.

what kind of problem do you have in mind ?

("K-greedy algorithm" does not mean much to me ...)

.

I am reading a paper that they use k-greedy for select feature on classification 

.

if you attach the reference, maybe you'll get some valuable advice, but "k-greedy for select feature on classification" does not really ring a bell to me

(well very slightly, just keeping the k features with the strongest correlation (loosely speaking) with the target ?)

anyway : please attach the reference

.

one last word ; if you do not know where to find it (whatever "it" is), then look in WEKA ... it might well be sitting there, waiting for you

http://www.cs.waikato.ac.nz/ml/weka/

.

Do you mean a greedy K-Means Algorithm? If yes try this:

http://www.programcreek.com/java-api-examples/index.php?source_dir=K-Means-TSP-master/src/VisualizeKM/Greedy.java