create.training.validation.split {iDOS}

create.training.validation.split

Description

Utility function to create random partitions of a dataset into training and validation sets. If samples are < 200, 66:34; otherwise 50:50 partitions are generated between training and validation sets respectively

Usage

create.training.validation.split(
  exp.data = NULL, ann.data = NULL, seed.number = 51214
  )

Arguments

exp.data

Feature by sample mRNA abundance matrix

ann.data

Sample by clinical attribute matrix

seed.number

Random seed for sampling

Value

A list of four matrices expression and two associated clinical matrices (exp.T, ann.T, exp.V and ann.V). One set for training and one for validation

Author(s)

Syed Haider

Examples

# load test data
x <- get.test.data(data.types = c("mRNA.T", "ann"));

# create training and validation sets
partitioned.datasets <- create.training.validation.split(
  exp.data = x$mRNA.T$BLCA, 
  ann.data = x$ann$BLCA, 
  seed.number = 51214
  );