# nolint start
library(mlexperiments)
library(mllrnrs)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)
library(mllrnrs)See https://github.com/kapsner/mllrnrs/blob/main/R/learner_xgboost.R for implementation details.
library(mlbench)
data("BostonHousing")
dataset <- BostonHousing |>
data.table::as.data.table() |>
na.omit()
feature_cols <- colnames(dataset)[1:13]
target_col <- "medv"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" = 4L)
options("mlexperiments.optim.xgb.nrounds" = 20L)
options("mlexperiments.optim.xgb.early_stopping_rounds" = 5L)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$train, .SD, .SDcols = feature_cols]
)
train_y <- log(dataset[data_split$train, get(target_col)])
test_x <- model.matrix(
~ -1 + .,
dataset[data_split$test, .SD, .SDcols = feature_cols]
)
test_y <- log(dataset[data_split$test, get(target_col)])fold_list <- splitTools::create_folds(
y = train_y,
k = 3,
type = "stratified",
seed = seed
)# required learner arguments, not optimized
learner_args <- list(
objective = "reg:squarederror",
eval_metric = "rmse"
)
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
predict_args <- NULL
performance_metric <- metric("rmsle")
performance_metric_args <- NULL
return_models <- FALSE
# required for grid search and initialization of bayesian optimization
parameter_grid <- expand.grid(
subsample = seq(0.6, 1, .2),
colsample_bytree = seq(0.6, 1, .2),
min_child_weight = seq(1, 5, 4),
learning_rate = seq(0.1, 0.2, 0.1),
max_depth = seq(1, 5, 4)
)
# 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(
subsample = c(0.2, 1),
colsample_bytree = c(0.2, 1),
min_child_weight = c(1L, 10L),
learning_rate = c(0.1, 0.2),
max_depth = c(1L, 10L)
)
optim_args <- list(
n_iter = ncores,
kappa = 3.5,
acq = "ucb"
)tuner <- mlexperiments::MLTuneParameters$new(
learner = mllrnrs::LearnerXgboost$new(
metric_optimization_higher_better = FALSE
),
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$execute(k = 3)
#>
#> Parameter settings [=====================================>----------------------------------------------------------] 4/10 ( 40%)
#> Parameter settings [===============================================>------------------------------------------------] 5/10 ( 50%)
#> Parameter settings [=========================================================>--------------------------------------] 6/10 ( 60%)
#> Parameter settings [==================================================================>-----------------------------] 7/10 ( 70%)
#> Parameter settings [============================================================================>-------------------] 8/10 ( 80%)
#> Parameter settings [=====================================================================================>----------] 9/10 ( 90%)
#> Parameter settings [===============================================================================================] 10/10 (100%)
head(tuner_results_grid)
#> setting_id metric_optim_mean nrounds subsample colsample_bytree min_child_weight learning_rate max_depth objective
#> <int> <num> <int> <num> <num> <num> <num> <num> <char>
#> 1: 1 0.1872223 62 0.6 0.8 5 0.2 1 reg:squarederror
#> 2: 2 0.1688788 99 1.0 0.8 5 0.1 5 reg:squarederror
#> 3: 3 0.1916676 97 0.8 0.8 5 0.1 1 reg:squarederror
#> 4: 4 0.1662343 55 0.6 0.8 5 0.2 5 reg:squarederror
#> 5: 5 0.1635528 100 1.0 0.8 1 0.1 5 reg:squarederror
#> 6: 6 0.1641982 100 0.8 0.8 5 0.1 5 reg:squarederror
#> eval_metric
#> <char>
#> 1: rmse
#> 2: rmse
#> 3: rmse
#> 4: rmse
#> 5: rmse
#> 6: rmsetuner <- mlexperiments::MLTuneParameters$new(
learner = mllrnrs::LearnerXgboost$new(
metric_optimization_higher_better = FALSE
),
strategy = "bayesian",
ncores = ncores,
seed = seed
)
tuner$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 subsample colsample_bytree min_child_weight learning_rate max_depth gpUtility acqOptimum inBounds Elapsed
#> <num> <int> <num> <num> <num> <num> <num> <num> <lgcl> <lgcl> <num>
#> 1: 0 1 0.6 0.8 5 0.2 1 NA FALSE TRUE 0.915
#> 2: 0 2 1.0 0.8 5 0.1 5 NA FALSE TRUE 1.028
#> 3: 0 3 0.8 0.8 5 0.1 1 NA FALSE TRUE 0.935
