[R] roc plot with zero length labels error

Uwe Ligges ligges at statistik.tu-dortmund.de
Fri Nov 13 19:50:21 CET 2009


[Going through some old and from what I see unanswered messages

Hard to tell what is going on without telling us the data. Works with 
the examples, so may be related to one of the objects scicomp5.model1, 
pred, T, or auc.


 > PLEASE do read the posting guide 
http://www.R-project.org/posting-guide.html
 > and provide commented, minimal, self-contained, reproducible code.


Best wishes,
Uwe Ligges




Chris Anderson wrote:
> I am trying to create the roc plot bootstrap method from library(verification), and when I set the plot =both or emp then I get the following error. The roc.plot works fine when the plot is set to binorm. This is my first time using this function in R and am not sure what this error means or how to resolve the issue. It seems to work ok with the example dataset. Is there an option or data formatting I need to due to resolve this error? 
>  
> roc.plot((scicomp5.model1[164]=="High Price"), pred, CI = T, n.boot = 100, plot = 'both',binormal = TRUE,
> +          main = paste('AREA UNDER CURVE (AUC) =', round(auc$A, 2)))
> Error in text.default(DAT[id, 3, i], DAT[id, 2, i], plot.thres[id2], pos = 4,  : 
>   zero length 'labels'
> 
> 
> 
> Chris Anderson
> 
> http://www.seocodebreaker.com/?thankyou-page=429
> ____________________________________________________________
> Instant Debt Consolidation Quote
> Free debt consolidation quote online! No obligation. No credit check.
> http://thirdpartyoffers.netzero.net/TGL2241/c?cp=cyoog8NQa4mNZIgs6R2NrwAAJ1HbVVWM9bC-t-Va2hgXndJzAAQAAAAFAAAAAEWLnT8AAAMlAAAAAAAAAAAAAAAAABI2kQAAAAA=
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at 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.




More information about the R-help mailing list