rf_ranking: A MVDA Function

In angy89/MVDA_package: Multi-View Biological Data Analysis

Description

This function determines a ranking of predictors by using random foresto from the package randomForest.

Usage

rf_ranking(prototype, info, MTRY = c(1, 2, 3), NTREE = c(100, 200, 500),
  NPERM = c(1, 2, 3), NODESIZE = c(1, 5))

Arguments

prototype	is the matrix of prototype, patients are on columns and featuers are on rows
info	is the factor of class label
MTRY	vector of possible values for the random forest's mtry parameters
NTREE	vector of possible values for the random forest's ntree parameters
NPERM	vector of possible values for the random forest's nperm parameters
NODESIZE	vector of possible values for the random forest's nodesize parameters

Value

A matrix of importance measure, one row for each predictor variable. The column(s) are different importance measures.

angy89/MVDA_package documentation built on May 7, 2019, 8:58 p.m.