Wednesday, March 16, 2011

QT clustering

QT clustering is a very simple clustering algorithm, where you don't need to provide the desired number of clusters (like in K-Means). Instead, you give a maximum distance allowed. In one variant, you consider the diameter of the clusters already formed. In another variant you consider a single linkage distance. Here you have the code


  1. The compression seems to be corrupted. I wasn't able to open it. Please upload again.

  2. The link to the code appears to be broken.

  3. I've just stumbled on your blog and I'm learning tons at each post I read!
    Thanks a lot for sharing your knowledge and work!
    (grazie mille!)

    p.s. the link points to the .tgz which is no longer there (renaming to .zip does the trick though so i guess the file is still there!)


  4. mmmh I haven't been able to really play with your code until now, but it seems like something is missing: the Clustering.cpp file is extremely short, the main function (qt_clustering) makes no use of the max_iterations variable, and seems to only go through the data once. Is this only an initialization? or is QT clustering really that simple? (that would probably surprise me)