I am using an already written R code which has a line of code as shown below

model_predictors <- buildModel(flag, data, outcomeName, folder)
auc <- model_predictors$auc
save(model, file=paste(folder,studyName,'_model_', flag$model[1], '_', outcomeName,".Rda",sep=''))

As you can see in the last line of code, the (training) model is saved in folder in a .Rda file format with a naming convention _model_. Now, I have to use this model to test/evaluate on unseen dataset.

So now my question, I see a .Rda file in my folder path and I can load the .Rda file in Rstudio but how do I make inference from this model? I am new to R and can anyone help me with this please?

Can someone help me understand how to run this model please?


I suppose you come from Python. R is quite different as it does not require to save to external files your model, you just need to have it in your workspace. Once you have a model object, you just have to use the predict function and specify the unseen dataset. Here's an example of a tree model:

model<-tree(Y~X1+X2, data=dataset) #estimate of the tree model
predictions<-predict(model, newdata=unseen_dataset) #prediction on new data

Be sure variable names between datasets correspond.

  • $\begingroup$ Thanks for the response. Upvoted and marked $\endgroup$ – The Great May 12 '20 at 16:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.