DataTableWithTrainTestSets: Random sampling of n training sets in a DataTableWithClasses.

In elqumsan/RNAseqMVA: Application of Multivariate Analysis methods to RNA-seq Data

Description

Select n random subsets for training. among the biological samples from a DataTableWithClasses.

Usage

DataTableWithTrainTestSets(
  self,
  stratified = TRUE,
  iterations = parameters$iterations,
  trainingProportion = parameters$trainingProportion
)

Arguments

self	an object of the class DataTableWithClasses
stratified=TRUE	if true, sampling is done in each class separately in order to preserve the relative frequencies of classes in training and testing sets.
iterations=parameters$iterations	number of train/test iterations, which defines the number of independent sampled subsets
trainingProportion=parameters$trainingProportion	proportion of samples to sample for each training set

Value

object of class DataTableWithTrainTestSets containing the following attributes

• iteration: which is number of resampling

• trainPropotion: which is ratio of train volume from whole of dataset

• statified: parameter which refer to stratification criteria would be included in analysis or not.

• trainSizePerClass: which is specify the train volume for each class included in analysis.

• trainIndices: which are whole indices for training process.

• testIndices: which are whole indices for the testing process.

Author(s)

Jacques van Helden and Mustafa AbuElQumsan

elqumsan/RNAseqMVA documentation built on March 10, 2021, 8:10 a.m.