## ----setup-------------------------------------------------------------------- # nolint start library(mlexperiments) library(mllrnrs) ## ----------------------------------------------------------------------------- library(mlbench) data("DNA") dataset <- DNA |> data.table::as.data.table() |> na.omit() feature_cols <- colnames(dataset)[160:180] 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(probability = TRUE, classification = TRUE) # set arguments for predict function and performance metric, # required for mlexperiments::MLCrossValidation and # mlexperiments::MLNestedCV predict_args <- list(reshape = TRUE) performance_metric <- metric("bacc") performance_metric_args <- NULL return_models <- FALSE # required for grid search and initialization of bayesian optimization parameter_grid <- expand.grid( num.trees = seq(500, 1000, 500), mtry = seq(2, 6, 2), min.node.size = seq(1, 9, 4), max.depth = seq(1, 9, 4), sample.fraction = seq(0.5, 0.8, 0.3) ) # 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( num.trees = c(100L, 1000L), mtry = c(2L, 9L), min.node.size = c(1L, 20L), max.depth = c(1L, 40L), sample.fraction = c(0.3, 1.) ) optim_args <- list( iters.n = ncores, kappa = 3.5, acq = "ucb" ) ## ----------------------------------------------------------------------------- tuner <- mlexperiments::MLTuneParameters$new( learner = mllrnrs::LearnerRanger$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 num.trees mtry min.node.size max.depth sample.fraction probability classification #> 1: 1 0.4786887 500 2 9 5 0.5 TRUE TRUE #> 2: 2 0.4791386 500 2 5 5 0.8 TRUE TRUE #> 3: 3 0.4419159 500 4 9 9 0.5 TRUE TRUE #> 4: 4 0.4809325 1000 2 9 1 0.5 TRUE TRUE #> 5: 5 0.4809325 500 2 9 1 0.8 TRUE TRUE #> 6: 6 0.4329589 1000 6 1 9 0.5 TRUE TRUE ## ----------------------------------------------------------------------------- tuner <- mlexperiments::MLTuneParameters$new( learner = mllrnrs::LearnerRanger$new(), strategy = "bayesian", ncores = ncores, seed = seed ) tuner$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 num.trees mtry min.node.size max.depth sample.fraction gpUtility acqOptimum inBounds Elapsed Score #> 1: 0 1 500 2 9 5 0.5 NA FALSE TRUE 1.597 -0.4791386 #> 2: 0 2 500 2 5 5 0.8 NA FALSE TRUE 1.641 -0.4786887 #> 3: 0 3 500 4 9 9 0.5 NA FALSE TRUE 2.161 -0.4392295 #> 4: 0 4 1000 2 9 1 0.5 NA FALSE TRUE 1.635 -0.4809325 #> 5: 0 5 500 2 9 1 0.8 NA FALSE TRUE 0.416 -0.4809325 #> 6: 0 6 1000 6 1 9 0.5 NA FALSE TRUE 3.373 -0.4378800 #> metric_optim_mean errorMessage probability classification #> 1: 0.4791386 NA TRUE TRUE #> 2: 0.4786887 NA TRUE TRUE #> 3: 0.4392295 NA TRUE TRUE #> 4: 0.4809325 NA TRUE TRUE #> 5: 0.4809325 NA TRUE TRUE #> 6: 0.4378800 NA TRUE TRUE ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLCrossValidation$new( learner = mllrnrs::LearnerRanger$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$execute() #> #> CV fold: Fold1 #> #> CV fold: Fold2 #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> head(validator_results) #> fold performance num.trees mtry min.node.size max.depth sample.fraction probability classification #> 1: Fold1 0.4206685 500 4 9 9 0.8 TRUE TRUE #> 2: Fold2 0.4011889 500 4 9 9 0.8 TRUE TRUE #> 3: Fold3 0.4252033 500 4 9 9 0.8 TRUE TRUE ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLNestedCV$new( learner = mllrnrs::LearnerRanger$new(), strategy = "grid", fold_list = fold_list, k_tuning = 3L, ncores = ncores, seed = seed ) validator$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. #> #> 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. #> #> 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. #> #> 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 num.trees mtry min.node.size max.depth sample.fraction probability classification #> 1: Fold1 0.4505456 1000 6 1 9 0.5 TRUE TRUE #> 2: Fold2 0.4162822 1000 6 1 9 0.5 TRUE TRUE #> 3: Fold3 0.4508978 1000 6 1 9 0.5 TRUE TRUE ## ----------------------------------------------------------------------------- validator <- mlexperiments::MLNestedCV$new( learner = mllrnrs::LearnerRanger$new(), strategy = "bayesian", fold_list = fold_list, k_tuning = 3L, ncores = ncores, seed = 312 ) 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$return_models <- TRUE validator$set_data( x = train_x, y = train_y ) validator_results <- validator$execute() #> #> CV fold: Fold1 #> #> Registering parallel backend using 4 cores. #> #> CV fold: Fold2 #> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%) #> #> Registering parallel backend using 4 cores. #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> #> Registering parallel backend using 4 cores. head(validator_results) #> fold performance num.trees mtry min.node.size max.depth sample.fraction probability classification #> 1: Fold1 0.4470914 1000 6 1 9 0.5000000 TRUE TRUE #> 2: Fold2 0.4419416 636 6 2 12 0.9378338 TRUE TRUE #> 3: Fold3 0.4737314 388 6 5 14 0.7457303 TRUE TRUE ## ----------------------------------------------------------------------------- preds_ranger <- mlexperiments::predictions( object = validator, newdata = test_x ) ## ----------------------------------------------------------------------------- perf_ranger <- mlexperiments::performance( object = validator, prediction_results = preds_ranger, y_ground_truth = test_y ) perf_ranger #> model performance #> 1: Fold1 0.4466305 #> 2: Fold2 0.4601201 #> 3: Fold3 0.4742046 ## ----------------------------------------------------------------------------- # define the target weights y_weights <- ifelse(train_y == "n", 0.8, ifelse(train_y == "ei", 1.2, 1)) head(y_weights) #> [1] 1.2 1.2 0.0 0.8 0.8 0.0 ## ----------------------------------------------------------------------------- tuner_w_weights <- mlexperiments::MLTuneParameters$new( learner = mllrnrs::LearnerRanger$new(), strategy = "grid", ncores = ncores, seed = seed ) tuner_w_weights$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 num.trees mtry min.node.size max.depth sample.fraction probability classification #> #> 1: 1 0.4665865 500 2 9 5 0.5 TRUE TRUE #> 2: 2 0.4656941 500 2 5 5 0.8 TRUE TRUE #> 3: 3 0.4486635 500 4 9 9 0.5 TRUE TRUE #> 4: 4 0.4809325 1000 2 9 1 0.5 TRUE TRUE #> 5: 5 0.4809325 500 2 9 1 0.8 TRUE TRUE #> 6: 6 0.4544915 1000 6 1 9 0.5 TRUE TRUE ## ----------------------------------------------------------------------------- validator_w_weights <- mlexperiments::MLCrossValidation$new( learner = mllrnrs::LearnerRanger$new(), fold_list = fold_list, ncores = ncores, seed = seed ) # append the optimized setting from above with the newly created weights validator_w_weights$learner_args <- c( tuner_w_weights$results$best.setting[-1] ) validator_w_weights$predict_args <- predict_args validator_w_weights$performance_metric <- performance_metric validator_w_weights$performance_metric_args <- performance_metric_args validator_w_weights$return_models <- return_models validator_w_weights$set_data( x = train_x, y = train_y ) validator_results <- validator_w_weights$execute() #> #> CV fold: Fold1 #> #> CV fold: Fold2 #> #> CV fold: Fold3 #> CV progress [========================================================================================================] 3/3 (100%) #> head(validator_results) #> fold performance num.trees mtry min.node.size max.depth sample.fraction probability classification #> #> 1: Fold1 0.4265252 500 2 5 9 0.5 TRUE TRUE #> 2: Fold2 0.4060490 500 2 5 9 0.5 TRUE TRUE #> 3: Fold3 0.4234232 500 2 5 9 0.5 TRUE TRUE ## ----include=FALSE------------------------------------------------------------ # nolint end