search

mlampros / ClusterR

Gaussian mixture models, k-means, mini-batch-kmeans and k-medoids clustering
https://mlampros.github.io/ClusterR/
84 stars 29 forks source link

Silhouette plot, margins too small #7

Closed elbamos closed 6 years ago

elbamos commented 6 years ago 
kmed_clusters <- analyte_data %>%
  select(-id) %>%
  as.matrix() %>%
  Cluster_Medoids(kmed_chosen, threads=2, swap_phase = MEDOID_SWAP)
par(mar=c(0,0,0,0))
Silhouette_Dissimilarity_Plot(kmed_clusters)

Produces:

Error in plot.new() : figure margins too large

Any advice?

mlampros commented 6 years ago

@elbamos I'm sorry for the late reply,

if kmed_chosen ( the clusters parameter) is large then probably the silhouette plot does not fit in the pc screen (even if edges of plot dragged / expanded). There was a related issue a few days back for another function but I think it applies to your issue too (especially the second part of the answer). Any suggestions are welcome.

mlampros commented 6 years ago

I close the issue for now, feel free to reopen it.