Several clustering indexes implementation

This indexes are designed to measure the similarity of two partitions.

All this indices are based on counting pair depending on wether they belong to the same cluster or not according to the partition C or C'. There are four possibilities:

• yy : the two points belong to the same cluster according to both C and C'
• yn : the two points belong to the same cluster according to C but not to C'
• ny : the two points belong to the same cluster according to C' but not to C
• nn : the two points does not belong to the same cluster according to C and C'

Also call Czebanowski-Dice index or Ochiai index

1. Silke Wagner and Dorothea Wagner, Comparing Clustering - An Overview, 2007
2. Bernard Desgraupes, Clustering Indices, 2016, [https://CRAN.R-project.org/package=clusterCrit]
3. Rand, William M.: Objective Criteria for the Evaluation of Clustering Methods. Journal of the American Statistical Association, 66(336):846-850, 1971.
4. Fowlkes, E. B., Mallows, C. L.: A Method for Comparing Two Hierarchical Clusterings. Journal of the American Statistical Association, 78(383):553–569, 1983.

• add internal cluster indexes
• complete References section
• add definition and formula for each indexes