[jira] [Created] (MAHOUT-1698) Streaming K-means and Fuzzy K-means to output clusteredPoints

[Sujit Thumma (JIRA)]

Sujit Thumma created MAHOUT-1698:
------------------------------------

Summary: Streaming K-means and Fuzzy K-means to output clusteredPoints
Key: MAHOUT-1698
URL: https://issues.apache.org/jira/browse/MAHOUT-1698
Project: Mahout
Issue Type: Improvement
Components: Clustering
Affects Versions: 0.10.0
Reporter: Sujit Thumma
Priority: Critical


Similar to K-Means algorithm is there a way streaming K-means and Fuzzy K-means output clustered points in map-reduce? This can be useful to map document with cluster ID. As of now only K-means can output clustered points and streaming k-means just outputs centroids.



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

[Dmitriy Lyubimov (JIRA)]

[ https://issues.apache.org/jira/browse/MAHOUT-1698?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Dmitriy Lyubimov updated MAHOUT-1698:
-------------------------------------
Assignee: Suneel Marthi

Post by Sujit Thumma (JIRA)
Streaming K-means and Fuzzy K-means to output clusteredPoints
-------------------------------------------------------------
Key: MAHOUT-1698
URL: https://issues.apache.org/jira/browse/MAHOUT-1698
Project: Mahout
Issue Type: Improvement
Components: Clustering
Affects Versions: 0.10.0
Reporter: Sujit Thumma
Assignee: Suneel Marthi
Priority: Critical
Similar to K-Means algorithm is there a way streaming K-means and Fuzzy K-means output clustered points in map-reduce? This can be useful to map document with cluster ID. As of now only K-means can output clustered points and streaming k-means just outputs centroids.

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

[Eric Lopes (JIRA)]

[ https://issues.apache.org/jira/browse/MAHOUT-1698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15023224#comment-15023224 ]

Eric Lopes commented on MAHOUT-1698:
------------------------------------

Hi, there. For Fuzzy K-Means, doens't enabling "runClustering" solve the problem?
As described here:
https://mahout.apache.org/users/clustering/fuzzy-k-means.html

"After running the algorithm, the output directory will contain: ...
clusteredPoints: (if runClustering enabled) a directory containing SequenceFile(IntWritable, WeightedVectorWritable)
..."

Eol.

Post by Sujit Thumma (JIRA)
Streaming K-means and Fuzzy K-means to output clusteredPoints
-------------------------------------------------------------
Key: MAHOUT-1698
URL: https://issues.apache.org/jira/browse/MAHOUT-1698
Project: Mahout
Issue Type: Improvement
Components: Clustering
Affects Versions: 0.10.0
Reporter: Sujit Thumma
Assignee: Suneel Marthi
Priority: Critical
Similar to K-Means algorithm is there a way streaming K-means and Fuzzy K-means output clustered points in map-reduce? This can be useful to map document with cluster ID. As of now only K-means can output clustered points and streaming k-means just outputs centroids.

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

[Suneel Marthi (JIRA)]

[ https://issues.apache.org/jira/browse/MAHOUT-1698?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Suneel Marthi updated MAHOUT-1698:
----------------------------------
Priority: Major (was: Critical)

Post by Sujit Thumma (JIRA)
Streaming K-means and Fuzzy K-means to output clusteredPoints
-------------------------------------------------------------
Key: MAHOUT-1698
URL: https://issues.apache.org/jira/browse/MAHOUT-1698
Project: Mahout
Issue Type: Improvement
Components: Clustering
Affects Versions: 0.10.0
Reporter: Sujit Thumma
Assignee: Suneel Marthi
Similar to K-Means algorithm is there a way streaming K-means and Fuzzy K-means output clustered points in map-reduce? This can be useful to map document with cluster ID. As of now only K-means can output clustered points and streaming k-means just outputs centroids.

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

[Suneel Marthi (JIRA)]

[ https://issues.apache.org/jira/browse/MAHOUT-1698?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Suneel Marthi resolved MAHOUT-1698.
-----------------------------------
Resolution: Won't Fix
Fix Version/s: 0.13.0

Post by Sujit Thumma (JIRA)
Streaming K-means and Fuzzy K-means to output clusteredPoints
-------------------------------------------------------------
Key: MAHOUT-1698
URL: https://issues.apache.org/jira/browse/MAHOUT-1698
Project: Mahout
Issue Type: Improvement
Components: Clustering
Affects Versions: 0.10.0
Reporter: Sujit Thumma
Assignee: Suneel Marthi
Fix For: 0.13.0
Similar to K-Means algorithm is there a way streaming K-means and Fuzzy K-means output clustered points in map-reduce? This can be useful to map document with cluster ID. As of now only K-means can output clustered points and streaming k-means just outputs centroids.

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

[Suneel Marthi (JIRA)]

[ https://issues.apache.org/jira/browse/MAHOUT-1698?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15306002#comment-15306002 ]

Suneel Marthi commented on MAHOUT-1698:
---------------------------------------

Resolving this as 'Won't Fix', since this is legacy MapReduce code. If u have a patch please feel free to create a new jira and submit a PR.

Post by Sujit Thumma (JIRA)
Streaming K-means and Fuzzy K-means to output clusteredPoints
-------------------------------------------------------------
Key: MAHOUT-1698
URL: https://issues.apache.org/jira/browse/MAHOUT-1698
Project: Mahout
Issue Type: Improvement
Components: Clustering
Affects Versions: 0.10.0
Reporter: Sujit Thumma
Assignee: Suneel Marthi
Fix For: 0.13.0
Similar to K-Means algorithm is there a way streaming K-means and Fuzzy K-means output clustered points in map-reduce? This can be useful to map document with cluster ID. As of now only K-means can output clustered points and streaming k-means just outputs centroids.

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