You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Dmitriy Lyubimov (JIRA)" <ji...@apache.org> on 2015/06/24 19:31:04 UTC

[jira] [Commented] (MAHOUT-1754) Distance and squared distance matrix routines

    [ https://issues.apache.org/jira/browse/MAHOUT-1754?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14599786#comment-14599786 ] 

Dmitriy Lyubimov commented on MAHOUT-1754:
------------------------------------------

part of a cumulative patch in https://github.com/apache/mahout/pull/145

(asfgit can't broadcast on multiple issues in same PR)

> Distance and squared distance matrix routines
> ---------------------------------------------
>
>                 Key: MAHOUT-1754
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-1754
>             Project: Mahout
>          Issue Type: Blog - New Blog Request
>            Reporter: Dmitriy Lyubimov
>            Assignee: Dmitriy Lyubimov
>             Fix For: 0.10.2
>
>
> R analogs: dist()
> this issue suggests to provide routine for distance and squared distance matrix computation. 
> Since most of the use actually requires or can use square distance routine, we suggest to provide both squared and non-squared eucledian distance matrices. 
> By convention, distributed versions are prepended by (d) letter:
> dist(x)
> sqDist(x)
> dsqDist
> The points are assumed to be row-wise. 
> We also provide variation for pair-wise distance matrix of two different inputs x and y: 
> sqDist(x,y)
> dsqDist(x,y).



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)