## ----setup--------------------------------------------------------------------
# nolint start
library(mlexperiments)
library(mlsurvlrnrs)
## -----------------------------------------------------------------------------
dataset <- survival::colon |>
data.table::as.data.table() |>
na.omit()
dataset <- dataset[get("etype") == 2, ]
surv_cols <- c("status", "time", "rx")
feature_cols <- colnames(dataset)[3:(ncol(dataset) - 1)]
cat_vars <- c("sex", "obstruct", "perfor", "adhere", "differ", "extent",
"surg", "node4", "rx")
## -----------------------------------------------------------------------------
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)
## -----------------------------------------------------------------------------
split_vector <- splitTools::multi_strata(
df = dataset[, .SD, .SDcols = surv_cols],
strategy = "kmeans",
k = 4
)
data_split <- splitTools::partition(
y = split_vector,
p = c(train = 0.7, test = 0.3),
type = "stratified",
seed = seed
)
train_x <- data.matrix(
dataset[
data_split$train, .SD, .SDcols = setdiff(feature_cols, surv_cols[1:2])
]
)
train_y <- survival::Surv(
event = (dataset[data_split$train, get("status")] |>
as.character() |>
as.integer()),
time = dataset[data_split$train, get("time")],
type = "right"
)
split_vector_train <- splitTools::multi_strata(
df = dataset[data_split$train, .SD, .SDcols = surv_cols],
strategy = "kmeans",
k = 4
)
test_x <- data.matrix(
dataset[data_split$test, .SD, .SDcols = setdiff(feature_cols, surv_cols[1:2])]
)
test_y <- survival::Surv(
event = (dataset[data_split$test, get("status")] |>
as.character() |>
as.integer()),
time = dataset[data_split$test, get("time")],
type = "right"
)
## -----------------------------------------------------------------------------
fold_list <- splitTools::create_folds(
y = split_vector_train,
k = 3,
type = "stratified",
seed = seed
)
## -----------------------------------------------------------------------------
# required learner arguments, not optimized
learner_args <- NULL
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
predict_args <- NULL
performance_metric <- c_index
performance_metric_args <- NULL
return_models <- FALSE
# required for grid search and initialization of bayesian optimization
parameter_grid <- expand.grid(
num.trees = seq(500, 1000, 500),
mtry = seq(2, 6, 2),
min.node.size = seq(1, 9, 4),
max.depth = seq(1, 9, 4),
sample.fraction = seq(0.5, 0.8, 0.3)
)
# reduce to a maximum of 10 rows
if (nrow(parameter_grid) > 10) {
set.seed(123)
sample_rows <- sample(seq_len(nrow(parameter_grid)), 10, FALSE)
parameter_grid <- kdry::mlh_subset(parameter_grid, sample_rows)
}
# required for bayesian optimization
parameter_bounds <- list(
num.trees = c(100L, 1000L),
mtry = c(2L, 9L),
min.node.size = c(1L, 20L),
max.depth = c(1L, 40L),
sample.fraction = c(0.3, 1.)
)
optim_args <- list(
iters.n = ncores,
kappa = 3.5,
acq = "ucb"
)
## -----------------------------------------------------------------------------
tuner <- mlexperiments::MLTuneParameters$new(
learner = LearnerSurvRangerCox$new(),
strategy = "grid",
ncores = ncores,
seed = seed
)
tuner$parameter_grid <- parameter_grid
tuner$learner_args <- learner_args
tuner$split_type <- "stratified"
tuner$split_vector <- split_vector_train
tuner$set_data(
x = train_x,
y = train_y,
cat_vars = cat_vars
)
tuner_results_grid <- tuner$execute(k = 3)
#>
#> Parameter settings [===========================>---------------------------------------------------------------------------------------------------------------] 2/10 ( 20%)
#> 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
#> 1: 1 0.6720841 500 2 9 5 0.5
#> 2: 1 0.6720841 500 2 9 5 0.5
#> 3: 1 0.6720841 500 2 9 5 0.5
#> 4: 1 0.6720841 500 2 9 5 0.5
#> 5: 1 0.6720841 500 2 9 5 0.5
#> 6: 1 0.6720841 500 2 9 5 0.5
## -----------------------------------------------------------------------------
tuner <- mlexperiments::MLTuneParameters$new(
learner = LearnerSurvRangerCox$new(),
strategy = "bayesian",
ncores = ncores,
seed = seed
)
tuner$parameter_grid <- parameter_grid
tuner$parameter_bounds <- parameter_bounds
tuner$learner_args <- learner_args
tuner$optim_args <- optim_args
tuner$split_type <- "stratified"
tuner$split_vector <- split_vector_train
tuner$set_data(
x = train_x,
y = train_y,
cat_vars = cat_vars
)
tuner_results_bayesian <- tuner$execute(k = 3)
#>
#> Registering parallel backend using 4 cores.
