# nolint start
library(mlexperiments)
library(mllrnrs)
The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
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[@]metanet.ch.
# nolint start
library(mlexperiments)
library(mllrnrs)
See https://github.com/kapsner/mllrnrs/blob/main/R/learner_ranger.R for implementation details.
library(mlbench)
data("DNA")
<- DNA |>
dataset ::as.data.table() |>
data.tablena.omit()
<- colnames(dataset)[160:180]
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(probability = TRUE, classification = TRUE)
learner_args
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
<- list(reshape = TRUE)
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 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(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 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.)
)<- list(
optim_args iters.n = ncores,
kappa = 3.5,
acq = "ucb"
)
<- mlexperiments::MLTuneParameters$new(
tuner learner = mllrnrs::LearnerRanger$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 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
<- mlexperiments::MLTuneParameters$new(
tuner learner = mllrnrs::LearnerRanger$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 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
<- mlexperiments::MLCrossValidation$new(
validator learner = mllrnrs::LearnerRanger$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 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
<- mlexperiments::MLNestedCV$new(
validator learner = mllrnrs::LearnerRanger$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.
#>
#> 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
<- mlexperiments::MLNestedCV$new(
validator learner = mllrnrs::LearnerRanger$new(),
strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = 312
)
$parameter_grid <- parameter_grid
validator$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
$set_data(
validatorx = train_x,
y = train_y
)
<- validator$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 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
<- mlexperiments::predictions(
preds_ranger object = validator,
newdata = test_x
)
<- mlexperiments::performance(
perf_ranger 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
Here, ranger
’s case.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$new(
tuner_w_weights learner = mllrnrs::LearnerRanger$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 num.trees mtry min.node.size max.depth sample.fraction probability classification
#> <int> <num> <num> <num> <num> <num> <num> <lgcl> <lgcl>
#> 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
<- mlexperiments::MLCrossValidation$new(
validator learner = mllrnrs::LearnerRanger$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 num.trees mtry min.node.size max.depth sample.fraction probability classification
#> <char> <num> <num> <num> <num> <num> <num> <lgcl> <lgcl>
#> 1: Fold1 0.4565664 500 4 9 9 0.8 TRUE TRUE
#> 2: Fold2 0.4266609 500 4 9 9 0.8 TRUE TRUE
#> 3: Fold3 0.4576471 500 4 9 9 0.8 TRUE TRUE
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.