[R] Error in Rose Method (class balancing)

[Neha gupta]

Hello David, thanks for your reply. I have added the information.

library(caret)
library(farff)
library(DMwR)

d=readARFF("bughunter.arff")
dput( head( d, 30 ) )

index <- createDataPartition(d$`Bug class`, p = .70,list = FALSE)

tr <- d[index, ]

ts <- d[-index, ]

boot3 <- trainControl(method = "repeatedcv", number=10,
repeats=10,classProbs = TRUE,verboseIter = FALSE,

summaryFunction = twoClassSummary, sampling = "rose")

set.seed(30218)

ct <- train(`Bug class` ~ ., data = tr, method = "pls", metric = "AUC", preProc
= c("center", "scale", "nzv"), trControl = boot3)

getTrainPerf(ct)

On Thu, Jul 23, 2020 at 1:08 AM David Winsemius <dwinsemius using comcast.net>
wrote:

>
> On 7/22/20 3:43 PM, Neha gupta wrote:
> > Hello,
> >
> >
> > I get the following error when I use the ROSE class balancing method but
> > when I use other methods like SMOTE, up, down, I do not get any error
> > message.
> >
> >
> > Something is wrong; all the ROC metric values are missing:
> >
> > ROC Sens Spec
> >
> > Min. : NA Min. : NA Min. : NA
> >
> > 1st Qu.: NA 1st Qu.: NA 1st Qu.: NA
> >
> > Median : NA Median : NA Median : NA
> >
> > Mean :NaN Mean :NaN Mean :NaN
> >
> > 3rd Qu.: NA 3rd Qu.: NA 3rd Qu.: NA
> >
> > Max. : NA Max. : NA Max. : NA
> >
> >
> >
> > library(DMwR)
> >
> > d=readARFF("bughunter.arff")
>
> After installing that package and loading pkg:DMwR I get:
>
>
> Error in readARFF("bughunter.arff") : could not find function "readARFF"
>
>
> Since you also posted in HTML, I suggest you read the Posting Guide,
> restart and R session and post a reproducible example that loads all
> needed packages and data.
>
> --
>
> David.
>
> >
> > index <- createDataPartition(d$`Bug class`, p = .70,list = FALSE)
> >
> > tr <- d[index, ]
> >
> > ts <- d[-index, ]
> >
> > boot3 <- trainControl(method = "repeatedcv", number=10,
> > repeats=10,classProbs = TRUE,verboseIter = FALSE,
> >
> > summaryFunction = twoClassSummary, sampling = "rose")
> >
> > set.seed(30218)
> >
> > ct <- train(`Bug class` ~ ., data = tr,
> >
> > method = "pls",
> >
> > metric = "AUC",
> >
> > preProc = c("center", "scale", "nzv"),
> >
> > trControl = boot3)
> >
> > getTrainPerf(ct)
> >
> >       [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
> > 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.
>

	[[alternative HTML version deleted]]