Skip to contents

Parallel NN indexing

Source: R/gene_clustering.R
parallel_nn2_idx.Rd

This function provides a parallel approach of finding the nearest neighbours of each points on a given embedding. The parallelisation is done by splitting the data into chunks and running the RANN::nn2 function on each chunk in parallel.

Usage

parallel_nn2_idx(embedding, k)

Arguments

embedding

The embedding matrix where each row represents a point and each column a dimension.

k

The number of nearest neighbours to be found.

Value

A matrix where each row contains the indices of the k-nearest neighbours of the corresponding point.