And yes. It has the implementation of FP Bonsai instead of regular FPGrowth and automatic minSupport Raising using minnig stage. And it mines only TopK patterns.
So its an amalgamation of multiple methods. Thats why i need an extension on the writeup :) Robin On Fri, Feb 12, 2010 at 8:58 PM, Robin Anil <robin.a...@gmail.com> wrote: > Sure, The only difference is the combiner. and a sorting step to achieve > compression of trees via TransactionTree class > > Can I take an extension on that? I will include the link to the paper for > now > > Robin > On Fri, Feb 12, 2010 at 8:54 PM, Lukáš Vlček <lukas.vl...@gmail.com>wrote: > >> Robin, >> >> how much is your implementation based on >> http://infolab.stanford.edu/~echang/recsys08-69.pdf ? I mean if it is >> close >> enough then it might be a good idea to include a link to the paper. If it >> differs more then it would be very good to elaborate what is different in >> your approach. >> >> Regards, >> Lukas >> >> On Fri, Feb 12, 2010 at 3:47 PM, Grant Ingersoll <gsing...@apache.org >> >wrote: >> >> > Ah, I added a link from the Algorithms page. Thanks! >> > >> > On Feb 12, 2010, at 9:45 AM, Robin Anil wrote: >> > >> > > >> > >> http://cwiki.apache.org/confluence/display/MAHOUT/ParallelFrequentPatternMining >> > >> > >> > >> > >
