Dictionary of Performance Measures

Source: R/mlr_measures.R

A simple Dictionary storing objects of class Measure. Each measure has an associated help page, see mlr_measures_[id].

Format

R6::R6Class object.

Methods

• get(key, ...)
  (character(1), ...) -> any
  Retrieves object with key key from the dictionary.

• mget(keys, ...)
  (character(), ...) -> named list()
  Retrieves objects with keys keys from the dictionary, returns them in a list named with keys.

• has(keys)
character() -> logical()
  Returns a logical vector with TRUE at its i-th position, if the i-th key exists.

• keys(pattern)
character(1) -> character()
  Returns all keys which comply to the regular expression pattern.

• add(key, value)
  (character(1), any) -> self
  Adds object value to the dictionary with key key, potentially overwriting a previously stored value.

• remove(key)
character() -> self
  Removes object with key key from the dictionary.

S3 methods

• as.data.table(dict)
  Dictionary -> data.table::data.table()
  Returns a data.table() with fields "key", "task_type", "predict_type", and "packages" as columns.

See also

Other Dictionary: Dictionary, mlr_generators, mlr_learners, mlr_resamplings, mlr_tasks

Other Measure: MeasureClassif, MeasureRegr, Measure

Examples

as.data.table(mlr_measures)
#>                     key task_type predict_type packages
#>  1:         classif.acc   classif     response  Metrics
#>  2:         classif.auc   classif         prob  Metrics
#>  3:       classif.costs   classif     response         
#>  4:          classif.f1   classif         prob  Metrics
#>  5:         classif.fdr   classif     response         
#>  6:          classif.fn   classif     response         
#>  7:         classif.fnr   classif     response         
#>  8:         classif.for   classif     response         
#>  9:          classif.fp   classif     response         
#> 10:         classif.fpr   classif     response         
#> 11:        classif.mmce   classif     response  Metrics
#> 12:         classif.npv   classif     response         
#> 13:         classif.ppv   classif     response         
#> 14:   classif.precision   classif     response         
#> 15:      classif.recall   classif     response         
#> 16: classif.sensitivity   classif     response         
#> 17: classif.specificity   classif     response         
#> 18:          classif.tn   classif     response         
#> 19:         classif.tnr   classif     response         
#> 20:          classif.tp   classif     response         
#> 21:         classif.tpr   classif     response         
#> 22:           oob_error      <NA>     response         
#> 23:            regr.mae      regr     response  Metrics
#> 24:            regr.mse      regr     response  Metrics
#> 25:   selected_features      <NA>     response         
#> 26:           time_both      <NA>     response         
#> 27:        time_predict      <NA>     response         
#> 28:          time_train      <NA>     response         
#>                     key task_type predict_type packages
mlr_measures$get("classif.mmce")
#> <MeasureClassifMMCE:classif.mmce>
#> Packages: Metrics
#> Range: [0, 1]
#> Minimize: TRUE
#> Predict type: response