How can we define GroupTrain for different type of datasets in Multiclass classfication? I tried an online available code for fisheriris dataset. It shows an error that G1vAll must be either a vector or character array. Please point out to my error.

%Editor window function [result] = multisvm(TrainingSet, GroupTrain, TestSet)

u = unique(GroupTrain);

numClasses = length(u);

result = zeros(length(TestSet(:,1)),1);

%bulid models

for k=1:numClasses

    G1vAll=(GroupTrain==u(k));
    models(k) = svmtrain(TrainingSet, G1vAll); %this line has error
end

%Following commands I used in Command window, if case I did anything wrong there:

load fisheriris; data = meas;

TrainingSet=[data(1:20,:);data(51:70,:);data(101:120,:)];

TestSet=[data(21:50,:);data(71:100,:);data(121:150,:)];

GroupTrain =[1:50,1; 51:100,1;101:150,1];

results = multisvm(TrainingSet, GroupTrain, TestSet);

disp('multi class problem');

disp(results);