I want to get predictions for the entire training data after using tune_grid() with 10-fold cross-validation to tune my model. Collect-predictions() only gives me the predictions for each fold. If I use finalize_workflow and then final_fit, collect_predictions() gives me the predictions on the test data (as it should). What is the most "tidymodels-way" of getting predictions for the whole training dataset after tuning?
What do you want to use those predictions for? I don't think there is a specific "tidymodels way", so I would use
predict() with the final fitted model (or workflow) and the training data as
This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.
If you have a query related to it or one of the replies, start a new topic and refer back with a link.