ClusterAMI: Adjusted Mutual Information [Vinh et al., 2009]

In FCPS: Fundamental Clustering Problems Suite

Adjusted Mutual Information [Vinh et al., 2009]

Description

Mutual information measures the amount of information that two clusterings share: the higher the MI, the more information shared, indicating a higher similarity between the two clusterings [Cover and Thomas, 1991].

Usage

ClusterAMI(Cls1, Cls2)

Arguments

Cls1	1:n numerical vector of numbers defining the classification as the main output of the first clustering or trial for the n cases of data. It has k unique numbers representing the arbitrary labels of the clustering.
Cls2	1:n numerical vector of numbers defining the classification as the main output of the second clustering algorithm trial for the n cases of data. It has p unique numbers representing the arbitrary labels of the clustering.

Details

Adjusted mutual information ranges from 0 (no similarity between true labels and cluster assignments) to 1 (perfect similarity). It adjusts for chance associations between true labels and cluster assignments.

Value

value of adjusted mutual information

Author(s)

Michael Thrun (Wrapper only)

References

[Vinh et al., 2009] Vinh, N. X.; Epps, J.; Bailey, J.: Information theoretic measures for clusterings comparison, Proceedings of the 26th Annual International Conference on Machine Learning (ICML), doi:10.1145/1553374.1553511, 2009.

[Cover and Thomas, 1991] Cover, T, and Thomas, J.A.: Elements of Information Theory. Wiley, 1991.

Examples

data(Hepta)
#compare to baseline
Cls2=kmeansClustering(Hepta$Data,7,Type = "Steinley")$Cls
ClusterAMI(Hepta$Cls,Cls2)
#compare different solutions
Cls3=kmeansClustering(Hepta$Data,5)$Cls
ClusterAMI(Cls3,Cls2)

FCPS documentation built on Nov. 5, 2025, 7:44 p.m.