From bebaa34e7cd295932cfe1cba58b27e259a70402b Mon Sep 17 00:00:00 2001
From: Kyle Belanger <kyleb44@hotmail.com>
Date: Wed, 7 Jun 2023 14:08:53 -0400
Subject: [PATCH] update

---
 ML/2-modeling.R | 24 ++++++++++++++++++++++++
 chapter4.qmd    | 16 +++++++++++++++-
 2 files changed, 39 insertions(+), 1 deletion(-)

diff --git a/ML/2-modeling.R b/ML/2-modeling.R
index 1d6b52c..b48e024 100644
--- a/ML/2-modeling.R
+++ b/ML/2-modeling.R
@@ -335,6 +335,30 @@ reg_test_results <-
   final_rf_reg_fit %>%
   tune::last_fit(split = model_data_split)
 
+
+reg_metrics(reg_test_results %>% tune::collect_predictions(), truth = FT4, estimate = .pred)
+
+final_reg_result_pred <- reg_test_results %>% tune::collect_predictions()
+
+ggplot(reg_test_results %>% tune::collect_predictions(), aes(x = FT4, y = .pred)) +
+  gp2$geom_abline(lty = 2) +
+  gp2$geom_point(alpha = 0.5) +
+  tune::coord_obs_pred()
+
+gp2$ggsave(
+  here("figures","reggression_pred.emf")
+  ,width  = 7
+  ,height = 7
+  ,dpi    = 300
+  ,device = devEMF::emf
+)
+gp2$ggsave(
+  here("figures","reggression_pred.png")
+  ,width  = 7
+  ,height = 7
+  ,dpi    = 300
+)
+
 ds_reg_class_pred <- reg_test_results %>%
   tune::collect_predictions() %>%
   dplyr::select(-id, -.config) %>%
diff --git a/chapter4.qmd b/chapter4.qmd
index 1c03466..9a663aa 100644
--- a/chapter4.qmd
+++ b/chapter4.qmd
@@ -68,8 +68,22 @@ the extent to which a feature has a \"meaningful\" impact on the
 predicted outcome [@laan2006]. As expected, TSH is the leading variable
 in importance rankings, leading all other variables by over 2000's
 points. The following three variables are all parts of a Complete Blood
-Count (CBC), followed by the patients glucose value.
+Count (CBC), followed by the patient's glucose value.
 
 ![Variable Importance Plot](figures/vip_class){#fig-vip-class}
 
 ## Predictability of Free T4 Results (Regression) 
+
+Today, it has become widely accepted that a more sound approach to
+assessing model performance is to assess the predictive accuracy via
+loss functions. Loss functions are metrics that compare the predicted
+values to the actual value (the output of a loss function is often
+referred to as the error or pseudo residual) [@boehmke2020]. The loss
+function used to evaluate the final model was selected as the Root Mean
+Square Error, and the final testing data achieved an RMSE of 0.334.
+@fig-reg-pred shows the plotted results. The predicted results were also
+used to add the diagnostic classification of Free T4. These results
+achieved an accuracy of 0.790, and thus very similar to the
+classification model.
+
+![Regression Predictions Plot](figures/reggression_pred){#fig-reg-pred}