data, k =1)

Arguments

data	an input data.frame or matrix Where each line corresponds to an observation.
k	the maximum number of nearest neighbors to search.

Details

Neighbors are found using the kd-tree algorithm.

Value

index	an n x k matrix of nearest neighbor indices.
dist	an n x k matrix of nearest neighbor distances.

Author(s)

The function has been implemented by Kai Li.

See Also

knn.emp for empirical estimation of the risk, knn.boot for an exact bootstrap estimation, and knn.cv for cross-validated estimation for the kNN algorithm.

Examples

data(Spam)
spam.data <- Spam[,-58]
knn.search(data=spam.data,k=7)

ExactSampling documentation built on May 2, 2019, 6:08 p.m.