gforce.metrics: Evaluates the correctness of a clustering solution.

In GFORCE: Clustering and Inference Procedures for High-Dimensional Latent Variable Models

Description

This can be used for either data or variable clustering. Cluster names can be either strings or numbers. Arbitrary data types cannot be used.

Usage

gforce.metrics(true_clust, est_clust, method = "purity")

Arguments

true_clust	length d vector of cluster assignments. This represents the true, or reference, clustering.
est_clust	length d vector of cluster assignments. This represents the estimated clustering.
method	the method used to evaluate the quality of the clustering solution est_clust. The three options are 'purity', 'perfect', 'misclassified-points'.

Value

Returns a numeric that represents the value of the chosen metric on the two clusterings true_clust and est_clust.

Examples

clust1 <- c(1,1,1,2,2,2,3,3,3)
clust2 <- c(1,1,2,1,2,2,3,3,3)
gforce.metrics(clust1,clust2,method='purity')

GFORCE documentation built on May 2, 2019, 3:44 a.m.