ranger: Binary Classification

# nolint start
library(mlexperiments)
library(mllrnrs)

See https://github.com/kapsner/mllrnrs/blob/main/R/learner_ranger.R for implementation details.

Preprocessing

Import and Prepare Data

library(mlbench)
data("PimaIndiansDiabetes2")
dataset <- PimaIndiansDiabetes2 |>
  data.table::as.data.table() |>
  na.omit()

feature_cols <- colnames(dataset)[1:8]
target_col <- "diabetes"

General Configurations

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)

Generate Training- and Test Data

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)]

Generate Training Data Folds

fold_list <- splitTools::create_folds(
  y = train_y,
  k = 3,
  type = "stratified",
  seed = seed
)

Experiments

Prepare Experiments

# required learner arguments, not optimized
learner_args <- list(probability = TRUE)

# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
predict_args <- list(prob = TRUE, positive = "pos")
performance_metric <- metric("auc")
performance_metric_args <- list(positive = "pos")
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"
)

Hyperparameter Tuning

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.
#> 
#>  Classification: using 'classification error rate' as optimization metric.
#> 
#>  Classification: using 'classification error rate' as optimization metric.
#> 
#>  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
#> 1:          1         0.1750403       500    2             9         5             0.5        TRUE
#> 2:          2         0.1712560       500    2             5         5             0.8        TRUE
#> 3:          3         0.1712560       500    4             9         9             0.5        TRUE
#> 4:          4         0.2335749      1000    2             9         1             0.5        TRUE
#> 5:          5         0.2479871       500    2             9         1             0.8        TRUE
#> 6:          6         0.1859098      1000    6             1         9             0.5        TRUE

Bayesian Optimization

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   1.005 -0.1749597
#> 2:     0          2       500    2             5         5             0.8        NA      FALSE     TRUE   1.008 -0.1748792
#> 3:     0          3       500    4             9         9             0.5        NA      FALSE     TRUE   0.995 -0.1786634
#> 4:     0          4      1000    2             9         1             0.5        NA      FALSE     TRUE   0.987 -0.2407407
#> 5:     0          5       500    2             9         1             0.8        NA      FALSE     TRUE   0.090 -0.2335749
#> 6:     0          6      1000    6             1         9             0.5        NA      FALSE     TRUE   0.332 -0.1785829
#>    metric_optim_mean errorMessage probability
#> 1:         0.1749597         <NA>        TRUE
#> 2:         0.1748792         <NA>        TRUE
#> 3:         0.1786634         <NA>        TRUE
#> 4:         0.2407407         <NA>        TRUE
#> 5:         0.2335749         <NA>        TRUE
#> 6:         0.1785829         <NA>        TRUE

k-Fold Cross Validation

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

head(validator_results)
#>     fold performance num.trees mtry min.node.size max.depth sample.fraction probability
#> 1: Fold1   0.8730830      1000    2             9         9             0.5        TRUE
#> 2: Fold2   0.8836594      1000    2             9         9             0.5        TRUE
#> 3: Fold3   0.8937253      1000    2             9         9             0.5        TRUE

Nested Cross Validation

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.
#> 
#>  Classification: using 'classification error rate' as optimization metric.
#> 
#>  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.
#> 
#>  Classification: using 'classification error rate' as optimization metric.
#> 
#>  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.
#> 
#>  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
#> 1: Fold1   0.8714966      1000    6             1         9             0.5        TRUE
#> 2: Fold2   0.8725542       500    4             9         9             0.8        TRUE
#> 3: Fold3   0.8886376       500    2             9         5             0.5        TRUE

Inner Bayesian Optimization

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
#> 1: Fold1   0.8754627      1000    6             1         9             0.5        TRUE
#> 2: Fold2   0.8767848       500    4             9         9             0.8        TRUE
#> 3: Fold3   0.8971170       500    2             5         9             0.5        TRUE

Holdout Test Dataset Performance

Predict Outcome in Holdout Test Dataset

preds_ranger <- mlexperiments::predictions(
  object = validator,
  newdata = test_x
)

Evaluate Performance on Holdout Test Dataset

perf_ranger <- mlexperiments::performance(
  object = validator,
  prediction_results = preds_ranger,
  y_ground_truth = test_y,
  type = "binary"
)
perf_ranger
#>    model performance       auc     prauc sensitivity specificity       ppv       npv tn tp fn fp       tnr       tpr       fnr
#> 1: Fold1   0.7874067 0.7874067 0.6119292   0.4615385   0.8481013 0.6000000 0.7613636 67 18 21 12 0.8481013 0.4615385 0.5384615
#> 2: Fold2   0.7802661 0.7802661 0.5977887   0.4615385   0.8860759 0.6666667 0.7692308 70 18 21  9 0.8860759 0.4615385 0.5384615
#> 3: Fold3   0.7831873 0.7831873 0.6174674   0.4615385   0.8354430 0.5806452 0.7586207 66 18 21 13 0.8354430 0.4615385 0.5384615
#>          fpr    bbrier       acc        ce     fbeta
#> 1: 0.1518987 0.1735079 0.7203390 0.2796610 0.5217391
#> 2: 0.1139241 0.1838647 0.7457627 0.2542373 0.5454545
#> 3: 0.1645570 0.1754549 0.7118644 0.2881356 0.5142857