0

Due to the size of my RAM, I decided to split my data into two and fit two different random forest models using the ranger r package. Is there a function in ranger that allows me to combine these two models into onefor prediction?

KEN
  • 55
  • 5

1 Answers1

0

Try using the stacks packages to create an ensemble model. Alternatively, do cross validation on with a sample of your data to train a number of models at a time and find the one that performs best on a holdout set. Check out parsnip from the tidymodels ecosystem.

thus__
  • 460
  • 3
  • 16
  • My models are trained on different sets of data. From what I read about the stacks packages, the models have to be trained on the same data. Please, correct me if I am wrong? – KEN Jan 25 '22 at 18:44