Generate predictions, uncertainty estimates, and SHAP values for new data. Models that were skipped during training are returned unchanged.
Usage
make_new_data_predictions(model, name, indx, total, new_data)
Arguments
- model
The model object.
- name
The name of the perturbation.
- indx
Integer index used, for progress report.
- total
Integer of the total number of perturbations passed to this function, for progress report.
- new_data
A dataframe of new cases with predictors as columns. Sample names are row names.
Value
The input model object with prediction outputs added under new_data,
including predictions, uncertainty estimates, target-event probabilities,
row-wise compressed SHAP values, and feature-contribution summaries. Models
skipped during training are returned unchanged.
Examples
if (FALSE) { # \dontrun{
make_new_data_predictions(my_model, "ko_ctnnb1", 1, 1, my_new_data)
} # }
