Apache Java Math
It feels that IT world has matured significantly during past few years. I seem to remember that something like clustering analysis was a tedious work and you'd have to use matlab or some C libraries.Today I've downloaded the jar file, tossed it into a new Eclipse project and printed out some really nice stats for a fastq file. ERR001342, my favourite dataset :)
I'm a bit confused why k-mean clustering gives me very different result each time I run it. Need to read more, or simply think about it for a minute.
Labels: ERR001342 statistics fastq
posted by Ambidexter @ 12:23 PM
