Skip to contents

Extreme Gradient Boosting Survival Learner

mlr_learners_surv.xgboost.Rd

eXtreme Gradient Boosting regression. Calls xgboost::xgb.train() from package xgboost.

Note

To compute on GPUs, you first need to compile xgboost yourself and link against CUDA. See https://xgboost.readthedocs.io/en/stable/build.html#building-with-gpu-support.

Custom mlr3 defaults

  • nrounds:

    • Actual default: no default.

    • Adjusted default: 1.

    • Reason for change: Without a default construction of the learner would error. Just setting a nonsense default to workaround this. nrounds needs to be tuned by the user.

  • nthread:

    • Actual value: Undefined, triggering auto-detection of the number of CPUs.

    • Adjusted value: 1.

    • Reason for change: Conflicting with parallelization via future.

  • verbose:

    • Actual default: 1.

    • Adjusted default: 0.

    • Reason for change: Reduce verbosity.

  • objective:

    • Actual default: reg:squarederror.

    • Adjusted default: survival:cox.

    • Reason for change: Changed to a survival objective.

Early stopping

Early stopping can be used to find the optimal number of boosting rounds. The early_stopping_set parameter controls which set is used to monitor the performance. Set early_stopping_set = "test" to monitor the performance of the model on the test set while training. The test set for early stopping can be set with the "test" row role in the mlr3::Task. Additionally, the range must be set in which the performance must increase with early_stopping_rounds and the maximum number of boosting rounds with nrounds. While resampling, the test set is automatically applied from the mlr3::Resampling. Not that using the test set for early stopping can potentially bias the performance scores.

Dictionary

This Learner can be instantiated via the dictionary mlr_learners or with the associated sugar function lrn():

mlr_learners$get("surv.xgboost")
lrn("surv.xgboost")

Meta Information

Parameters

IdTypeDefaultLevelsRange
aft_loss_distributioncharacternormalnormal, logistic, extreme-
aft_loss_distribution_scalenumeric-\((-\infty, \infty)\)
alphanumeric0\([0, \infty)\)
base_scorenumeric0.5\((-\infty, \infty)\)
boostercharactergbtreegbtree, gblinear, dart-
callbacksuntypedlist-
colsample_bylevelnumeric1\([0, 1]\)
colsample_bynodenumeric1\([0, 1]\)
colsample_bytreenumeric1\([0, 1]\)
disable_default_eval_metriclogicalFALSETRUE, FALSE-
early_stopping_roundsintegerNULL\([1, \infty)\)
early_stopping_setcharacternonenone, train, test-
etanumeric0.3\([0, 1]\)
feature_selectorcharactercycliccyclic, shuffle, random, greedy, thrifty-
fevaluntyped-
gammanumeric0\([0, \infty)\)
grow_policycharacterdepthwisedepthwise, lossguide-
interaction_constraintsuntyped--
iterationrangeuntyped--
lambdanumeric1\([0, \infty)\)
lambda_biasnumeric0\([0, \infty)\)
max_bininteger256\([2, \infty)\)
max_delta_stepnumeric0\([0, \infty)\)
max_depthinteger6\([0, \infty)\)
max_leavesinteger0\([0, \infty)\)
maximizelogicalNULLTRUE, FALSE-
min_child_weightnumeric1\([0, \infty)\)
missingnumericNA\((-\infty, \infty)\)
monotone_constraintsinteger0\([-1, 1]\)
normalize_typecharactertreetree, forest-
nroundsinteger-\([1, \infty)\)
nthreadinteger1\([1, \infty)\)
ntreelimitinteger-\([1, \infty)\)
num_parallel_treeinteger1\([1, \infty)\)
objectivecharactersurvival:coxsurvival:cox, survival:aft-
one_droplogicalFALSETRUE, FALSE-
predictorcharactercpu_predictorcpu_predictor, gpu_predictor-
print_every_ninteger1\([1, \infty)\)
process_typecharacterdefaultdefault, update-
rate_dropnumeric0\([0, 1]\)
refresh_leaflogicalTRUETRUE, FALSE-
sampling_methodcharacteruniformuniform, gradient_based-
sample_typecharacteruniformuniform, weighted-
save_nameuntyped--
save_periodinteger-\([0, \infty)\)
scale_pos_weightnumeric1\((-\infty, \infty)\)
seed_per_iterationlogicalFALSETRUE, FALSE-
skip_dropnumeric0\([0, 1]\)
strict_shapelogicalFALSETRUE, FALSE-
subsamplenumeric1\([0, 1]\)
top_kinteger0\([0, \infty)\)
tree_methodcharacterautoauto, exact, approx, hist, gpu_hist-
tweedie_variance_powernumeric1.5\([1, 2]\)
updateruntyped--
verboseinteger1\([0, 2]\)
watchlistuntyped-
xgb_modeluntyped--

References

Chen, Tianqi, Guestrin, Carlos (2016). “Xgboost: A scalable tree boosting system.” In Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 785--794. ACM. doi:10.1145/2939672.2939785 .

See also

Author

be-marc

Super classes

mlr3::Learner -> mlr3proba::LearnerSurv -> LearnerSurvXgboost

Methods

Public methods

Inherited methods

Method new()

Creates a new instance of this R6 class.

Usage

LearnerSurvXgboost$new()

Method importance()

The importance scores are calculated with xgboost::xgb.importance().

Usage

LearnerSurvXgboost$importance()

Returns

Named numeric().

Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerSurvXgboost$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

learner = mlr3::lrn("surv.xgboost")
print(learner)
#> <LearnerSurvXgboost:surv.xgboost>: Gradient Boosting
#> * Model: -
#> * Parameters: nrounds=1, nthread=1, verbose=0, early_stopping_set=none
#> * Packages: mlr3, mlr3proba, mlr3extralearners, xgboost
#> * Predict Types:  [crank], lp
#> * Feature Types: integer, numeric
#> * Properties: importance, missings, weights

# available parameters:
learner$param_set$ids()
#>  [1] "aft_loss_distribution"       "aft_loss_distribution_scale"
#>  [3] "alpha"                       "base_score"                 
#>  [5] "booster"                     "callbacks"                  
#>  [7] "colsample_bylevel"           "colsample_bynode"           
#>  [9] "colsample_bytree"            "disable_default_eval_metric"
#> [11] "early_stopping_rounds"       "early_stopping_set"         
#> [13] "eta"                         "feature_selector"           
#> [15] "feval"                       "gamma"                      
#> [17] "grow_policy"                 "interaction_constraints"    
#> [19] "iterationrange"              "lambda"                     
#> [21] "lambda_bias"                 "max_bin"                    
#> [23] "max_delta_step"              "max_depth"                  
#> [25] "max_leaves"                  "maximize"                   
#> [27] "min_child_weight"            "missing"                    
#> [29] "monotone_constraints"        "normalize_type"             
#> [31] "nrounds"                     "nthread"                    
#> [33] "ntreelimit"                  "num_parallel_tree"          
#> [35] "objective"                   "one_drop"                   
#> [37] "predictor"                   "print_every_n"              
#> [39] "process_type"                "rate_drop"                  
#> [41] "refresh_leaf"                "sampling_method"            
#> [43] "sample_type"                 "save_name"                  
#> [45] "save_period"                 "scale_pos_weight"           
#> [47] "seed_per_iteration"          "skip_drop"                  
#> [49] "strict_shape"                "subsample"                  
#> [51] "top_k"                       "tree_method"                
#> [53] "tweedie_variance_power"      "updater"                    
#> [55] "verbose"                     "watchlist"                  
#> [57] "xgb_model"