```
# NOT RUN {
## We are not running these examples any more, because they
## take a long time to run and this is against the CRAN repository
## policy. Copy and paste them by hand to your R prompt if
## you want to run them.
# }
# NOT RUN {
# eigenvectors of a random symmetric matrix
M <- matrix(rexp(10^6), 10^3, 10^3)
M <- (M + t(M))/2
V <- eigen(M, symmetric=TRUE)$vectors[,c(1,2)]
# displays size of the groups in the final partition
gr <- scg_group(V, nt=c(2,3))
col <- rainbow(max(gr))
plot(table(gr), col=col, main="Group size", xlab="group", ylab="size")
## comparison with the grouping obtained by kmeans
## for a partition of same size
gr.km <- kmeans(V,centers=max(gr), iter.max=100, nstart=100)$cluster
op <- par(mfrow=c(1,2))
plot(V[,1], V[,2], col=col[gr],
main = "SCG grouping",
xlab = "1st eigenvector",
ylab = "2nd eigenvector")
plot(V[,1], V[,2], col=col[gr.km],
main = "K-means grouping",
xlab = "1st eigenvector",
ylab = "2nd eigenvector")
par(op)
## kmeans disregards the first eigenvector as it
## spreads a much smaller range of values than the second one
### comparing optimal and k-means solutions
### in the one-dimensional case.
x <- rexp(2000, 2)
gr.true <- scg_group(cbind(x), 100)
gr.km <- kmeans(x, 100, 100, 300)$cluster
scg_eps(cbind(x), gr.true)
scg_eps(cbind(x), gr.km)
# }
# NOT RUN {
# }
```

Run the code above in your browser using DataLab