Silhouette (clustering)

Determining the optimal number of cluster in the ACCA clustering using the average silhouette approach.

Usage

best_acca(m, ...)

# S3 method for class 'cmatrix'
best_acca(m, mink, maxk, maxrep = 2L, maxiter = 100L, ...)

# S3 method for class 'matrix'
best_acca(m, mink, maxk, maxrep = 2L, maxiter = 100L, ...)

Arguments

m

[matrix(1)]
correlation matrix from corr_matrix.

...

Not used. Included for S3 method consistency.

mink

[integer(1)]
minimum number of clusters considered.

maxk

[integer(1)]
maximum number of clusters considered.

maxrep

[integer(1)]
maximum number of interactions without change in the clusters in the ACCA method.

maxiter

[integer(1)]
maximum number of interactions in the ACCA method.

Value

[list(3)]
A list with: silhouette average with per k $silhouette.ave; the sequence of clusters tested $k and the optimal number of clusters $best.k.

References

Leonard Kaufman; Peter J. Rousseeuw (1990). Finding groups in data : An introduction to cluster analysis. Hoboken, NJ: Wiley-Interscience. p. 87. doi:10.1002/9780470316801. ISBN 9780471878766.

Starczewski, Artur, and Adam Krzyżak. "Performance evaluation of the silhouette index. "International Conference on Artificial Intelligence and Soft Computing. Springer, Cham, 2015.

See also

sil_acca

Author

Igor D.S. Siciliani, Paulo H. dos Santos

Examples

x <- corrp::corrp(iris)
m <- corrp::corr_matrix(x)
best_acca(m, 2, 6)
#> $silhouette.ave
#> [1]  0.1269651 -0.4922020 -0.1472888  0.0000000 -0.2543257
#> 
#> $k
#> [1] 2 3 4 5 6
#> 
#> $best.k
#> [1] 2
#>