rf: Random Survival Forest Wrapper Function

In pranavdorbala/proteomicsHF: ARIC Proteomics of Heart Failure -- Biomarker Discovery Pipeline

Description

This function wraps the randomForestSRC::rfsrc() function. It first runs an initial tuning algorithm, identifying the most appropriate parameters for random forest model fit. Then, the model runs the more detailed random forest tree generation step. The tree is then returned. The time variable must be stored in a variable named time, and outcome in variable named outc. These variable translations are done automatically in the functions accessed by users.

Usage

rf(data, seed)

Arguments

data	Tibble of data containing the variables to be regressed.
seed	The random seed to standardize random forest creation

Value

rand.tree

The random forest grown in this algorithm

tune.tree

The tuning forest and parameters derived

vars.tree

The variables used to grow this forest

Examples

## Not run: 

tree <- rf(visit.data, seed=101010)

TRUE USAGE:

tree.list <- filter.rf(visit.data, time="fuptime", outc="hfdiag",
                       iter = 30, adjust = adjustment.variables)

## End(Not run)

pranavdorbala/proteomicsHF documentation built on March 9, 2021, 12:22 a.m.