modSkew: Skew Data by Factor Range

In exprso: Rapid Deployment of Machine Learning Algorithms

Description

modSkew skews a data set by making all sample vectors have the same total sum, introducing a new feature, and then making all sample vectors again have the same total sum.

Usage

modSkew(object, alpha = 0, uniform = TRUE)

Arguments

object	An ExprsArray object. The object that should undergo a replication of some feature selection and dimension reduction history.
alpha	An integer. The maximum range of skew factors used for skewing if uniform = TRUE. The standard deviation of the skew factors if uniform = FALSE. See Details.
uniform	A boolean. Toggles whether to draw skew factors from a uniform distribution or a normal distribution.

Details

If uniform = TRUE, skew factors are randomly sampled from the uniform distribution (0, alpha) + 1. Otherwise, skew factors are randomly sampled from the normal distribution with a mean of 0 and standard deviation of alpha. When using the normal distribution, these skew factors are transformed by taking the absolute value then adding one. For this reason, data are always unskewed when alpha = 0.

Value

A pre-processed ExprsArray object.

exprso documentation built on May 1, 2019, 7:11 p.m.