Re: Soliciting opinion on scala packaging convention for Mahout

2013-10-01 Thread Ted Dunning
It is important to use at least Apache Mahout as part of the name. >From there, it is only four more characters to org.apache.mahout.math On Tue, Oct 1, 2013 at 3:21 PM, Dmitriy Lyubimov wrote: > Hello, > > I guess it was scala style to have shorter packages (e.g. "mahout.math" > instead of

[jira] [Commented] (MAHOUT-1344) Self-Organizing Map algorithm (batch version)

2013-10-01 Thread Ted Dunning (JIRA)
[ https://issues.apache.org/jira/browse/MAHOUT-1344?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13783669#comment-13783669 ] Ted Dunning commented on MAHOUT-1344: - This is really unfortunate. You just provided

Jenkins build is back to normal : mahout-nightly #1370

2013-10-01 Thread Apache Jenkins Server
See

Jenkins build is back to normal : mahout-nightly ยป Mahout Integration #1370

2013-10-01 Thread Apache Jenkins Server
See

Soliciting opinion on scala packaging convention for Mahout

2013-10-01 Thread Dmitriy Lyubimov
Hello, I guess it was scala style to have shorter packages (e.g. "mahout.math" instead of "o.a.m.mahout") as it happens my current scala work uses "mahout.math" form. Should i really be bothered with adding o.a. everywhere? (I know spark used to be just "spark" but now that they moved to incuba

Re: K-SVD

2013-10-01 Thread Ted Dunning
Yes. This should be relatively easy to build in Mahout. There are several decent courses of action: 1) use the streaming k-means to reduce the data to a sketch of the original data and then apply an in-memory k-svd algorithm to that. This could be really, really fast and has a reasonable chance

Re: 0.9?

2013-10-01 Thread Pat Ferrel
Tunneling (rat-holing?) into the cross-recommender and Solr+Mahout version. Things to note: 1) The pure Mahout XRecommenderJob needs a cross-LLR or a cross-similairty job. Currently there is only cooccurrence for sparsification, which is far from optimal. This might take the form of a cross RSJ

K-SVD

2013-10-01 Thread Niederberger Thomas (tnied...@hsr.ch)
Hello everyone, I'm currently working on my master thesis in compressed sensing for video. Part of my project might be to learn a dictionary from a large collection of videos. The typical algorithm to use for this task is called K-SVD. K-SVD is very similar to K-Means but there are two key differe

Re: 0.9?

2013-10-01 Thread Isabel Drost-Fromm
On Monday, September 30, 2013 11:21:30 AM Grant Ingersoll wrote: > This sounds good to the extent we can get them done. Do you have JIRA > issues for any of these open? November isn't hard and fast for 0.9, but I > suspect it will be January if we push things out. We could also think about inclu