Fit a ranger Random Forest model to a cv_set

Usage

fit_ranger(
  cv_set,
  y_var,
  id_vars,
  pred_vars,
  hyper_control = list(mtry = NULL, min.node.size = NULL, num.trees = 500),
  importance = "none",
  quantile_levels = c(0.01, 0.025, seq(0.05, 0.95, by = 0.05), 0.975, 0.99),
  return_model = FALSE
)

Arguments

cv_set: list object containing analysis and assessment data.frames
y_var: string name of column of observed values
id_vars: names of columns used as keys/ids in data.frames
pred_vars: vector string of predictor variables to use in model
hyper_control: hyperparameters to use in the model, in either list or named vector format. Defaults are ranger defaults
importance: the method with which to estimate variable importance. Default = 'none' means no variable importance is estimated
quantile_levels: quantile levels to use when predicted via quantile regression. Default = c(0.01,0.025, seq(0.05,0.95, by = 0.05), 0.975, 0.99)
return_model: whether or not to return ranger model object. Default = FALSE.

Value

prediction intervals on analysis and assessment data or list containing model object and prediction intervals, if return_model = TRUE