| clear query|facets|time |
Search criteria: .
Results from 181 to 190 from
2732 (0.286s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: Finding best NearestNUserNeighborhood size - Mahout - [mail # user]
|
|
...The stochastic nature of the evaluation means your results will vary randomly from run to run. This looks to my eyeballs like most of the variation you see. You probably want to average over...
|
|
|
Author: Sean Owen,
2013-01-23, 13:16
|
|
|
Re: MatrixMultiplicationJob runs with 1 mapper only ? - Mahout - [mail # user]
|
|
...Mappers are usually extremely fast since they start themselves on top of the data and their job is usually just parsing and emitting key value pairs. Hadoop's choices are usually fine. ...
|
|
|
Author: Sean Owen,
2013-01-23, 13:12
|
|
|
Re: Question - Mahout Taste - User-Based Recommendations... - Mahout - [mail # user]
|
|
...That's a question of using item-item similarity. For that you need to use something based on an ItemSimilarity, which is not user-based but instead the item-based implementation. Or you can ...
|
|
|
Author: Sean Owen,
2013-01-22, 19:59
|
|
|
Re: Question - Mahout Taste - User-Based Recommendations... - Mahout - [mail # user]
|
|
...Yes that's right. Look as UserBasedRecommender.mostSimilarUserIDs(), and Recommender.estimatePreference(). These do what you are interested in, and yes they are easy since they are just step...
|
|
|
Author: Sean Owen,
2013-01-22, 18:40
|
|
|
Re: Boolean preferences and evaluation - Mahout - [mail # user]
|
|
...Yes any metric that concerns estimated value vs real value can't be used since all values are 1. Yes, when you use the non-boolean version with boolean data you always get 1. When you use th...
|
|
|
Author: Sean Owen,
2013-01-22, 16:42
|
|
|
Re: Boolean preferences and evaluation - Mahout - [mail # user]
|
|
...That sounds reversed. Are you sure? without pref values, you should get 0. With values, you almost certainly won't get 0 RMSE. RMSE can't be used with boolean data. Code #4 needs to us...
|
|
|
Author: Sean Owen,
2013-01-22, 16:08
|
|
|
Re: Boolean preferences and evaluation - Mahout - [mail # user]
|
|
...No it's really #2, since the first still has data that is not true/false. I am not sure what eval you are running, but an RMSE test wouldn't be useful in case #2. It would always be 0 since ...
|
|
|
Author: Sean Owen,
2013-01-22, 07:58
|
|
|
Re: Changing in-memory DataModel to a DB dependent only DataModel after building recommender - Mahout - [mail # user]
|
|
...That's all right, but it's not something implemented in this project, except maybe in SVDRecommender to some extent. On Mon, Jan 21, 2013 at 8:57 PM, Osman Başkaya wrote:...
|
|
|
Author: Sean Owen,
2013-01-21, 20:59
|
|
|
Re: Changing in-memory DataModel to a DB dependent only DataModel after building recommender - Mahout - [mail # user]
|
|
...If you don't have the data in memory you can't compute anything. The recommender itself doesn't do anything without data. That's why it seemed like you really just wanted to compute everythi...
|
|
|
Author: Sean Owen,
2013-01-21, 20:40
|
|
|
Re: Changing in-memory DataModel to a DB dependent only DataModel after building recommender - Mahout - [mail # user]
|
|
...You would have to write this yourself, yes. If you're not keeping the data in memory, you're not updating the results in real-time. So there's no real need to keep any DataModel around at al...
|
|
|
Author: Sean Owen,
2013-01-21, 19:58
|
|
|
|
