Kohonen SOM plot is displaying observations within cluster plot. how to remove?

Question

I am running :

kmeansDat.t <- som_model$codes[[1]] %>% as.matrix


som_cluster <- cutree(hclust(dist(kmeansDat.t)), 5) %>% as.matrix
# plot these results:
plot(som_model, type="mapping", bgcol = pretty_palette[som_cluster], main = "Clusters") 
add.cluster.boundaries(som_model, som_cluster)

My output is cluttered by dark circles each appears to be representing the number of observations in each node. How can I remove them ?

Any idea why this is happening?

Answer 1

Setting pchs="" inside plot.kohonen solves the problem:

library(kohonen)
library(magrittr)
# A dataset for testing the code
data(yeast)
X <- matrix(rnorm(100000), nrow=1000)
som_model <- som(X, somgrid(30, 30, "hexagonal"))
kmeansDat.t <- som_model$codes[[1]] %>% as.matrix
pretty_palette <- rainbow(5)   
som_cluster <- cutree(hclust(dist(kmeansDat.t)), 5) %>% as.matrix
# Plot Kohonen's map
plot(som_model, type="mapping", bgcol = pretty_palette[som_cluster], 
     main = "Clusters", pchs="") 
add.cluster.boundaries(som_model, som_cluster)