glmnet: Multiclass Classification

library(mlexperiments)
library(mllrnrs)

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

Preprocessing

Import and Prepare Data

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

feature_cols <- colnames(dataset)[160:180]
target_col <- "Class"

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(
  family = "multinomial",
  type.measure = "class",
  standardize = TRUE
)

# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
predict_args <- list(type = "response", 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(
  alpha = seq(0, 1, 0.05)
)
# 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(
  alpha = c(0., 1.)
)
optim_args <- list(
  iters.n = ncores,
  kappa = 3.5,
  acq = "ucb"
)

Hyperparameter Tuning

Bayesian Optimization

tuner <- mlexperiments::MLTuneParameters$new(
  learner = mllrnrs::LearnerGlmnet$new(
    metric_optimization_higher_better = FALSE
  ),
  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 alpha gpUtility acqOptimum inBounds Elapsed      Score metric_optim_mean      lambda errorMessage      family
#> 1:     0          1  0.70        NA      FALSE     TRUE   1.666 -0.4728578         0.4728578 0.003092562           NA multinomial
#> 2:     0          2  0.90        NA      FALSE     TRUE   1.635 -0.4737550         0.4737550 0.002639842           NA multinomial
#> 3:     0          3  0.65        NA      FALSE     TRUE   1.657 -0.4733064         0.4733064 0.003330451           NA multinomial
#> 4:     0          4  0.10        NA      FALSE     TRUE   1.744 -0.4733064         0.4733064 0.017972493           NA multinomial
#> 5:     0          5  0.45        NA      FALSE     TRUE   0.577 -0.4733064         0.4733064 0.003993887           NA multinomial
#> 6:     0          6  0.05        NA      FALSE     TRUE   0.687 -0.4728578         0.4728578 0.022574498           NA multinomial
#>    type.measure standardize
#> 1:        class        TRUE
#> 2:        class        TRUE
#> 3:        class        TRUE
#> 4:        class        TRUE
#> 5:        class        TRUE
#> 6:        class        TRUE

k-Fold Cross Validation

validator <- mlexperiments::MLCrossValidation$new(
  learner = mllrnrs::LearnerGlmnet$new(
    metric_optimization_higher_better = FALSE
  ),
  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 alpha      lambda      family type.measure standardize
#> 1: Fold1   0.3672581   0.7 0.003092562 multinomial        class        TRUE
#> 2: Fold2   0.3524351   0.7 0.003092562 multinomial        class        TRUE
#> 3: Fold3   0.3700659   0.7 0.003092562 multinomial        class        TRUE

Nested Cross Validation

Inner Bayesian Optimization

validator <- mlexperiments::MLNestedCV$new(
  learner = mllrnrs::LearnerGlmnet$new(
    metric_optimization_higher_better = FALSE
  ),
  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     alpha      lambda      family type.measure standardize
#> 1: Fold1   0.3652609 0.7000000 0.004817737 multinomial        class        TRUE
#> 2: Fold2   0.3416288 0.4178147 0.017108341 multinomial        class        TRUE
#> 3: Fold3   0.3467740 0.1000000 0.041963982 multinomial        class        TRUE

Holdout Test Dataset Performance

Predict Outcome in Holdout Test Dataset

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

Evaluate Performance on Holdout Test Dataset

perf_glmnet <- mlexperiments::performance(
  object = validator,
  prediction_results = preds_glmnet,
  y_ground_truth = test_y
)
perf_glmnet
#>    model performance
#> 1: Fold1   0.3606304
#> 2: Fold2   0.3603913
#> 3: Fold3   0.3529292