[jira] [Resolved] (MAHOUT-1094) when i am giving the testing data from the new set of data without using split ..it is giving the completely wrong confusion matrix

["Robin Anil (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/MAHOUT-1094?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Robin Anil resolved MAHOUT-1094.
--------------------------------

    Resolution: Cannot Reproduce

There is nothing in the bug with which we can reproduce the problem. The dataset or the full log or what the wrong-ness in the confusion matrix is.
                
> when i am giving the testing data from the new set of data without using split ..it is giving the completely wrong confusion matrix
> -----------------------------------------------------------------------------------------------------------------------------------
>
>                 Key: MAHOUT-1094
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-1094
>             Project: Mahout
>          Issue Type: Question
>          Components: Classification
>    Affects Versions: 0.7
>         Environment: hadoop 0.20
>            Reporter: Priyadarshan raj
>              Labels: newbie
>   Original Estimate: 336h
>  Remaining Estimate: 336h
>
> hi,
> i am able to successfully create  a model by the command below:-
> bin/mahout trainnb -i /user/cloudera/MahoutWeighted/1_FactWt-train-vectors -el -o /user/cloudera/MahoutWeighted/model -li /user/cloudera/MahoutWeighted/labelindex -ow
> ....
> but  i am unable to use that model...when i am feeding the model with test data in the same way,i trained it..i am not able to get the correct confusion matrix.and the number of map output records coming is equal to the number of files i am feeding .can anyone tell me why it is not coming to be number of lines ??

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira