You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Saikat Kanjilal (JIRA)" <ji...@apache.org> on 2015/04/02 07:38:53 UTC
[jira] [Comment Edited] (MAHOUT-1539) Implement affinity matrix
computation in Mahout DSL
[ https://issues.apache.org/jira/browse/MAHOUT-1539?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14392179#comment-14392179 ]
Saikat Kanjilal edited comment on MAHOUT-1539 at 4/2/15 5:38 AM:
-----------------------------------------------------------------
Enough with high level concepts already :), so I took the next logical step:
I'm not ready to include my code into the mahout master repo yet, so I created my own repo and started a sample implementation there, you will see a first cut of LocalitySensitiveHashing implemented using Euclidean Distance only, code is at least compiling as a first step:
https://github.com/skanjila/AffinityMatrix
TBD
1) Implement unit and potentially integration tests to test performance of this
2) Once LSH is all the way tested I will then implement the affinityMatrix piece on top of this
3) I will then add some more unit tests for Affinitymatrix
4) I will then add CosineDistance and ManhattanDistance as configurable parameters
5) I will need to incorporate into spark API specifically invoking the SparkContext and using the broadcast mechanisms in the spark clusters as appropriate
6) I will merge this into my mahout checkout out branch
Some early feedback on the code would be greatly appreciated, watch for changes in my repo coming frequently
was (Author: kanjilal):
Enough with high level concepts already :), so I took the next logical step:
I'm not ready to include my code into the mahout master repo yet, so I created my own repo and started a sample implementation there, you will see a first cut of LocalitySensitiveHashing implemented using Euclidean Distance only, code is at least compiling as a first step:
https://github.com/skanjila/AffinityMatrix
TBD
1) Implement unit and potentially integration tests to test performance of this
2) Once LSH is all the way tested I will then implement the affinityMatrix piece on top of this
3) I will then add some more unit tests for Affinitymatrix
4) I will then add CosineDistance and ManhattanDistance as configurable parameters
5) I will need to incorporate into spark API specifically invoking the SparkContext and using the broadcast mechanisms in the spark clusters as appropriate
5) I will merge this into my mahout checkout out branch
Some early feedback on the code would be greatly appreciated, watch for changes in my repo coming frequently
> Implement affinity matrix computation in Mahout DSL
> ---------------------------------------------------
>
> Key: MAHOUT-1539
> URL: https://issues.apache.org/jira/browse/MAHOUT-1539
> Project: Mahout
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 0.9
> Reporter: Shannon Quinn
> Assignee: Shannon Quinn
> Labels: DSL, scala, spark
> Fix For: 0.10.1
>
> Attachments: ComputeAffinities.scala
>
>
> This has the same goal as MAHOUT-1506, but rather than code the pairwise computations in MapReduce, this will be done in the Mahout DSL.
> An orthogonal issue is the format of the raw input (vectors, text, images, SequenceFiles), and how the user specifies the distance equation and any associated parameters.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)