## ----setup-------------------------------------------------------------------- # nolint start library(mlexperiments) ## ----------------------------------------------------------------------------- library(mlbench) data("DNA") dataset <- DNA |> data.table::as.data.table() |> na.omit() feature_cols <- colnames(dataset)[1:180] target_col <- "Class" ## ----------------------------------------------------------------------------- seed <- 123 if (isTRUE(as.logical(Sys.getenv("_R_CHECK_LIMIT_CORES_")))) { # on cran ncores <- 2L } else { ncores <- ifelse( test = parallel::detectCores() > 4, yes = 4L, no = ifelse( test = parallel::detectCores() < 2L, yes = 1L, no = parallel::detectCores() ) ) } options("mlexperiments.bayesian.max_init" = 10L) ## ----------------------------------------------------------------------------- data_split <- splitTools::partition( y = dataset[, get(target_col)], p = c(train = 0.7, test = 0.3), type = "stratified", seed = seed ) train_x <- model.matrix( ~ -1 + ., dataset[data_split$train, .SD, .SDcols = feature_cols] ) train_y <- dataset[data_split$train, get(target_col)] test_x <- model.matrix( ~ -1 + ., dataset[data_split$test, .SD, .SDcols = feature_cols] ) test_y <- dataset[data_split$test, get(target_col)] ## ----------------------------------------------------------------------------- fold_list <- splitTools::create_folds( y = train_y, k = 3, type = "stratified", seed = seed ) ## ----------------------------------------------------------------------------- # required learner arguments, not optimized learner_args <- list(method = "class") # set arguments for predict function and performance metric, # required for mlexperiments::MLCrossValidation and # mlexperiments::MLNestedCV predict_args <- list(type = "class") performance_metric <- metric("bacc") performance_metric_args <- NULL return_models <- FALSE # required for grid search and initialization of bayesian optimization parameter_grid <- expand.grid( minsplit = seq(2L, 82L, 10L), cp = seq(0.01, 0.1, 0.01), maxdepth = seq(2L, 30L, 5L) ) # reduce to a maximum of 10 rows if (nrow(parameter_grid) > 10) { set.seed(123) sample_rows <- sample(seq_len(nrow(parameter_grid)), 10, FALSE) parameter_grid <- kdry::mlh_subset(parameter_grid, sample_rows) } # required for bayesian optimization parameter_bounds <- list( minsplit = c(2L, 100L), cp = c(0.01, 0.1), maxdepth = c(2L, 30L) ) optim_args <- list( iters.n = ncores, kappa = 3.5, acq = "ucb" ) ## ----------------------------------------------------------------------------- tuner <- mlexperiments::MLTuneParameters$new( learner = LearnerRpart$new(), strategy = "grid", ncores = ncores, seed = seed ) tuner$parameter_grid <- parameter_grid tuner$learner_args <- learner_args tuner$split_type <- "stratified" tuner$set_data( x = train_x, y = train_y ) tuner_results_grid <- tuner$execute(k = 3) #> #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================================================================>-------------------] 8/10 ( 80%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================================================================>----------] 9/10 ( 90%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================================================================] 10/10 (100%) #> Classification: using 'classification error rate' as optimization metric. head(tuner_results_grid) #> setting_id metric_optim_mean minsplit cp maxdepth method #> 1: 1 0.09465558 2 0.07 22 class #> 2: 2 0.09465558 32 0.02 27 class #> 3: 3 0.09465558 72 0.10 7 class #> 4: 4 0.09465558 32 0.09 27 class #> 5: 5 0.09465558 52 0.02 12 class #> 6: 6 0.09465558 2 0.04 7 class ## ----------------------------------------------------------------------------- tuner <- mlexperiments::MLTuneParameters$new( learner = LearnerRpart$new(), strategy = "bayesian", ncores = ncores, seed = seed ) tuner$parameter_grid <- parameter_grid tuner$parameter_bounds <- parameter_bounds tuner$learner_args <- learner_args tuner$optim_args <- optim_args tuner$split_type <- "stratified" tuner$set_data( x = train_x, y = train_y ) tuner_results_bayesian <- tuner$execute(k = 3) #> #> Registering parallel backend using 4 cores. head(tuner_results_bayesian) #> Epoch setting_id minsplit cp maxdepth gpUtility acqOptimum inBounds Elapsed Score metric_optim_mean errorMessage method #> 1: 0 1 2 0.07 22 NA FALSE TRUE 2.108 -0.09465558 0.09465558 NA class #> 2: 0 2 32 0.02 27 NA FALSE TRUE 2.122 -0.09465558 0.09465558 NA class #> 3: 0 3 72 0.10 7 NA FALSE TRUE 2.025 -0.09465558 0.09465558 NA class #> 4: 0 4 32 0.09 27 NA FALSE TRUE 2.258 -0.09465558 0.09465558 NA class #> 5: 0 5 52 0.02 12 NA FALSE TRUE 2.030 -0.09465558 0.09465558 NA class #> 6: 0 6 2 0.04 7 NA FALSE TRUE 2.099 -0.09465558 0.09465558 NA class ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLCrossValidation$new( learner = LearnerRpart$new(), fold_list = fold_list, ncores = ncores, seed = seed ) validator$learner_args <- tuner$results$best.setting[-1] validator$predict_args <- predict_args validator$performance_metric <- performance_metric validator$performance_metric_args <- performance_metric_args validator$return_models <- return_models validator$set_data( x = train_x, y = train_y ) validator_results <- validator$execute() #> #> CV fold: Fold1 #> #> CV fold: Fold2 #> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%) #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> head(validator_results) #> fold performance minsplit cp maxdepth method #> 1: Fold1 0.8950174 2 0.07 22 class #> 2: Fold2 0.8978974 2 0.07 22 class #> 3: Fold3 0.8917513 2 0.07 22 class ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLNestedCV$new( learner = LearnerRpart$new(), strategy = "grid", fold_list = fold_list, k_tuning = 3L, ncores = ncores, seed = seed ) validator$parameter_grid <- parameter_grid validator$learner_args <- learner_args validator$split_type <- "stratified" validator$predict_args <- predict_args validator$performance_metric <- performance_metric validator$performance_metric_args <- performance_metric_args validator$return_models <- return_models validator$set_data( x = train_x, y = train_y ) validator_results <- validator$execute() #> #> CV fold: Fold1 #> #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================================================================>-------------------] 8/10 ( 80%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================================================================>----------] 9/10 ( 90%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================================================================] 10/10 (100%) #> Classification: using 'classification error rate' as optimization metric. #> #> CV fold: Fold2 #> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%) #> #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================================================================>-------------------] 8/10 ( 80%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================================================================>----------] 9/10 ( 90%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================================================================] 10/10 (100%) #> Classification: using 'classification error rate' as optimization metric. #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================>-----------------------------------------------------------------------------] 2/10 ( 20%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [============================================================================>-------------------] 8/10 ( 80%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [=====================================================================================>----------] 9/10 ( 90%) #> Classification: using 'classification error rate' as optimization metric. #> #> Parameter settings [===============================================================================================] 10/10 (100%) #> Classification: using 'classification error rate' as optimization metric. head(validator_results) #> fold performance minsplit cp maxdepth method #> 1: Fold1 0.8950174 2 0.07 22 class #> 2: Fold2 0.8978974 2 0.07 22 class #> 3: Fold3 0.8917513 2 0.07 22 class ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLNestedCV$new( learner = LearnerRpart$new(), strategy = "bayesian", fold_list = fold_list, k_tuning = 3L, ncores = ncores, seed = seed ) validator$parameter_grid <- parameter_grid validator$learner_args <- learner_args validator$split_type <- "stratified" validator$parameter_bounds <- parameter_bounds validator$optim_args <- optim_args validator$predict_args <- predict_args validator$performance_metric <- performance_metric validator$performance_metric_args <- performance_metric_args validator$return_models <- return_models validator$set_data( x = train_x, y = train_y ) validator_results <- validator$execute() #> #> CV fold: Fold1 #> #> Registering parallel backend using 4 cores. #> #> CV fold: Fold2 #> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%) #> #> Registering parallel backend using 4 cores. #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> #> Registering parallel backend using 4 cores. head(validator_results) #> fold performance minsplit cp maxdepth method #> 1: Fold1 0.8950174 2 0.07 22 class #> 2: Fold2 0.8978974 2 0.07 22 class #> 3: Fold3 0.8917513 2 0.07 22 class ## ----------------------------------------------------------------------------- # define the target weights y_weights <- ifelse(train_y == "n", 0.8, ifelse(train_y == "ei", 1.2, 1)) head(y_weights) #> [1] 1.2 1.2 0.0 0.8 0.8 0.0 ## ----------------------------------------------------------------------------- tuner_w_weights <- mlexperiments::MLTuneParameters$new( learner = LearnerRpart$new(), strategy = "grid", ncores = ncores, seed = seed ) tuner_w_weights$parameter_grid <- parameter_grid tuner_w_weights$learner_args <- c( learner_args, list(case_weights = y_weights) ) tuner_w_weights$split_type <- "stratified" tuner_w_weights$set_data( x = train_x, y = train_y ) tuner_results_grid <- tuner_w_weights$execute(k = 3) #> #> Parameter settings [============================>-------------------------------------------------------------------] 3/10 ( 30%) #> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%) #> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%) #> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%) #> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%) #> Parameter settings [============================================================================>-------------------] 8/10 ( 80%) #> Parameter settings [=====================================================================================>----------] 9/10 ( 90%) #> Parameter settings [===============================================================================================] 10/10 (100%) head(tuner_results_grid) #> setting_id metric_optim_mean minsplit cp maxdepth method #> #> 1: 1 0.1062916 2 0.07 22 class #> 2: 2 0.1062916 32 0.02 27 class #> 3: 3 0.1062916 72 0.10 7 class #> 4: 4 0.1062916 32 0.09 27 class #> 5: 5 0.1062916 52 0.02 12 class #> 6: 6 0.1062916 2 0.04 7 class ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLCrossValidation$new( learner = LearnerRpart$new(), fold_list = fold_list, ncores = ncores, seed = seed ) # append the optimized setting from above with the newly created weights validator$learner_args <- c( tuner$results$best.setting[-1], list("case_weights" = y_weights) ) validator$predict_args <- predict_args validator$performance_metric <- performance_metric validator$performance_metric_args <- performance_metric_args validator$return_models <- return_models validator$set_data( x = train_x, y = train_y ) validator_results <- validator$execute() #> #> CV fold: Fold1 #> #> CV fold: Fold2 #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> head(validator_results) #> fold performance minsplit cp maxdepth method #> #> 1: Fold1 0.8812005 2 0.07 22 class #> 2: Fold2 0.9129256 2 0.07 22 class #> 3: Fold3 0.8800668 2 0.07 22 class ## ----include=FALSE------------------------------------------------------------ # nolint end