allpair_RandIndex {clustra}

allpair_RandIndex: helper for replicated cluster comparison

Description

Runs RandIndex for all pairs of cluster results in its list input and produces a matrix for use by rand_plot. Understands replicates within k values.

Usage

allpair_RandIndex(results)

Arguments

results

A list with each element packed internally by the clustra_rand function with elements:

• k - number of clusters

• rep - replicate number

• deviance - final deviance

• group - integer cluster assignments Note that item order is assumed to be the same across all rep and k but group numbering need not be same. The algorithm only examines if pairs of items are in same or different clusters within each results list element.

Value

A data frame with RandIndex for all pairs from trajectories results. The data frame names and its format is intended to be the input for rand_plot. Note that all pairs is the lower triangle plus diagonal of an all-pairs symmetric matrix.