evaluationScheme-class {recommenderlab} | R Documentation |
An evaluation scheme created from a data set. The scheme can be a simple split into training and test data, k-fold cross-evaluation or using k bootstrap samples.
Objects can be created by
evaluationScheme(data, method="split", train=0.9, k=10, given=3).
method
:"character"
;
evaluation method.given
:"integer"
; items given for evaluation. k
:"integer"
; number of runs for evaluation. train
:"numeric"
; portion of data used for training for "split" and
"bootstrap".runsTrain
:"list"
; internal
repesentation for the split in training and test data for the
evaluation runs.data
:"ratingMatrix"
; the data set. knownData
:"ratingMatrix"
; data
set with only known (given) items. unknownData
:"ratingMatrix"
;
data set with only unknown items. signature(x = "evaluationScheme")
: access data.
Parameters are type
("train", "known" or "unknown") and
run
(1...k).signature(object = "evaluationScheme")