Testing Mahout Classification Module - RandomForest

[Sharath Chandra Guntuku <sh...@gmail.com>]

Hi,

We created a Random forest model using a training set. When we try to use
this model for predicting the class labels of a new test data, all the
output classes came as  -1 = unknown.

These are the commands we are using:

For training:

usr/bin/hadoop jar
~/Downloads/mahout-0.7-cdh4.2.0/mahout-core-0.7-cdh4.2.0-job.jar
org.apache.mahout.classifier.df.tools.Describe -p td/New_Mix_Mal.arff -f
testdata_conficker/temp.info -d 7 N L

For loading the test data:

/usr/bin/hadoop jar
~/Downloads/mahout-0.7-cdh4.2.0/mahout-examples-0.7-cdh4.2.0-job.jar
org.apache.mahout.classifier.df.mapreduce.BuildForest
-Dmapred.max.split.size=1874231 -d 23-04/features_complete.arff -ds
testdata_conficker/temp.info -sl 5 -p -t 100 -o 23-04_output_new

For starting the classifier:

/usr/bin/hadoop jar
~/Downloads/mahout-0.7-cdh4.2.0/mahout-examples-0.7-cdh4.2.0-job.jar
org.apache.mahout.classifier.df.mapreduce.TestForest -i
23-04/features_complete.arff -ds testdata_conficker/temp.info -m
23-04_output_new -a -mr -o 23-04_output_final

Could somebody tell where I am going wrong!

Thanks!
------------------------------------------------------------------------------
Regards,
*Sharath Chandra Guntuku*
Undergraduate Student (Final Year)
*Computer Science Department*
*Email*: f2009149@hyderabad.bits-pilani.ac.in

*BITS-Pilani*, Hyderabad Campus
Jawahar Nagar, Shameerpet, RR Dist,
Hyderabad - 500078, Andhra Pradesh