confusionMatrix.bayes: Confusion matrix for reporting accuracy

In tbonza/supml: "Algorithms for Supervised Machine Learning"

Description

Using an accuracy score when classes are imbalanced can be really deceiving. A confusion matrix can be used as an alternative measure of performance. This confusion matrix expects boolean spatial matrices for Y. It uses a 'resolve' matrix to exclude ineligible predictions.

Usage

## S3 method for class 'bayes'
confusionMatrix(object, Y_true, Y_predict)

Arguments

object	bayes s3 object
Y_true	boolean matrix of correct values
Y_predict	boolean matrix of predicted values

Value

2 by 2 confusion matrix

tbonza/supml documentation built on May 17, 2019, 3:14 a.m.