SplitData: Selection of samples for training

In beyergroup/ADImpute: Adaptive Dropout Imputer (ADImpute)

Description

SplitData selects a portion (ratio) of samples (columns in data) to be used as training set

Usage

SplitData(data, ratio = .7, write.to.file = FALSE, train.only = TRUE)

Arguments

data	matrix; raw counts (genes as rows and samples as columns)
ratio	numeric; ratio of the samples to be used for training
write.to.file	logical; should the output be written to a file?
train.only	logical; if TRUE define only a training dataset, if FALSE writes both training and validation sets (defaults to TRUE)

Details

Selects a portion (ratio) of samples (columns in data) to be used as training set and writes to file 'training_raw.txt'.

Value

matrix containing raw counts (genes as rows and samples as columns)

beyergroup/ADImpute documentation built on Dec. 19, 2021, 8:48 a.m.