default_params: Default parameter space for mlr3automl
In a-hanf/mlr3automl: AutoML in mlr3

Description Usage Arguments Value

View source: R/default_params.R

The parameter ranges are based on this Google doc.

default_params(
  learner_list,
  feature_counts,
  using_hyperband = TRUE,
  using_prefixes = TRUE,
  preprocessing = "stability",
  feature_types = NULL,
  additional_params = NULL,
  custom_trafo = NULL
)

`learner_list`	(`list()` \| `character()`) `List` of names from mlr_learners. Can be used to customize the learners to be tuned over. Default learners for classification: `c("classif.ranger", "classif.xgboost", "classif.liblinear")` Default learners for regression: `c("regr.ranger", "regr.xgboost", "regr.svm", "regr.liblinear", "regr.cv_glmnet")` Might break mlr3automl if a user-provided learner is incompatible with the provided task.
`feature_counts`	(`integer()`) 3x2 integer matrix with rownames c("no_encoding", "one_hot_encoding", "impact_encoding") and colnames c("numeric_cols", "all_cols"). The number of features is needed for tuning of `mtry` in Random Forest and setting the max. number of components in PCA.
`using_hyperband`	(`logical(1)`) For Tuning with Hyperband, a subsampling budget parameter is added to the pipeline.
`using_prefixes`	(`logical(1)`) If `TRUE`, parameter IDs are prefixed with the `learner$id`. Used to avoid name conflicts in branched pipelines.
`preprocessing`	(`character(1)` \| Graph) Type of preprocessing used.
`feature_types`	(`character()`) Types of features in the dataset. Used to determine appropriate imputation methods.
`additional_params`	(ParamSet) Additional parameter space to tune over, e.g. for custom learners / preprocessing.
`custom_trafo`	(`function(x, param_set)`) Trafo function to be applied in addition to existing transformations. Can be used to transform additional_params.