maximiseSilhouette {coca} | R Documentation |
Choose the number of clusters K that maximises the silhouette, starting from a set of kernel matrices each corresponding to a different choice of K and the corresponding clusterings of the data for each of those values of K.
maximiseSilhouette(
kernelMatrix,
clLabels,
maxK,
savePNG = FALSE,
fileName = "silhouette",
isDistance = FALSE,
widestGap = FALSE,
dunns = FALSE,
dunn2s = FALSE
)
kernelMatrix |
N X N X (maxK-1) array of kernel matrices. |
clLabels |
(maxK-1) X N matrix containing the clusterings obtained for different values of K. |
maxK |
Maximum number of clusters considered. |
savePNG |
If TRUE, a plot of the silhouette is saved in the working folder. Defaults to FALSE. |
fileName |
If |
isDistance |
Boolean. If TRUE, the kernel matrices are interpreted as matrices of distances, otherwise as matrices of similarities. |
widestGap |
Boolean. If TRUE, also computes widest gap index (and plots
it if |
dunns |
Boolean. If TRUE, also computes Dunn's index: minimum separation
/ maximum diameter (and plots it if |
dunn2s |
Boolean. If TRUE, also computes an alternative version
of Dunn's index: minimum average dissimilarity between two cluster / maximum
average within cluster dissimilarity (and plots it if |
The function returns a list containing:
silh |
a vector of length |
K |
the lowest number of clusters for which the silhouette is maximised. |
Alessandra Cabassi alessandra.cabassi@mrc-bsu.cam.ac.uk