Superclasses:
Data partitions for cross validation
An object of the cvpartition class defines
a random partition on a set of data of a specified size. Use this
partition to define test and training sets for validating a statistical
model using cross validation.
| cvpartition | Create cross-validation partition for data |
| disp | Display cvpartition object |
| display | Display cvpartition object |
| repartition | Repartition data for cross-validation |
| test | Test indices for cross-validation |
| training | Training indices for cross-validation |
| NumObservations | Number of observations (including observations with missing group values) |
| NumTestSets | Number of test sets |
| TestSize | Size of each test set |
| TrainSize | Size of each training set |
| Type | Type of partition |
Value. To learn how this affects your use of the class, see Comparing Handle and Value Classes (MATLAB) in the MATLAB® Object-Oriented Programming documentation.
Use a 10-fold stratified cross validation to compute the misclassification
error for classify on iris data.
load('fisheriris');
CVO = cvpartition(species,'k',10);
err = zeros(CVO.NumTestSets,1);
for i = 1:CVO.NumTestSets
trIdx = CVO.training(i);
teIdx = CVO.test(i);
ytest = classify(meas(teIdx,:),meas(trIdx,:),...
species(trIdx,:));
err(i) = sum(~strcmp(ytest,species(teIdx)));
end
cvErr = sum(err)/sum(CVO.TestSize);