Entering edit mode

Jörg
▴
40

@jorg-3228
Last seen 9.9 years ago

Hello,
I have been working a lot with the clValid package lately. I find it a
really helpful, well written and documented package. However, I ran
into a problem and hope someone can help me:
Using this command:
"
clust=clValid(obj=matrix,nClust=2:8,validation=c("internal",
"stability"),metric ="euclidean", method ="average",neighbSize =
10,maxitems =dim(matrix)[1], clMethods = c("fanny"))"
I receive the following messages:
Warning messages:
1: In vClusters(mat, clMethods[i], nClust, validation = validation, :
fanny unable to find 4 clusters, returning NA for these validation
measures
2: In vClusters(mat, clMethods[i], nClust, validation = validation, :
fanny unable to find 5 clusters, returning NA for these validation
measures
...(repeats until 8 clusters)
There are no fuzzy clusters computed for k=4..8
However, using fanny directly there is no warning message at all (the
same for k=4..8):
fanny(x=matrix,k=5,metric ="euclidean",maxit = 500)
Note that maxit=500 is the standard and not reached for any of the
clusters.
Interestingly using metric ="correlation" reports no warnings for
clValid.
Any idea what the problem might be?
Thanks a lot
J?rg
--