mlexperiments (version 0.0.5)

validate_fold_equality: validate_fold_equality

Description

Validate that the same folds were used in two or more independent experiments.

Usage

validate_fold_equality(experiments)

Value

Writes messages to the console on the result of the comparison.

Arguments

experiments

A list of experiments.

Details

This function can be applied to all implemented experiments, i.e., MLTuneParameters, MLCrossValidation, and MLNestedCV. However, it is required that the list experiments contains only experiments of the same class.

Examples

dataset <- do.call(
  cbind,
  c(sapply(paste0("col", 1:6), function(x) {
    rnorm(n = 500)
    },
    USE.NAMES = TRUE,
    simplify = FALSE
   ),
   list(target = sample(0:1, 500, TRUE))
))

fold_list <- splitTools::create_folds(
  y = dataset[, 7],
  k = 3,
  type = "stratified",
  seed = 123
)

# GLM
glm_optimization <- mlexperiments::MLCrossValidation$new(
  learner = LearnerGlm$new(),
  fold_list = fold_list,
  seed = 123
)

glm_optimization$learner_args <- list(family = binomial(link = "logit"))
glm_optimization$predict_args <- list(type = "response")
glm_optimization$performance_metric_args <- list(positive = "1")
glm_optimization$performance_metric <- metric("auc")
glm_optimization$return_models <- TRUE

# set data
glm_optimization$set_data(
  x = data.matrix(dataset[, -7]),
  y = dataset[, 7]
)

glm_cv_results <- glm_optimization$execute()

# KNN
knn_optimization <- mlexperiments::MLCrossValidation$new(
  learner = LearnerKnn$new(),
  fold_list = fold_list,
  seed = 123
)
knn_optimization$learner_args <- list(
  k = 3,
  l = 0,
  test = parse(text = "fold_test$x")
)
knn_optimization$predict_args <- list(type = "prob")
knn_optimization$performance_metric_args <- list(positive = "1")
knn_optimization$performance_metric <- metric("auc")

# set data
knn_optimization$set_data(
  x = data.matrix(dataset[, -7]),
  y = dataset[, 7]
)

cv_results_knn <- knn_optimization$execute()

# validate folds
validate_fold_equality(
  list(glm_optimization, knn_optimization)
)