information_gain: Calculate the Information Gain for a set split

In teofanan/classprobtree: Fitting and Display of Classification and Probability Estimation Trees

Description

information_gain calculates the Information Gain resulting from the splitting of a set. This is the difference between the entropy of the entire set and the weighted entropies of the

Usage

information_gain(x, y)

Arguments

x	the target vector i.e. the entire set of labels (target variable values)
y	the splitting vector i.e. the vector of values for the splitting attribute

Value

The calculated Information Gain (IG)

See Also

entropy best_information_gain

teofanan/classprobtree documentation built on May 17, 2019, 5:53 p.m.