diversityForest (version 0.5.0)
Innovative Complex Split Procedures in Random Forests Through
Candidate Split Sampling
Description
Implementations of three diversity forest (DF) (Hornung, 2022,
) variants.
The DF algorithm is a split-finding approach that allows complex split procedures to
be realized in random forest variants.
The three DF variants implemented are:
1. interaction forests (IFs) (Hornung & Boulesteix, 2022, ):
Model quantitative and qualitative interaction effects using bivariable splitting.
Come with the Effect Importance Measure (EIM), which can be used to identify variable
pairs that have well-interpretable quantitative and qualitative interaction effects
with high predictive relevance.
2. multi forests (MuFs) (Hornung & Hapfelmeier, 2024, ):
Model multi-class outcomes using multi-way and binary splitting. Come with two
variable importance measures (VIMs): The multi-class VIM measures the degree to which
the variables are specifically associated with one or more outcome classes, and the
discriminatory VIM, similar to conventional VIMs, measures the overall influence
strength of the variables.
3. the basic form of diversity forests that uses conventional univariable, binary
splitting (Hornung, 2022).
Except for multi forests, which are tailored for multi-class outcomes, all included
diversity forest variants support categorical, metric, and survival outcomes.
The package also includes plotting functions that make it possible to learn about the
forms of the effects identified using IFs and MuFs.
This is a fork of the R package 'ranger' (main author: Marvin N. Wright), which
implements random forests using an efficient C++ implementation.