Skip to contents

Calculate eigengap and rotation-cost estimates of the number of clusters to use when clustering a similarity matrix. This function was adapted from SNFtool::estimateClustersGivenGraph, but scales up the Laplacian operator prior to eigenvalue calculations to minimize the risk of floating point-related errors.

Usage

estimate_nclust_given_graph(W, NUMC = 2:10)

Arguments

W

Similarity matrix to calculate number of clusters for.

NUMC

Range of cluster counts to consider among when picking best number of clusters.

Value

A list containing the top two eigengap and rotation-cost estimates for the number of clusters in a given similarity matrix.