"argument is of length zero" error in RandomForest tuneRF()

Question

I used this code,

tuneRF(x = mtry[,c(4:18)],
   y = mtry$Os, ntreeTry=50, stepFactor=2, 
   improve=0.05,trace=TRUE, plot=TRUE, doBest=FALSE)

And got the error:

Error in if (errorOld < 0) stop("Initial setting gave 0 error and no room for improvement.") :
argument is of length zero

What should I change?

You should provide a [reproducible example](http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) — MrFlick, Dec 09 '15 at 21:22
yes. I prepared on dataset that it's 80% of total data. ans os is one column that I want to predict it. — s.tajik, Dec 11 '15 at 16:48

score 0 · Answer 1 · answered Aug 16 '17 at 20:39

I ran into this same error when my I accidentally typed a column that didn't exist for the response column. Perhaps your mtry$Os column does not exist (it's hard to solve your problem w/o a reproducible example).

Example:

> library(randomForest)
> data("iris")
> tuneRF(x = iris[1:4,], y = iris$notacol)
Error in if (errorOld < 0) stop("Initial setting gave 0 error and no room for improvement.") : 
  argument is of length zero

"argument is of length zero" error in RandomForest tuneRF()

1 Answers1