ucpm: Uschi's classification performance measures

Description Usage Arguments Details Value Author(s) References Examples

View source: R/ucpm.R

Description

Function to calculate the Correctness Rate, the Accuracy, the Ability to Seperate and the Confidence of a classification rule.

Usage

1
ucpm(m, tc, ec = NULL)

Arguments

m

matrix of (scaled) membership values

tc

vector of true classes

ec

vector of estimated classes (only required if scaled membership values are used)

Details

Value

A list with elements:

CR

Correctness Rate

AC

Accuracy

AS

Ability to Seperate

CF

Confidence

CFvec

Confidence for each (true) class

Author(s)

Karsten Luebke, karsten.luebke@fom.de

References

Garczarek, Ursula Maria (2002): Classification rules in standardized partition spaces. Dissertation, University of Dortmund. URL http://hdl.handle.net/2003/2789

Examples

1
2
3
library(MASS)
data(iris)
ucpm(predict(lda(Species ~ ., data = iris))$posterior, iris$Species)

Example output

Loading required package: MASS
$CR
[1] 0.98

$AC
[1] 0.9527401

$AS
[1] 0.971972

$CF
[1] 0.983818

$CFvec
    setosa versicolor  virginica 
 1.0000000  0.9791587  0.9722954 

klaR documentation built on March 26, 2020, 5:50 p.m.

Related to ucpm in klaR...