Re: [R] Question about subsetting S4 object in ROCR

You can access the data directly by using something like perf@x.values[[1]]. Not sure if that helps you. The package pROC allows you to do partial areas under the curve by selecting a range of specificity or sensitivity that you're interested in. On Tue, May 28, 2013 at 2:17 AM, Guido Leoni wrot

Re: [R] Question about subsetting S4 object in ROCR

Ye sorry of course i'm interested to the area ranging from 0;0 to 0.4;0.8 thank you Guido 2013/5/27 Uwe Ligges > > > On 27.05.2013 16:18, Guido Leoni wrote: > >> Dear list >> I'm testing a predictor and I produced nice performance plots with ROCR >> package utilizing the 3 standard command >> >

Re: [R] Question about subsetting S4 object in ROCR

On 27.05.2013 16:18, Guido Leoni wrote: Dear list I'm testing a predictor and I produced nice performance plots with ROCR package utilizing the 3 standard command pred <- prediction(predictions, labels) perf <- performance(pred, measure = "tpr", x.measure = "fpr") plot(perf, col=rainbow(10))

[R] Question about subsetting S4 object in ROCR

Dear list I'm testing a predictor and I produced nice performance plots with ROCR package utilizing the 3 standard command pred <- prediction(predictions, labels) perf <- performance(pred, measure = "tpr", x.measure = "fpr") plot(perf, col=rainbow(10)) The pred object and the perfo object are S4