Merge pull request #321 from SchlossLab/iss-262_roc

Plot ROC & PRC curves

NAMESPACE

@@ -4,6 +4,10 @@ export("!!")
 export("%>%")
 export(":=")
 export(.data)
+export(calc_baseline_precision)
+export(calc_mean_prc)
+export(calc_mean_roc)
+export(calc_model_sensspec)
 export(calc_perf_metrics)
 export(combine_hp_performance)
 export(compare_models)
@@ -22,6 +26,8 @@ export(get_tuning_grid)
 export(group_correlated_features)
 export(permute_p_value)
 export(plot_hp_performance)
+export(plot_mean_prc)
+export(plot_mean_roc)
 export(plot_model_performance)
 export(preprocess_data)
 export(randomize_feature_order)

NEWS.md

@@ -1,8 +1,12 @@
 # mikropml development version
 
-- Created an example showing how to plot feature importances in the `parallel` vignette (#310, @kelly-sovacool).
+- New example showing how to plot feature importances in the `parallel` vignette (#310, @kelly-sovacool).
 - You can now use `parRF`, a parallel implementation of the `rf` method, with
   the same default hyperparameters as `rf` set automatically (#306, @kelly-sovacool).
+- New functions to calculate and plot ROC and PRC curves: (#321, @kelly-sovacool)
+  - `calc_model_sensspec()` - calculate sensitivity, specificity, and precision for a model.
+  - `calc_mean_roc()` & `plot_mean_roc()` - calculate & plot specificity and mean sensitivity for multiple models.
+  - `calc_mean_prc()` & `plot_mean_prc()` - calculate & plot recall and mean precision for multiple models.
 
 # mikropml 1.4.0
 

R/data.R

@@ -20,6 +20,11 @@
 #' All other columns are OTU relative abundances.
 "otu_mini_bin"
 
+#' Mini OTU abundance dataset - preprocessed
+#'
+#' This is the result of running `preprocess_data("otu_mini_bin")`
+"otu_data_preproc"
+
 #' Mini OTU abundance dataset with 3 categorical variables
 #'
 #' A dataset containing relatives abundances of OTUs for human stool samples