You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Andrew Palumbo (JIRA)" <ji...@apache.org> on 2015/04/02 20:03:53 UTC

[jira] [Comment Edited] (MAHOUT-1635) Getting an exception when I provide classification labels manually for Naive Bayes

    [ https://issues.apache.org/jira/browse/MAHOUT-1635?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14393048#comment-14393048 ] 

Andrew Palumbo edited comment on MAHOUT-1635 at 4/2/15 6:03 PM:
----------------------------------------------------------------

I'm leaning towards removing this option and making the extract label option the default.  I'm not sure that it really makes alot of sense or if it was ever fully implemented in the 0.6 to 0.7 move.  mahout trainnb requires <Text, VectorWritable> input. if a user wants to supply numbered categories they can simply add forward slashes around the keys as is the current convention. eg: /0/, /1/, etc.  

I'll look more closely at it.
     


was (Author: andrew_palumbo):
I'm leaning towards removing this option.  I'm not sure that it really makes alot of sense or if it was ever fully implemented in the 0.6 to 0.7 move.  mahout trainnb requires <Text, VectorWritable> input. if a user wants to supply numbered categories they can simply add forward slashes as is the convention.

I'll look more closely at it.
     

> Getting an exception when I provide classification labels manually for Naive Bayes
> ----------------------------------------------------------------------------------
>
>                 Key: MAHOUT-1635
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-1635
>             Project: Mahout
>          Issue Type: Bug
>          Components: Classification
>    Affects Versions: 0.9
>            Reporter: Suman Somasundar
>            Assignee: Andrew Palumbo
>              Labels: legacy
>             Fix For: 0.10.0
>
>         Attachments: zip_1
>
>
> If I let the Naive Bayes program itself extract the classification labels, the program runs fine. But, I get the following error when I provide the classification labels for the dataset manually.
> Error: java.lang.IllegalArgumentException: Wrong numLabels: 0. Must be > 0!
>         at com.google.common.base.Preconditions.checkArgument(Preconditions.java:88)
>         at org.apache.mahout.classifier.naivebayes.training.WeightsMapper.setup(WeightsMapper.java:45)
>         at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142)
>         at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:784)
>         at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341)
>         at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:169)
>         at java.security.AccessController.doPrivileged(Native Method)
>         at javax.security.auth.Subject.doAs(Subject.java:415)
>         at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1640)
>         at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:164)



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