#> 4: 0 4 0.6 0.8 5 0.2 5 NA FALSE TRUE 1.013
#> 5: 0 5 1.0 0.8 1 0.1 5 NA FALSE TRUE 0.248
#> 6: 0 6 0.8 0.8 5 0.1 5 NA FALSE TRUE 0.218
#> Score metric_optim_mean nrounds errorMessage objective eval_metric
#> <num> <num> <int> <lgcl> <char> <char>
#> 1: -0.1872223 0.1872223 62 NA reg:squarederror rmse
#> 2: -0.1688788 0.1688788 99 NA reg:squarederror rmse
#> 3: -0.1916676 0.1916676 97 NA reg:squarederror rmse
#> 4: -0.1662343 0.1662343 55 NA reg:squarederror rmse
#> 5: -0.1635528 0.1635528 100 NA reg:squarederror rmse
#> 6: -0.1641982 0.1641982 100 NA reg:squarederror rmsevalidator <- mlexperiments::MLCrossValidation$new(
learner = mllrnrs::LearnerXgboost$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$execute()
#>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#>
#> CV fold: Fold3
head(validator_results)
#> fold performance subsample colsample_bytree min_child_weight learning_rate max_depth nrounds objective eval_metric
#> <char> <num> <num> <num> <num> <num> <num> <int> <char> <char>
#> 1: Fold1 0.03396237 0.6 1 1 0.1 5 99 reg:squarederror rmse
#> 2: Fold2 0.05035231 0.6 1 1 0.1 5 99 reg:squarederror rmse
#> 3: Fold3 0.03987737 0.6 1 1 0.1 5 99 reg:squarederror rmsevalidator <- mlexperiments::MLNestedCV$new(
learner = mllrnrs::LearnerXgboost$new(
metric_optimization_higher_better = FALSE
),
strategy = "grid",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
validator$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
#>
#> 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%)
#> CV fold: Fold2
#> CV progress [====================================================================>-----------------------------------] 2/3 ( 67%)
#>
#> 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%)
#> CV fold: Fold3
#> CV progress [========================================================================================================] 3/3 (100%)
#>
#> 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(validator_results)
#> fold performance nrounds subsample colsample_bytree min_child_weight learning_rate max_depth objective eval_metric
#> <char> <num> <int> <num> <num> <num> <num> <num> <char> <char>
#> 1: Fold1 0.03942935 53 0.8 0.8 5 0.1 5 reg:squarederror rmse
#> 2: Fold2 0.05037283 100 0.6 1.0 1 0.1 5 reg:squarederror rmse
#> 3: Fold3 0.04125686 35 0.6 1.0 5 0.2 5 reg:squarederror rmsevalidator <- mlexperiments::MLNestedCV$new(
learner = mllrnrs::LearnerXgboost$new(
metric_optimization_higher_better = FALSE
),
strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
validator$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator$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 subsample colsample_bytree min_child_weight learning_rate max_depth nrounds objective eval_metric
#> <char> <num> <num> <num> <num> <num> <num> <int> <char> <char>
#> 1: Fold1 0.04712865 0.5029800 0.4977050 6 0.1195995 2 53 reg:squarederror rmse
#> 2: Fold2 0.05054316 0.4489853 0.7725962 2 0.2000000 5 65 reg:squarederror rmse
#> 3: Fold3 0.04027241 0.7465061 0.8234365 1 0.2000000 5 29 reg:squarederror rmsepreds_xgboost <- mlexperiments::predictions(
object = validator,
newdata = test_x
)perf_xgboost <- mlexperiments::performance(
object = validator,
prediction_results = preds_xgboost,
y_ground_truth = test_y,
type = "regression"
)
perf_xgboost
#> model performance SSE MSE RMSE MEDSE SAE MAE MEDAE RSQ EXPVAR RRSE
#> <char> <num> <num> <num> <num> <num> <num> <num> <num> <num> <num> <num>
#> 1: Fold1 0.04135927 4.102050 0.02646484 0.1626802 0.006572713 17.66284 0.1139538 0.08107227 0.8278688 0.8280100 0.4148870
#> 2: Fold2 0.04757084 4.799370 0.03096368 0.1759650 0.006181385 19.54728 0.1261115 0.07862178 0.7986077 0.9943971 0.4487675
#> 3: Fold3 0.03918577 3.567998 0.02301934 0.1517213 0.006275152 17.01818 0.1097947 0.07921586 0.8502788 0.8048249 0.3869382
#> RAE MAPE KendallTau SpearmanRho
#> <num> <num> <num> <num>
#> 1: 0.3847300 0.03826134 0.7533943 0.9036017
#> 2: 0.4257766 0.04426443 0.7628554 0.9148171
#> 3: 0.3706880 0.03763162 0.7815047 0.9278985These 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.