CODEWITHSUNDEEP
rfunctionsyntax-error
Skylar Gay
Skylar Gay

Reputation: 7

How to resolve a NA/NaN/Inf execution halted error?

Quitting from lines 12-26 (6,4-PresentationRMARKDOWN.Rmd) Error in do_one(nmeth) : NA/NaN/Inf in foreign function call (arg 1) Calls: ... withCallingHandlers -> withVisible -> eval -> eval -> kmeans -> do_one

Execution halted

pwvspl <- function(dataselected){
  dataselected <- iris
  data(dataselected)
  set.seed(8593)
  dataselected
  dataselected$species <- NULL
  (kmeans.result <- kmeans(dataselected,3))
  table(dataselected$Species, kmeans.result$cluster)
  plot(dataselected[c("Petal.Length","Petal.Width")], col = kmeans.result$cluster)
  points(kmeans.result$centers[c("Petal.Length","Petal.Width")],col=1:3, pch=3, cex=2)
  data(dataselected)
  data_for_clustering <-dataselected[,-5]
  clusters_dataselected <- kmeans(data_for_clustering, centers=3)
  plotcluster(data_for_clustering,clusters_dataselected$cluster)
  clusplot(data_for_clustering,clusters_dataselected$cluster, color=TRUE, shade=TRUE, main = "Petal Width vs. Petal Length", xlab="Petal Length", ylab="Petal Width")
}

I am unsure what is causing this error. How do I resolve this error?

Upvotes: 0

Views: 276

Answers (2)

user16051136
user16051136

Reputation:

Instead of dataselected$species <- NULL change this line to just converting the species factors to numeric:

dataselected$Species <- as.numeric(dataselected$Species)

enter image description here

Upvotes: 1

Julian Neuer
Julian Neuer

Reputation: 316

Welcome to SO.

The traceback shows

3. do_one(nmeth) 
2. kmeans(dataselected, 3) 
1. pwvspl()

which means the error is inside the kmeans function. To be precise, the error is in function do_one, which is called by kmeans.

The help page for kmeans says

numeric matrix of data, or an object that can be coerced to such a matrix (such as a numeric vector or a data frame with all numeric columns).

But the iris dataframe has nonnumeric columns (whose values become NA when the function tries to coerce them to numeric).

That's the cause of the error.

Upvotes: 0

Related Questions