[R] Error finding clusters for new data with FlexMix

Luiz Alberto Lima mr.luizalberto at gmail.com
Sun Sep 27 07:54:49 CEST 2015


Hello,

I am trying to find the clusters for new data using FlexMix. I have the
following code:

library(flexmix)

x <- c(0.605, 0.523, 0.677, 0.101, 0.687, 0.586, 0.517, 0.592, 0.653,
0.617)
y <- c(0.222, 0.741, 0.182, 0.162, 0.192, 0.254, 0.745, 0.669, 0.198,
0.214)
test <- c(0.720, 0.168, 0.520, 0.134, 0.558)

model <- flexmix(y ~ x, data = data.frame(x = x, y = y), k=2)
pred <- predict(model, newdata=data.frame(x = test))
clusters_train <- clusters(model)
clusters_test <- clusters(model, newdata=data.frame(x = test))

When I execute the last line of the code, I receive the following error
message:

> clusters_test <- clusters(model, newdata=data.frame(x = test))
Error in model.frame.default(model at terms, data = data, na.action = NULL,  :
  variable lengths differ (found for 'x')

What am I doing wrong?

Thanks!

	[[alternative HTML version deleted]]



More information about the R-help mailing list