1
Regarding cross validation, I would like to know if when we use the command below the system makes a random choice of data or sequential. I am looking for a way to use the data order to generate the Folds (K=10) and not a random form.
cross_validation = trainControl (method="cv", number=10)
classificador = naiveBayes(x=base[-13], y=base$target, trcontrol=cross_validation)
1
The choice of the data is random. If the argument method is not defined, the method of resampling used is the bootstrap. By definition, bootstrap is a random (i.e., non-sequential) method of resampling with replenishment.
Also, the expression "Cross Validation in the dataset sequence" makes no sense. Cross-validation is a resampling technique and should be done randomly. If it is not random, it is not cross-validation.
Browser other questions tagged r machine-learning
You are not signed in. Login or sign up in order to post.