head(tuner_results_bayesian)
#> Epoch setting_id num.trees mtry min.node.size max.depth sample.fraction gpUtility acqOptimum inBounds Elapsed Score metric_optim_mean errorMessage
#> 1: 0 1 500 2 9 5 0.5 NA FALSE TRUE 6.461 0.6693199 0.6693199 NA
#> 2: 0 2 500 2 5 5 0.8 NA FALSE TRUE 7.056 0.6688048 0.6688048 NA
#> 3: 0 3 500 4 9 9 0.5 NA FALSE TRUE 7.871 0.6661409 0.6661409 NA
#> 4: 0 4 1000 2 9 1 0.5 NA FALSE TRUE 11.942 0.6663512 0.6663512 NA
#> 5: 0 5 500 2 9 1 0.8 NA FALSE TRUE 5.117 0.6654894 0.6654894 NA
#> 6: 0 6 1000 6 1 9 0.5 NA FALSE TRUE 15.607 0.6621016 0.6621016 NA
## -----------------------------------------------------------------------------
validator <- mlexperiments::MLCrossValidation$new(
learner = LearnerSurvRangerCox$new(),
fold_list = fold_list,
ncores = ncores,
seed = seed
)
validator$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$set_data(
x = train_x,
y = train_y,
cat_vars = cat_vars
)
validator_results <- validator$execute()
#>
#> CV fold: Fold1
#>
#> CV fold: Fold2
#> CV progress [=================================================================================================>-------------------------------------------------] 2/3 ( 67%)
#>
#> CV fold: Fold3
#> CV progress [===================================================================================================================================================] 3/3 (100%)
#>
head(validator_results)
#> fold performance num.trees mtry min.node.size max.depth sample.fraction
#> 1: Fold1 0.6469363 1000 2 9 9 0.5
#> 2: Fold2 0.6949011 1000 2 9 9 0.5
#> 3: Fold3 0.6781061 1000 2 9 9 0.5
## -----------------------------------------------------------------------------
validator <- mlexperiments::MLNestedCV$new(
learner = LearnerSurvRangerCox$new(),
strategy = "grid",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
validator$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator$split_vector <- split_vector_train
validator$predict_args <- predict_args
validator$performance_metric <- performance_metric
validator$performance_metric_args <- performance_metric_args
validator$return_models <- return_models
validator$set_data(
x = train_x,
y = train_y,
cat_vars = cat_vars
)
validator_results <- validator$execute()
#>
#> CV fold: Fold1
#>
#> Parameter settings [===========================>---------------------------------------------------------------------------------------------------------------] 2/10 ( 20%)
#> 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: Fold2
#> CV progress [=================================================================================================>-------------------------------------------------] 2/3 ( 67%)
#>
#> Parameter settings [===========================>---------------------------------------------------------------------------------------------------------------] 2/10 ( 20%)
#> 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 [===========================>---------------------------------------------------------------------------------------------------------------] 2/10 ( 20%)
#> 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(validator_results)
#> fold performance num.trees mtry min.node.size max.depth sample.fraction
#> 1: Fold1 0.6455262 500 2 5 9 0.5
#> 2: Fold2 0.6949011 1000 2 9 9 0.5
#> 3: Fold3 0.6714574 500 2 9 5 0.5
## -----------------------------------------------------------------------------
validator <- mlexperiments::MLNestedCV$new(
learner = LearnerSurvRangerCox$new(),
strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = 312
)
validator$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator$split_vector <- split_vector_train
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$set_data(
x = train_x,
y = train_y,
cat_vars = cat_vars
)
validator_results <- validator$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 num.trees mtry min.node.size max.depth sample.fraction
#> 1: Fold1 0.6468081 1000 2 9 9 0.5000000
#> 2: Fold2 0.6940663 1000 2 9 9 0.5000000
#> 3: Fold3 0.6639019 796 2 1 2 0.8221974
## -----------------------------------------------------------------------------
preds_ranger <- mlexperiments::predictions(
object = validator,
newdata = test_x
)
## -----------------------------------------------------------------------------
perf_ranger <- mlexperiments::performance(
object = validator,
prediction_results = preds_ranger,
y_ground_truth = test_y
)
perf_ranger
#> model performance
#> 1: Fold1 0.6515910
#> 2: Fold2 0.6600127
#> 3: Fold3 0.6558614
## ----include=FALSE------------------------------------------------------------
# nolint end