kmknn: k-Means for k-Nearest Neighbors

Implements a k-nearest neighbor search based on pre-clustering with the k-means algorithm, as described by Wang (2012). This is faster than conventional kd-trees for neighbor searching in higher (> 20) dimensional data. Functions are also provided to search for all neighbors within a given distance. Parallelization is achieved using the BiocParallel framework.

if (!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")

BiocManager::install("kmknn")

Try the kmknn package in your browser