[
https://issues.apache.org/jira/browse/MAHOUT-542?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Danny Bickson updated MAHOUT-542:
---------------------------------
Attachment: MAHOUT-542-4.patch
Hi everyone,
Issue solved. I've created a new patch and tested it to work on movielens 1M
dataset. On amaon EC2 machine it takes 1998 seconds (large instance).
With an accuracy of: RMSE: 0.8546120366924382, MAE: 0.6798083002225481
It seems that 3 files where already included in the patch while being in SVN.
Another issue was line 94 of math.als.AlternateLeastSquaresSolverTest.java
which calls fail(). This killed the unit testing. Commenting it and running the
rest of the command did not seem to affect the running results.
Please take a look into this.
Best,
Danny Bickson
> MapReduce implementation of ALS-WR
> ----------------------------------
>
> Key: MAHOUT-542
> URL: https://issues.apache.org/jira/browse/MAHOUT-542
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.5
> Reporter: Sebastian Schelter
> Attachments: MAHOUT-452.patch, MAHOUT-542-2.patch,
> MAHOUT-542-3.patch, MAHOUT-542-4.patch
>
>
> As Mahout is currently lacking a distributed collaborative filtering
> algorithm that uses matrix factorization, I spent some time reading through a
> couple of the Netflix papers and stumbled upon the "Large-scale Parallel
> Collaborative Filtering for the Netflix Prize" available at
> http://www.hpl.hp.com/personal/Robert_Schreiber/papers/2008%20AAIM%20Netflix/netflix_aaim08(submitted).pdf.
> It describes a parallel algorithm that uses "Alternating-Least-Squares with
> Weighted-λ-Regularization" to factorize the preference-matrix and gives some
> insights on how the authors distributed the computation using Matlab.
> It seemed to me that this approach could also easily be parallelized using
> Map/Reduce, so I sat down and created a prototype version. I'm not really
> sure I got the mathematical details correct (they need some optimization
> anyway), but I wanna put up my prototype implementation here per Yonik's law
> of patches.
> Maybe someone has the time and motivation to work a little on this with me.
> It would be great if someone could validate the approach taken (I'm willing
> to help as the code might not be intuitive to read) and could try to
> factorize some test data and give feedback then.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
