mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Divya" <di...@k2associates.com.sg>
Subject classification example doubts
Date Fri, 19 Nov 2010 06:52:02 GMT
Hi,

 

I have few questions regarding classification in Mahout 

May be my questions would look silly ..

As I am new bee to Mahout and trying to understand the logic .

 

I am following https://cwiki.apache.org/MAHOUT/twenty-newsgroups.html for
classification.

 

1)      I want to  know what should go in "bayes-test-input".

 

As when I extract the 20news-bydate.tar.gz I get only 20news-bydate-test and
20news-bydate-train.

 

As per steps 20news-bydate-train  we generate input dataset  and that output
we use as input to train the  classifier.

 

2)      If we take Wikipedia example
https://cwiki.apache.org/MAHOUT/wikipedia-bayes-example.html

 

To  trainclassifier We have used Wikipediainput to generate model .

To test classifier again we used wikipediamodel as input and Wikipedia input
as test documents directory.

I didn't understand why are we doing so ?

 

3)      Last thing I want to know that when we use run testclassifier using
command line we can see the output.

How can we make use of this output?

 

 

Thanks in advance

Regards,

Divya 

 

 

 


Mime
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message