The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

glmnet: Binary 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("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$train, .SD, .SDcols = feature_cols]
)
train_y <- as.integer(dataset[data_split$train, get(target_col)]) - 1L


test_x <- model.matrix(
  ~ -1 + .,
  dataset[data_split$test, .SD, .SDcols = feature_cols]
)
test_y <- as.integer(dataset[data_split$test, get(target_col)]) - 1L

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 = "binomial",
  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")
performance_metric <- metric("auc")
performance_metric_args <- list(positive = "1")
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   0.934 -0.1751825         0.1751825 0.094027663           NA binomial
#> 2:     0          2  0.90        NA      FALSE     TRUE   0.971 -0.1788321         0.1788321 0.080262968           NA binomial
#> 3:     0          3  0.65        NA      FALSE     TRUE   0.948 -0.1788321         0.1788321 0.101260561           NA binomial
#> 4:     0          4  0.10        NA      FALSE     TRUE   0.931 -0.1751825         0.1751825 0.006282777           NA binomial
#> 5:     0          5  0.45        NA      FALSE     TRUE   0.027 -0.1751825         0.1751825 0.110644301           NA binomial
#> 6:     0          6  0.05        NA      FALSE     TRUE   0.030 -0.1751825         0.1751825 0.006551691           NA binomial
#>    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   0.8773136 0.7568403 0.1047508 binomial        class        TRUE
#> 2: Fold2   0.8630354 0.7568403 0.1047508 binomial        class        TRUE
#> 3: Fold3   0.8304127 0.7568403 0.1047508 binomial        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   0.8773136   0.9 0.08390173 binomial        class        TRUE
#> 2: Fold2   0.8767848   0.1 0.15109601 binomial        class        TRUE
#> 3: Fold3   0.8507631   0.5 0.11271736 binomial        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,
  type = "binary"
)
perf_glmnet
#>    model performance       auc     prauc sensitivity specificity       ppv       npv tn tp fn fp       tnr       tpr       fnr
#> 1: Fold1   0.7656605 0.7656605 0.5841923   0.3333333   0.8860759 0.5909091 0.7291667 70 13 26  9 0.8860759 0.3333333 0.6666667
#> 2: Fold2   0.7831873 0.7831873 0.5822704   0.3846154   0.8860759 0.6250000 0.7446809 70 15 24  9 0.8860759 0.3846154 0.6153846
#> 3: Fold3   0.7627394 0.7627394 0.5747411   0.3589744   0.8607595 0.5600000 0.7311828 68 14 25 11 0.8607595 0.3589744 0.6410256
#>          fpr    bbrier       acc        ce     fbeta
#> 1: 0.1139241 0.1831706 0.7033898 0.2966102 0.4262295
#> 2: 0.1139241 0.1786208 0.7203390 0.2796610 0.4761905
#> 3: 0.1392405 0.1861673 0.6949153 0.3050847 0.4375000
#>

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.