mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Mirko Gontek <mirko.gon...@uni-koeln.de>
Subject Re: FileDataModel throws UnsupportedOperationException
Date Wed, 22 Apr 2009 15:46:46 GMT
Great! Thanks for that info, Sean.

>> I would like to implement a GenericItemBasedRecommender, my  
>> testdata is a DB
>> with 300.000 Preferences (130.000 items, 12.000 users).
>
> Typically if you have many more items than users, you would prefer a
> user-based recommender, for performance. This is because a user-based
> recommender compares the user to all other users, and an item compares
> an item to all other items..
>
> But, an item-based recommender could be fast and appropriate if you
> have a very efficient source of item-item similarities -- see below.
>
Ok, I think I will test User-based recommender, instead. For now I  
don't have a source of item-item similarities.

>
> Yes I would recommend you use memory as much as possible. At some
> point you will not be able to, of course. Then I think you would
> resort to a JDBC-based data model which does *not* read into memory.
> You might store pre-computed item-item similarities in a DB rather
> than memory. This will slow things down of course, but becomes
> necessary.

Yeah, I was wondering. I experimented with a simple non-caching JDBC  
DataModel implementation for an RDF triple store. However the  
performance was so bad that I thought memory-based would be the only  
way to do it. Well, my data could become too large for my memory.  
Maybe I will have to tweak my DB connection. But for now, I will stick  
with the memory-solution as long as possible.

Thanks, Mirko
Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message