[
https://issues.apache.org/jira/browse/MAHOUT-1346?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13920319#comment-13920319
]
Sebastian Schelter commented on MAHOUT-1346:
--------------------------------------------
Dmitriy, I read through your write-up and I have no words. I really love what
you created and I'm looking forward to having this as part of Mahout. Would
like to see our algorithms rewritten in your linear algebra dsl and executed
(and optimized!) on Spark.
Btw, be sure to also post your writeup to the spark mailinglist, I'm sure the
guys there are also interested!
> Spark Bindings (DRM)
> --------------------
>
> Key: MAHOUT-1346
> URL: https://issues.apache.org/jira/browse/MAHOUT-1346
> Project: Mahout
> Issue Type: Improvement
> Affects Versions: 0.8
> Reporter: Dmitriy Lyubimov
> Assignee: Dmitriy Lyubimov
> Fix For: 1.0
>
> Attachments: ScalaSparkBindings.pdf
>
>
> Spark bindings for Mahout DRM.
> DRM DSL.
> Disclaimer. This will all be experimental at this point.
> The idea is to wrap DRM by Spark RDD with support of some basic
> functionality, perhaps some humble beginning of Cost-based optimizer
> (0) Spark serialization support for Vector, Matrix
> (1) Bagel transposition
> (2) slim X'X
> (2a) not-so-slim X'X
> (3) blockify() (compose RDD containing vertical blocks of original input)
> (4) read/write Mahout DRM off HDFS
> (5) A'B
> ...
--
This message was sent by Atlassian JIRA
(v6.2#6252)
