Brandt's Tumblr

Hierclust: Simple Hierarchical Clustering

For a project that I have coming up soon at work, I’m going to need to do hierarchical clustering of spatial data as part of a Ruby on Rails project. I was sure that there would be a pre-existing library to help me out, but as it turns out, there isn’t.

Well, I’d been looking for a chance to do a little recreational programming, and to release an open source project, and to use Dr Nic’s nify “newgem” library. So without further ado…

Allow me to announce hierclust, a ruby library for performing hierarchical clustering. The current release is the result of only an hour or so of work, so it’s a naive implementation that leaves a lot to be desired performance-wise. The basics are there, though. It’s usable as is, and there are lots of improvements coming down the road shortly.

Enjoy!