# nolint start
library(mlexperiments)
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.
# nolint start
library(mlexperiments)
See https://github.com/kapsner/mlexperiments/blob/main/R/learner_rpart.R for implementation details.
library(mlbench)
data("DNA")
<- DNA |>
dataset ::as.data.table() |>
data.tablena.omit()
<- colnames(dataset)[1:180]
feature_cols <- "Class" target_col
<- 123
seed if (isTRUE(as.logical(Sys.getenv("_R_CHECK_LIMIT_CORES_")))) {
# on cran
<- 2L
ncores else {
} <- ifelse(
ncores test = parallel::detectCores() > 4,
yes = 4L,
no = ifelse(
test = parallel::detectCores() < 2L,
yes = 1L,
no = parallel::detectCores()
)
)
}options("mlexperiments.bayesian.max_init" = 10L)
<- splitTools::partition(
data_split y = dataset[, get(target_col)],
p = c(train = 0.7, test = 0.3),
type = "stratified",
seed = seed
)
<- model.matrix(
train_x ~ -1 + .,
$train, .SD, .SDcols = feature_cols]
dataset[data_split
)<- dataset[data_split$train, get(target_col)]
train_y
<- model.matrix(
test_x ~ -1 + .,
$test, .SD, .SDcols = feature_cols]
dataset[data_split
)<- dataset[data_split$test, get(target_col)] test_y
<- splitTools::create_folds(
fold_list y = train_y,
k = 3,
type = "stratified",
seed = seed
)
# required learner arguments, not optimized
<- list(method = "class")
learner_args
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
<- list(type = "class")
predict_args <- metric("bacc")
performance_metric <- NULL
performance_metric_args <- FALSE
return_models
# required for grid search and initialization of bayesian optimization
<- expand.grid(
parameter_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(seq_len(nrow(parameter_grid)), 10, FALSE)
sample_rows <- kdry::mlh_subset(parameter_grid, sample_rows)
parameter_grid
}
# required for bayesian optimization
<- list(
parameter_bounds minsplit = c(2L, 100L),
cp = c(0.01, 0.1),
maxdepth = c(2L, 30L)
)<- list(
optim_args iters.n = ncores,
kappa = 3.5,
acq = "ucb"
)
<- mlexperiments::MLTuneParameters$new(
tuner learner = LearnerRpart$new(),
strategy = "grid",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$learner_args <- learner_args
tuner$split_type <- "stratified"
tuner
$set_data(
tunerx = train_x,
y = train_y
)
<- tuner$execute(k = 3)
tuner_results_grid #>
#> 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
<- mlexperiments::MLTuneParameters$new(
tuner learner = LearnerRpart$new(),
strategy = "bayesian",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$parameter_bounds <- parameter_bounds
tuner
$learner_args <- learner_args
tuner$optim_args <- optim_args
tuner
$split_type <- "stratified"
tuner
$set_data(
tunerx = train_x,
y = train_y
)
<- tuner$execute(k = 3)
tuner_results_bayesian #>
#> 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
<- mlexperiments::MLCrossValidation$new(
validator learner = LearnerRpart$new(),
fold_list = fold_list,
ncores = ncores,
seed = seed
)
$learner_args <- tuner$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
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> 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
<- mlexperiments::MLNestedCV$new(
validator learner = LearnerRpart$new(),
strategy = "grid",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
validator$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
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> 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
<- mlexperiments::MLNestedCV$new(
validator learner = LearnerRpart$new(),
strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
validator$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
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> 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
Here, rpart
’s weights
-argument is used to rescale the case-weights during the training.
# define the target weights
<- ifelse(train_y == "n", 0.8, ifelse(train_y == "ei", 1.2, 1))
y_weights head(y_weights)
#> [1] 1.2 1.2 0.0 0.8 0.8 0.0
<- mlexperiments::MLTuneParameters$new(
tuner_w_weights learner = LearnerRpart$new(),
strategy = "grid",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner_w_weights$learner_args <- c(
tuner_w_weights
learner_args,list(case_weights = y_weights)
)$split_type <- "stratified"
tuner_w_weights
$set_data(
tuner_w_weightsx = train_x,
y = train_y
)
<- tuner_w_weights$execute(k = 3)
tuner_results_grid #>
#> 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
#> <int> <num> <int> <num> <int> <char>
#> 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
<- mlexperiments::MLCrossValidation$new(
validator learner = LearnerRpart$new(),
fold_list = fold_list,
ncores = ncores,
seed = seed
)
# append the optimized setting from above with the newly created weights
$learner_args <- c(
validator$results$best.setting[-1],
tunerlist("case_weights" = y_weights)
)
$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$execute()
validator_results #>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#>
#> CV fold: Fold3
#> CV progress [========================================================================================================] 3/3 (100%)
#>
head(validator_results)
#> fold performance minsplit cp maxdepth method
#> <char> <num> <num> <num> <num> <char>
#> 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
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.