Hello!
Using FIX, I do not get an RData file when training a classifier, using my data. I get the following error in the .RLog1 log:
f.vec[is.nan(f.vec)] <- min(f.vec[!is.nan(f.vec)])
Warning message:
In min(f.vec[!is.nan(f.vec)]) :
no non-missing arguments to min; returning Inf
>
> # select usign Kruskal test
> data.train.pval.vec <- apply(hcp.data[,-dim(hcp.data)[2]], 2, function(x){kruskal.test(x, as.numeric(hcp.data$class.labs))$p.value})
Error in kruskal.test.default(x, as.numeric(hcp.data$class.labs)) :
'x' and 'g' must have the same length
Calls: apply -> FUN -> kruskal.test -> kruskal.test.default
Execution halted
This warning pops up when NAs exist in a data set, but I cannot trace any files back to see where NAs might be produced. Any thoughts on where this issue might be coming from and how to correct it?
Ted
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=FSL&A=1
This message was issued to members of www.jiscmail.ac.uk/FSL, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/
|