perfCv

Cross-validation accuracy of given dataset and classifier

Contents

Syntax

Description

vRr=perfCv(DS, opt) returns the cross-validation recognition rate based on the given options.

• vRr: validating recognition rate
• DS: Dataset
  • DS.input: Input data (each column is a feature vector)
  • DS.output: Output class (ranging from 1 to N)
• opt: optionsss
  • opt.classifier: Classifier to be used
  • opt.classifierOpt: Options for the classifier
  • opt.cvOpt: options for cross validation (obtained from cvDataGen)

vRr=perfCv(DS, opt, 1) also plots the dataset and misclasified instances (if the dimension is 2).

[vRrOverall, tRrOverall, vRr, tRr, computedClass]=perfCv(...) returns more info about cross-validation:

• vRrOverall: Overall validating RR
• tRrOverall: Overall training RR
• vRr: Validating RR for all folds
• tRr: Training RR for all folds
• computedClass: The computed class of each data instance in DS

Example

DS=prData('iris');
opt=perfCv('defaultOpt');
vRr=perfCv(DS, opt, 1);

See Also

perfCv4classifier, perfLoo.

Published with MATLAB® R2020b