CreateTrainData: Preparation of training data for method evaluation

In ADImpute: Adaptive Dropout Imputer (ADImpute)

Description

CreateTrainingData selects a subset of cells to use as training set and sets a portion (mask) of the non-zero entries in each row of the subset to zero

Usage

CreateTrainData(data, train.ratio = .7, train.only = TRUE, mask = .1,
write = FALSE)

Arguments

data	matrix; raw counts (genes as rows and samples as columns)
train.ratio	numeric; ratio of the samples to be used for training
train.only	logical; if TRUE define only a training dataset, if FALSE writes both training and validation sets (defaults to TRUE)
mask	numeric; ratio of total non-zero samples to be masked per gene (defaults to .1)
write	logical; should the output be written to a file?

Value

list with resulting matrix after subsetting and after masking

ADImpute documentation built on Nov. 8, 2020, 5:30 p.m.