scgNormEps(V, groups, mtype = c("symmetric", "laplacian",
"stochastic"), p = NULL, norm = c("row", "col"))
V
).nrow(V)
integers labeling
each group vertex in the partition.nrow(V)
.
p
is the stationary probability distribution of a Markov chain
when mtype
= normEps
returns with a numeric vector whose $i$th component is
$\Vert v_i-Pv_i\Vert$ (see Details).scgNormEps
computes $\Vert v_i-Pv_i\Vert$,
where $v_i$ is the $i$th eigenvector in V
and
$P$ is the projector corresponding to the mtype
argument.scg
.v <- rexp(20)
km <- kmeans(v,5)
sum(km$withinss)
scgNormEps(cbind(v), km$cluster)^2
Run the code above in your browser using DataLab