evaluate {recommenderlab} | R Documentation |
Evaluates a single or a list of recommender model given an evaluation scheme.
evaluate(x, method, ...) ## S4 method for signature 'evaluationScheme, character': evaluate(x, method, n=1:10, parameter=NULL, progress = TRUE, keepModel=FALSE) ## S4 method for signature 'evaluationScheme, list': evaluate(x, method, n=1:10, parameter=NULL, progress = TRUE, keepModel=FALSE)
x |
an evaluation scheme (class "evaluationScheme" ). |
method |
a character string or a list. If
a single character string is given it defines the recommender method
used for evaluation. If several recommender methods need to be compared,
method contains a nested list. Each element describes a recommender
method and consists of a list with two elements: a character string
named "method" containing the method and a list names
"parameters" containing the parameters used for this recommender method.
See Recommender for available methods. |
n |
N (number of recommendations) of the top-N lists generated. |
parameter |
parameters for the recommender algorithm. |
progress |
report progress? |
keepModel |
store used recommender models? |
... |
further arguments. |
Returns an object of class "evaluationResults"
or if method
is a list an object of class "evaluationResultList"
.
evaluationScheme
,
evaluationResults
.
evaluationResultList
.
data("MSWeb") MSWeb10 <- sample(MSWeb[rowCounts(MSWeb) >10,], 100) ## create an evaluation scheme es <- evaluationScheme(MSWeb10, method="cross-validation", k=4, given=3) ## run evaluation ev <- evaluate(es, "POPULAR") ev ## look at the results avg(ev) plot(ev, type="o", annotate = TRUE) ## now run evaluate with a list algorithms <- list( RANDOM = list(name = "RANDOM", param = NULL), POPULAR = list(name = "POPULAR", param = NULL), UBCF = list(name = "UBCF", param = NULL), IBCF = list(name = "IBCF", param=NULL), AR = list(name = "AR", param=NULL) ) evlist <- evaluate(es, algorithms) plot(evlist, legend="topright") ## select the first results evlist[[1]]