Abstract class used as a template to define new customized simple voting schemes.
new()Method for initializing the object arguments during runtime.
SimpleVoting$new(cutoff = NULL)cutoffA character vector defining the minimum probability used to perform a positive classification. If is not defined, 0.5 will be used as default value.
getCutoff()The function obtains the minimum probabilistic value used to perform a positive classification.
SimpleVoting$getCutoff()A numeric value.
getFinalPred()The function is used to return the prediction values computed by a voting strategy.
SimpleVoting$getFinalPred(type = NULL, target = NULL, filter = NULL)typeA character to define which type of predictions should be returned. If not defined all type of probabilities will be returned. Conversely if 'prob' or 'raw' is defined then computed 'probabilistic' or 'class' values are returned.
targetA character defining the value of the positive class.
filterA logical value used to specify if only predictions matching the target value should be returned or not. If TRUE the function returns only the predictions matching the target value. Conversely if FALSE (by default) the function returns all the predictions.
A FinalPred object.
execute()Abstract function used to implement the operation of the voting scheme.
SimpleVoting$execute(predictions, verbose = FALSE)predictionsA ClusterPredictions object containing
all the predictions achieved for each cluster.
verboseA logical value to specify if more verbosity is needed.
clone()The objects of this class are cloneable with this method.
SimpleVoting$clone(deep = FALSE)deepWhether to make a deep clone.
D2MCS, ClassMajorityVoting,
ClassWeightedVoting, ProbAverageVoting,
ProbAverageWeightedVoting, ProbBasedMethodology,
CombinedVoting