ranger_filter function

Random forest ranger filter

Fits a random forest model via the ranger package and ranks variables by variable importance.

ranger_filter(
  y,
  x,
  nfilter = NULL,
  type = c("index", "names", "full"),
  num.trees = 1000,
  mtry = ncol(x) * 0.2,
  ...
)

Arguments

• y: Response vector
• x: Matrix or dataframe of predictors
• nfilter: Number of predictors to return. If NULL all predictors are returned.
• type: Type of vector returned. Default "index" returns indices, "names" returns predictor names, "full" returns a named vector of variable importance.
• num.trees: Number of trees to grow. See ranger::ranger .
• mtry: Number of predictors randomly sampled as candidates at each split. See ranger::ranger .
• ...: Optional arguments passed to ranger::ranger .

Returns

Integer vector of indices of filtered parameters (type = "index") or character vector of names (type = "names") of filtered parameters. If type is "full" a named vector of variable importance is returned.

Details

This filter uses the ranger() function from the ranger package. Variable importance is calculated using mean decrease in gini impurity.