get best model for variable based on metric — get

From a folder containing model object created with scripts used in the BDF-SSL framework, select the best model candidate based on a evaluation metric for a given variable.

Usage

get_best(
  model_eval,
  type_ = "cubist",
  prefix = NULL,
  variable_ = "CORG",
  metric = "test.rmse",
  maximise = F
)

Arguments

model_eval: model evaluation object created with evaluate_model_batch()
type_: Model type, i.e., "cubist", "pls", "svmLinear"...
prefix: Model names prefix, usually defines model type. Default is type_
variable_: Variable for which the best model is to be searched
metric: evaluation statistic which is used to select best model
maximise: Should the model with the highest metric be selected? E.g., for R2 set to True. Default is False.

Note

Not yet generalised