<< libsvm_partest utilities libsvm_savemodel >>
libsvm Toolbox >> utilities > libsvm_rocplot

libsvm_rocplot

plotroc draws the recevier operating characteristic(ROC) curve for an svm-model

Calling Sequence

auc = libsvm_rocplot(training_label, training_instance)
auc = libsvm_rocplot(training_label, training_instance , model)
auc = libsvm_rocplot(training_label, training_instance , libsvm_options)
auc = libsvm_rocplot(training_label, training_instance , libsvm_options, uselinear)

Description

Use cross-validation on training data to get decision values and plot ROC curve.

Use the given model to predict testing data and obtain decision values for ROC

Examples

[label,instance]=libsvmread(fullfile(libsvm_getpath(),"demos","heart_scale"));
// 5-fold cross-classification, training of svm is done inside of libsvm_rocplot
libsvm_rocplot(label, instance,'-v 5');

// training using libsvm_svmtrain
model = libsvm_svmtrain(label,instance);
libsvm_rocplot(label,instance,model);

//--------------------------
//libsvm_rocplot for linear models
[label,instance]=libsvmread(fullfile(libsvm_getpath(),"demos","heart_scale"));
// 5-fold cross-classification, training of svm is done inside of libsvm_rocplot
libsvm_rocplot(label, instance,'-v 5',%t);

// training using train
model = libsvm_lintrain(label,instance);
libsvm_rocplot(label,instance,model);

See also

Authors


Report an issue
<< libsvm_partest utilities libsvm_savemodel >>