prediction - How to predict on a new dataset using caretEnsemble package in R? -

i using caretensemble package in r combining multiple models trained in caret. have got list of final trained models (say model_list) using caretlist function same package follows.

    model_list <- caretlist(     x = input_predictors,      y = input_labels,      metric = 'accuracy',     tunelist = list(         randomforestmodel =   caretmodelspec(method='rf',                                               tunelength=1,                                               preprocess=c('boxcox', 'center', 'scale')),          ldamodel = caretmodelspec(method='lda',                                    tunelength=1,                                    preprocess=c('boxcox', 'center', 'scale')),         logisticregressionmodel =  caretmodelspec(method='glm',                                                    tunelength=1,                                                    preprocess=c('boxcox', 'center', 'scale'))     ),      trcontrol = mytraincontrol ) 

the train control object provided follows :

    mytraincontrol = traincontrol(method = "cv",                                number = 10,                                index=createresample(training_input_data$retinopathy, 10),                               savepredictions = true,                                classprobs = true,                                verboseiter = true,                                summaryfunction = twoclasssummary) 

now training on list of models :

ens <- caretensemble(model_list) 

applying summary on ens tells me selected models (out of model_list), weightage allocated selected models, out-of-sample auc values each of selected models, , in-sample auc values ens.

now want compute performance of ens on other test-data (to idea out-of-sample performance). how achieve it?

i trying out :

enspredictions <- predict(ens, newdata = test_data) 

but it's giving me error :

error in `[.data.frame`(out, , obslevels, drop = false) :    undefined columns selected