EvaluationMeasures (version 1.1.0)

EvaluationMeasures.MCC: EvaluationMeasures.MCC

Description

MCC of prediction

Usage

EvaluationMeasures.MCC(Real = NULL, Predicted = NULL, Positive = 1, TP = NULL, TN = NULL, FP = NULL, FN = NULL)

Arguments

Real

Real binary values of the class

Predicted

Predicted binary values of the class

Positive

Consider 1 label as Positive Class unless changing this parameter to 0

TP

Number of True Positives. Number of 1 in real which is 1 in predicted.

TN

Number of True Negatives. Number of 0 in real which is 0 in predicted.

FP

Number of False Positives. Number of 0 in real which is 1 in predicted.

FN

Number of False Negatives. Number of 1 in real which is 0 in predicted.

Value

MCC

Details

Matthews Correlation Coefficient is correlation coefficient between real and predicted.

Positive One means perfect prediction,Zero means random prediction, Negative one means total disagreement.

By getting the predicted and real values or number of TP,TN,FP,FN return the Matthews Correlation Coefficient of model

Examples

EvaluationMeasures.MCC(c(1,0,1,0,1,0,1,0),c(1,1,1,1,1,1,0,0))