TRIPOD reporting guidelines for prediction models ask you to describe details about the model specification in your paper:
15a Present the full prediction model to allow predictions for individuals (i.e., all regression coefficients, and model intercept or baseline survival at a given time point).
I have a basic understanding of the steps of model training, hyperparameter tuning, and validation in tidymodels, but I'm not clear on how to pull these details.
Using this keras neural net as an example, what's the best way to extract and present the full prediction model? What would you report, assuming this was your final model?
library(tidymodels) data(bivariate) biv_rec <- recipe(Class ~ ., data = bivariate_train) %>% step_BoxCox(all_predictors())%>% step_normalize(all_predictors()) %>% prep(training = bivariate_train, retain = TRUE) set.seed(57974) nnet_fit <- mlp(epochs = 100, hidden_units = 5, dropout = 0.1) %>% set_mode("classification") %>% set_engine("keras", verbose = 0) %>% fit(Class ~ ., data = juice(biv_rec))