Groupwork2

## Loading required package: ggplot2

## Loading required package: lattice

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ lubridate 1.9.2     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ✖ purrr::lift()   masks caret::lift()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## 
## Attaching package: 'xgboost'
## 
## 
## The following object is masked from 'package:dplyr':
## 
##     slice
## 
## 
## randomForest 4.7-1.1
## 
## Type rfNews() to see new features/changes/bug fixes.
## 
## 
## Attaching package: 'randomForest'
## 
## 
## The following object is masked from 'package:dplyr':
## 
##     combine
## 
## 
## The following object is masked from 'package:ggplot2':
## 
##     margin
## 
## 
## Loading required package: Matrix
## 
## 
## Attaching package: 'Matrix'
## 
## 
## The following objects are masked from 'package:tidyr':
## 
##     expand, pack, unpack
## 
## 
## Loaded glmnet 4.1-8
## 
## 
## Attaching package: 'ranger'
## 
## 
## The following object is masked from 'package:randomForest':
## 
##     importance

Grid Search

This is the grid we will search over. The values were chosen after careful consideration

learning_rates <- c(0.01, 0.1, 0.3, 0.5)
max_depth <- seq(4, 12)
gamma <- c(0.0, 0.5, 1.0, 0.3)

set.seed(5003)
models = c("gabexgb")


missing_value_methods = c(missing_value_none)


balance_methods = c(balance_method_1)


feature_selection_method = no_feature_selection


data_use <- data %>% select(-X, -SaO2, -heart_rhythm)  %>% one_hot_encode_all_caret()


results = list()

for (model in models)
  for (balance_method in balance_methods)
    for (missing_value_method in missing_value_methods){
      result <- evaluate_model(data_use, model_type = model, missing_method = missing_value_method, 
                           feature_selection_method = no_feature_selection, 
                           balance_method = balance_method)
      results = append(results, result)
}

results$best_params

## [[1]]
## [1] "objective : binary:logistic | metric : error | learning_rate : 0.5 | max_depth : 12 | gamma : 0.3"