PomaRandForest: Classification Random Forest

In pcastellanoescuder/POMA: Tools for Omics Data Analysis

Classification Random Forest

Description

PomaRandForest performs classification random forest. This method can be used both for prediction and variable selection.

Usage

PomaRandForest(
  data,
  ntest = NULL,
  ntree = 500,
  mtry = floor(sqrt(ncol(t(SummarizedExperiment::assay(data))))),
  nodesize = 1,
  nvar = 20
)

Arguments

data	A SummarizedExperiment object.
ntest	Numeric. Indicates the percentage of observations that will be used as test set. Default is NULL (no test set).
ntree	Numeric. Indicates the number of trees to grow.
mtry	Numeric. Indicates the number of variables randomly sampled as candidates at each split. This value is set sqrt(p) (where p is number of variables in data) by default.
nodesize	Numeric. Indicates the minimum size of terminal nodes. Default is 1.
nvar	Numeric. Indicates the number of variables to show in the Gini Index plot.

Value

A list with results including plots and tables.

Author(s)

Pol Castellano-Escuder

References

A. Liaw and M. Wiener (2002). Classification and Regression by randomForest. R News 2(3), 18–22.

Examples

data <- POMA::st000336 %>% # Example SummarizedExperiment object included in POMA
  PomaImpute() %>% 
  PomaNorm()

## Output is a list with objects `MeanDecreaseGini` (tibble), `MeanDecreaseGini_plot` (ggplot2 object), `oob_error` (tibble), `error_tree` (ggplot2 object), and `model` (randomForest object)
data %>% 
  PomaRandForest(ntree = 500,
                 mtry = floor(sqrt(ncol(t(SummarizedExperiment::assay(data))))),
                 nodesize = 1,
                 nvar = 20)

pcastellanoescuder/POMA documentation built on Nov. 28, 2024, 1:21 p.m.