mahout-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Divya" <di...@k2associates.com.sg>
Subject RE: multilabel classification-Cbayes
Date Wed, 08 Dec 2010 09:33:30 GMT
Hi,

Train input files 2 wikipedia chunks of 1 MB each.
Test input file is one Wikipedia chunk of 1 MB.

I have passed -type cbayes argument for trainclassifier it gave me the result and I could
see the generated model.
File name                        								Size 
--------------------------------------------                              ------------------------------------
   
wiki-sub_model_cbayes\trainer-tfIdf\trainer-tfIdf\part-00000                    110KB
wiki-sub_model_cbayes\trainer-thetaNormalizer\part-00000                        1KB
wiki-sub_model_cbayes\trainer-weights\Sigma_j\part-00000                        81KB
wiki-sub_model_cbayes\trainer-weights\Sigma_k\part-00000                         1KB
wiki-sub_model_cbayes\trainer-weights\Sigma_kSigma_j\part-00000                  1KB


But when I cbayes argument for testclassifier I have got null pointer exception .

$ bin/mahout testclassifier -m examples/bin/work/wikipedia/wikipediaClassification/wiki_sub_model_cbayes
-d examples/bin/work/wikipedi
a/wikipediaClassification/train-subject -type cbayes
Running on hadoop, using HADOOP_HOME=C:\cygwin\home\Divya\hadoop-0.20.2
HADOOP_CONF_DIR=C:\cygwin\home\Divya\hadoop-0.20.2\conf
10/12/08 16:39:22 INFO bayes.TestClassifier: Loading model from: {basePath=examples/bin/work/wikipedia/wikipediaClassification/wiki_sub
_model_cbayes, classifierType=bayes, alpha_i=1.0, dataSource=hdfs, gramSize=1, verbose=false,
encoding=UTF-8, defaultCat=unknown, testD
irPath=examples/bin/work/wikipedia/wikipediaClassification/train-subject}
10/12/08 16:39:22 INFO bayes.TestClassifier: Testing Bayes Classifier
Exception in thread "main" java.lang.NullPointerException
        at org.apache.mahout.classifier.ConfusionMatrix.getCount(ConfusionMatrix.java:102)
        at org.apache.mahout.classifier.ConfusionMatrix.incrementCount(ConfusionMatrix.java:118)
        at org.apache.mahout.classifier.ConfusionMatrix.incrementCount(ConfusionMatrix.java:122)
        at org.apache.mahout.classifier.ConfusionMatrix.addInstance(ConfusionMatrix.java:90)
        at org.apache.mahout.classifier.ResultAnalyzer.addInstance(ResultAnalyzer.java:68)
        at org.apache.mahout.classifier.bayes.TestClassifier.classifySequential(TestClassifier.java:266)
        at org.apache.mahout.classifier.bayes.TestClassifier.main(TestClassifier.java:186)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
        at java.lang.reflect.Method.invoke(Method.java:597)
        at org.apache.hadoop.util.ProgramDriver$ProgramDescription.invoke(ProgramDriver.java:68)
        at org.apache.hadoop.util.ProgramDriver.driver(ProgramDriver.java:139)
        at org.apache.mahout.driver.MahoutDriver.main(MahoutDriver.java:184)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
        at java.lang.reflect.Method.invoke(Method.java:597)
        at org.apache.hadoop.util.RunJar.main(RunJar.java:156)


Regards,
Divya 

-----Original Message-----
From: Robin Anil [mailto:robin.anil@gmail.com] 
Sent: Wednesday, December 08, 2010 3:08 PM
To: user@mahout.apache.org
Subject: Re: multilabel classification

Complementary Bayes classifier is perfect for multi-label classification

On Wed, Dec 8, 2010 at 12:15 PM, David Hagar <david@occamlaw.com> wrote:

> Hi all,
>
> I'm looking at a multilabel classification problem -- I saw there was
> some talk on the mailing list last year of adapting the mahout LDA
> code to L-LDA for multilabel classification.
>
> Does anyone know if progress has been made on this front? Or are there
> other algorithms within mahout useful for this task?
>
> Thanks,
> David
>


Mime
View raw message