# nolint start
library(mlexperiments)
library(mlsurvlrnrs)
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(mlsurvlrnrs)
See https://github.com/kapsner/mlsurvlrnrs/blob/main/R/learner_surv_ranger_cox.R for implementation details.
<- survival::colon |>
dataset ::as.data.table() |>
data.tablena.omit()
<- dataset[get("etype") == 2, ]
dataset
<- c("status", "time", "rx")
surv_cols <- colnames(dataset)[3:(ncol(dataset) - 1)]
feature_cols <- c("sex", "obstruct", "perfor", "adhere", "differ", "extent",
cat_vars "surg", "node4", "rx")
<- 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::multi_strata(
split_vector df = dataset[, .SD, .SDcols = surv_cols],
strategy = "kmeans",
k = 4
)
<- splitTools::partition(
data_split y = split_vector,
p = c(train = 0.7, test = 0.3),
type = "stratified",
seed = seed
)
<- data.matrix(
train_x
dataset[$train, .SD, .SDcols = setdiff(feature_cols, surv_cols[1:2])
data_split
]
)<- survival::Surv(
train_y event = (dataset[data_split$train, get("status")] |>
as.character() |>
as.integer()),
time = dataset[data_split$train, get("time")],
type = "right"
)<- splitTools::multi_strata(
split_vector_train df = dataset[data_split$train, .SD, .SDcols = surv_cols],
strategy = "kmeans",
k = 4
)
<- data.matrix(
test_x $test, .SD, .SDcols = setdiff(feature_cols, surv_cols[1:2])]
dataset[data_split
)<- survival::Surv(
test_y event = (dataset[data_split$test, get("status")] |>
as.character() |>
as.integer()),
time = dataset[data_split$test, get("time")],
type = "right"
)
<- splitTools::create_folds(
fold_list y = split_vector_train,
k = 3,
type = "stratified",
seed = seed
)
# required learner arguments, not optimized
<- NULL
learner_args
# set arguments for predict function and performance metric,
# required for mlexperiments::MLCrossValidation and
# mlexperiments::MLNestedCV
<- NULL
predict_args <- c_index
performance_metric <- NULL
performance_metric_args <- FALSE
return_models
# required for grid search and initialization of bayesian optimization
<- expand.grid(
parameter_grid num.trees = seq(500, 1000, 500),
mtry = seq(2, 6, 2),
min.node.size = seq(1, 9, 4),
max.depth = seq(1, 9, 4),
sample.fraction = seq(0.5, 0.8, 0.3)
)# reduce to a maximum of 10 rows
if (nrow(parameter_grid) > 10) {
set.seed(123)
<- sample(seq_len(nrow(parameter_grid)), 10, FALSE)
sample_rows <- kdry::mlh_subset(parameter_grid, sample_rows)
parameter_grid
}
# required for bayesian optimization
<- list(
parameter_bounds num.trees = c(100L, 1000L),
mtry = c(2L, 9L),
min.node.size = c(1L, 20L),
max.depth = c(1L, 40L),
sample.fraction = c(0.3, 1.)
)<- list(
optim_args iters.n = ncores,
kappa = 3.5,
acq = "ucb"
)
<- mlexperiments::MLTuneParameters$new(
tuner learner = LearnerSurvRangerCox$new(),
strategy = "grid",
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
tuner$learner_args <- learner_args
tuner$split_type <- "stratified"
tuner$split_vector <- split_vector_train
tuner
$set_data(
tunerx = train_x,
y = train_y,
cat_vars = cat_vars
)
<- tuner$execute(k = 3)
tuner_results_grid #>
#> 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
<- mlexperiments::MLTuneParameters$new(
tuner learner = LearnerSurvRangerCox$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
$split_type <- "stratified"
tuner$split_vector <- split_vector_train
tuner
$set_data(
tunerx = train_x,
y = train_y,
cat_vars = cat_vars
)
<- tuner$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 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
<- mlexperiments::MLCrossValidation$new(
validator learner = LearnerSurvRangerCox$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
$set_data(
validatorx = train_x,
y = train_y,
cat_vars = cat_vars
)
<- validator$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 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
<- mlexperiments::MLNestedCV$new(
validator learner = LearnerSurvRangerCox$new(),
strategy = "grid",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = seed
)
$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator$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
$set_data(
validatorx = train_x,
y = train_y,
cat_vars = cat_vars
)
<- validator$execute()
validator_results #>
#> 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
<- mlexperiments::MLNestedCV$new(
validator learner = LearnerSurvRangerCox$new(),
strategy = "bayesian",
fold_list = fold_list,
k_tuning = 3L,
ncores = ncores,
seed = 312
)
$parameter_grid <- parameter_grid
validator$learner_args <- learner_args
validator$split_type <- "stratified"
validator$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
$set_data(
validatorx = train_x,
y = train_y,
cat_vars = cat_vars
)
<- validator$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
#> 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
<- 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 0.6515910
#> 2: Fold2 0.6600127
#> 3: Fold3 0.6558614
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.