Example on how to do stratified sampling in Caret. This is useful for imbalanced datasets, and can be used to give more weight to a minority class

stratified_sampling.R

len_pos <- nrow(example_dataset[example_dataset$target==1,])
len_neg <- nrow(example_dataset[example_dataset$target==0,])

train_model <- function(training_data, labels, model_type, ...) {
  experiment_control <- trainControl(method="repeatedcv",
                                     number = 10,
                                     repeats = 2,
                                     classProbs = T,
                                     summaryFunction = custom_summary_function)
  train(x = training_data,
        y = labels,
        method = model_type,
        metric = "custom_score",
        trControl = experiment_control,
        verbose = F,
        ...)
}
 
# strata refers to which feature to do stratified sampling on.
# sampsize refers to the size of the bootstrap samples to be taken from each class. These samples will be taken as input
# for each tree. 
 
fit_results <- train_model(example_dataset
                           , as.factor(sprintf("c%d", as.numeric(example_dataset$target)))        
                           ,"rf"
                           ,tuneGrid = expand.grid(mtry = c( 3,5,10))
                           ,ntree=500
                           ,strata=as.factor(example_dataset$target)
                           ,sampsize = c('1'=as.integer(len_pos*0.25),'0'=as.integer(len_neg*0.8))
                     )