K-nearest neighbors (problem with code)

Hello, I have a little problem with understanding code. I write a paper, about KNN method and modification of this method. I found code, that works perfectly: find nearest neighbors, makes cross-validation, makes plots... http://mlalgorithms.svn.sourceforge.net/viewvc/mlalgorithms/Litvinov2009KMeans/?view=tar

But I can't understand how to change that code for different data sets, in their example, authors use Fisher iris datasets, but for my work I need to use different datasets. For example: (matrix 20 X 30, or 3 X 3000) ( http://www.machinelearning.ru/wiki/index.php?title=%D0%9C%D0%B5%D1%82%D0%BE%D0%B4_k_%D0%B1%D0%BB%D0%B8%D0%B6%D0%B0%D0%B9%D1%88%D0%B8%D1%85_%D1%81%D0%BE%D1%81%D0%B5%D0%B4%D0%B5%D0%B9_(%D0%BF%D1%80%D0%B8%D0%BC%D0%B5%D1%80))

How do I change the code to get the result I needed? I'm new to Matlab, do not kick me hard =)