information_gain {msu}

Estimating information gain between two categorical variables.

Description

Information gain (also called mutual information) is a measure of the mutual dependence between two variables (see https://en.wikipedia.org/wiki/Mutual_information).

Usage

information_gain(x, y)

IG(x, y)

Arguments

x

A factor representing a categorical variable.

y

A factor representing a categorical variable.

Value

Information gain estimation based on Sannon entropy for variables x and y.

Examples

information_gain(factor(c(0,1)), factor(c(1,0)))
information_gain(factor(c(0,0,1,1)), factor(c(0,1,1,1)))
information_gain(factor(c(0,0,1,1)), factor(c(0,1,0,1)))
## Not run: 
information_gain(c(0,1), c(1,0))

## End(Not run)