mergeTuneParetoResults {TunePareto} | R Documentation |
Merges the results of multiple TuneParetoResult
objects as returned by tunePareto
, and recalculates the optimal solutions for the merged solution set. All supplied TuneParetoResult
objects must use the same objective functions.
mergeTuneParetoResults(...)
... |
A set of |
A TuneParetoResult
object containing the parameter configurations of all objects in the ...
argument and selecting the Pareto-optimal solutions among all these configurations. For more details on the object structure, refer to tunePareto
.
tunePareto
, recalculateParetoSet
# optimize an SVM with small costs on # the 'iris' data set r1 <- tunePareto(classifier = tunePareto.svm(), data = iris[, -ncol(iris)], labels = iris[, ncol(iris)], cost=seq(0.01,0.1,0.01), objectiveFunctions=list(cvWeightedError(10, 10), cvSensitivity(10, 10, caseClass="setosa"))) print(r1) # another call to tunePareto with higher costs r2 <- tunePareto(classifier = tunePareto.svm(), data = iris[, -ncol(iris)], labels = iris[, ncol(iris)], cost=seq(0.5,10,0.5), objectiveFunctions=list(cvWeightedError(10, 10), cvSensitivity(10, 10, caseClass="setosa"))) print(r2) # merge the results print(mergeTuneParetoResults(r1,r2))