LearnerSurvRangerCox {mlsurvlrnrs}

R6 Class to construct a Ranger survival learner for Cox regression

Description

The LearnerSurvRangerCox class is the interface to perform a Cox regression with the ranger R package for use with the mlexperiments package.

Details

Optimization metric: C-index Can be used with

• mlexperiments::MLTuneParameters

• mlexperiments::MLCrossValidation

• mlexperiments::MLNestedCV

Super class

mlexperiments::MLLearnerBase -> LearnerSurvRangerCox

Methods

Public methods

• LearnerSurvRangerCox$new()

• LearnerSurvRangerCox$clone()

Inherited methods

• mlexperiments::MLLearnerBase$bayesian_scoring_function()
• mlexperiments::MLLearnerBase$cross_validation()
• mlexperiments::MLLearnerBase$fit()
• mlexperiments::MLLearnerBase$predict()

Method new()

Create a new LearnerSurvRangerCox object.

Usage

LearnerSurvRangerCox$new()

Returns

A new LearnerSurvRangerCox R6 object.

Examples

LearnerSurvRangerCox$new()

Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerSurvRangerCox$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

ranger::ranger()

Examples

# survival analysis

dataset <- survival::colon |>
  data.table::as.data.table() |>
  na.omit()
dataset <- dataset[get("etype") == 2, ]

seed <- 123
surv_cols <- c("status", "time", "rx")

feature_cols <- colnames(dataset)[3:(ncol(dataset) - 1)]

param_list_ranger <- expand.grid(
  sample.fraction = seq(0.6, 1, .2),
  min.node.size = seq(1, 5, 4),
  mtry = seq(2, 6, 2),
  num.trees = c(5L, 10L),
  max.depth = seq(1, 5, 4)
)

ncores <- 2L

split_vector <- splitTools::multi_strata(
  df = dataset[, .SD, .SDcols = surv_cols],
  strategy = "kmeans",
  k = 4
)

train_x <- model.matrix(
  ~ -1 + .,
  dataset[, .SD, .SDcols = setdiff(feature_cols, surv_cols[1:2])]
)
train_y <- survival::Surv(
  event = (dataset[, get("status")] |>
             as.character() |>
             as.integer()),
  time = dataset[, get("time")],
  type = "right"
)

fold_list <- splitTools::create_folds(
  y = split_vector,
  k = 3,
  type = "stratified",
  seed = seed
)

surv_ranger_cox_optimizer <- mlexperiments::MLCrossValidation$new(
  learner = LearnerSurvRangerCox$new(),
  fold_list = fold_list,
  ncores = ncores,
  seed = seed
)
surv_ranger_cox_optimizer$learner_args <- as.list(
  data.table::data.table(param_list_ranger[1, ], stringsAsFactors = FALSE)
)
surv_ranger_cox_optimizer$performance_metric <- c_index

# set data
surv_ranger_cox_optimizer$set_data(
  x = train_x,
  y = train_y
)

surv_ranger_cox_optimizer$execute()


## ------------------------------------------------
## Method `LearnerSurvRangerCox$new`
## ------------------------------------------------

LearnerSurvRangerCox$new()