OptimalBinningWoE (version 1.0.8)

obwoe_algorithm: Binning Algorithm Parameter

Description

A qualitative tuning parameter for selecting the optimal binning algorithm in step_obwoe.

Usage

obwoe_algorithm(values = NULL)

Value

A dials qualitative parameter object.

Arguments

values

A character vector of algorithm names to include in the parameter space. If NULL (default), includes all 29 algorithms (28 specific algorithms plus "auto").

Details

The algorithms are organized into three groups:

Universal (support both numerical and categorical features): "auto", "jedi", "jedi_mwoe", "cm", "dp", "dmiv", "fetb", "mob", "sketch", "udt"

Numerical only: "bb", "ewb", "fast_mdlp", "ir", "kmb", "ldb", "lpdb", "mblp", "mdlp", "mrblp", "oslp", "ubsd"

Categorical only: "gmb", "ivb", "mba", "milp", "sab", "sblp", "swb"

When tuning with mixed feature types, consider restricting values to universal algorithms only.

See Also

step_obwoe, obwoe

Examples

# Default: all algorithms
obwoe_algorithm()

# Restrict to universal algorithms for mixed data
obwoe_algorithm(values = c("jedi", "mob", "dp", "cm"))

# Numerical-only algorithms
obwoe_algorithm(values = c("mdlp", "fast_mdlp", "ewb", "ir"))