could anyone guide me how to make roc curve from the trained model , i know their is perfcurve function for it but i don't have any score values return by the classifiers. am unable to use this function. so any other way?

1 次查看(过去 30 天)
if true
% code
Label: ''
Description: ''
ClassLabels: [91x1 double]
GroundTruth: [23450x1 double]
NumberOfObservations: 23450
ControlClasses: [90x1 double]
TargetClasses: 1
ValidationCounter: 1
SampleDistribution: [23450x1 double]
ErrorDistribution: [23450x1 double]
SampleDistributionByClass: [91x1 double]
ErrorDistributionByClass: [91x1 double]
CountingMatrix: [92x91 double]
CorrectRate: 0.9986
ErrorRate: 0.0014
LastCorrectRate: 0.9986
LastErrorRate: 0.0014
InconclusiveRate: 0
ClassifiedRate: 1
Sensitivity: 1
Specificity: 0.9993
PositivePredictiveValue: 0.5789
NegativePredictiveValue: 1
PositiveLikelihood: 1.4643e+03
NegativeLikelihood: 0
Prevalence: 9.3817e-04
DiagnosticTable: [2x2 double]
end

回答(0 个)

类别

Help CenterFile Exchange 中查找有关 Bioinformatics Toolbox 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by