zachmayer / caretEnsemble

caret models all the way down :turtle:
Other
226 stars 75 forks source link

weights of the models #243

Open seymakalay opened 6 years ago

seymakalay commented 6 years ago

Hi, I am having hard time to interpret the weights of glm and rpart, what are the models' weights for glm and rpart? many thanks in advance,,,

greedy_ensemble <- caretEnsemble( model_list, metric="ROC", trControl=trainControl( number=2, summaryFunction=twoClassSummary, classProbs=TRUE )) summary(greedy_ensemble) The following models were ensembled: glm, rpart They were weighted: 1.4489 -0.9559 -2.0442 The resulting ROC is: 0.7573 The fit for each individual model on the ROC is: method ROC ROCSD glm 0.6829333 0.05890797 rpart 0.7206765 0.06849524