Hi All,
I am looking for some help figuring out what is causing an error in my
attempt to fit a regularized logistic regression (specifically finding the
optimal lambda value using cv.glmnet).
Running the following command:
RegLR_CV<-cv.glmnet(x=train.sub.clean[,-c(431)],y=as.factor(train.sub$finalAttrite),family="binomial")
where the table train.sub.clean are all numeric and has had all zero
variance variables removed (using the carat package).
This function runs for a while then produces the following error. Anyone
recommend what I should be looking for to troubleshoot? It must be my data
set as the toy examples in the package run fine.
Error:
Error in as.matrix(cbind2(1, newx) %*% nbeta) :
error in evaluating the argument 'x' in selecting a method for
function 'as.matrix': Error in t(.Call(Csparse_dense_crossprod, y,
t(x))) :
error in evaluating the argument 'x' in selecting a method for
function 't': Error: invalid class 'NA' to dup_mMatrix_as_dgeMatrix
R:
R version 2.13.0 (2011-04-13)
Platform: x86_64-pc-mingw32/x64 (64-bit)
glmnet: 1.7
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
