Decision Forest predictions output format

[Prabhu Prakash Ganesh <pr...@mediaiqdigital.com>]

Hi all,

   I have a quick question. I am trying to build a decision forest using
Mahout’s partial implementation and then predict using that.

I run the command like this



$HADOOP_HOME/bin/hadoop jar …/mahout-examples-<version>-job.jar
org.apache.mahout.classifier.df.mapreduce.TestForest -i <test_data> -ds
<descriptor_file> -m ob -a -mr -o predictions



It works fine and outputs the confusion matrix in the log and creates a
folder called predictions in HDFS with a file called testing.out. Now can
someone please tell me what the format of this file is it doesn’t seem to
be a text file.

It seems to be a binary file, but not sure in what format. How do I read
this predictions output file?



Thanks

Prabhu

RE: Decision Forest predictions output format

[Prabhu Prakash Ganesh <pr...@mediaiqdigital.com>]

Sorry, could have figured this out myself. The output is in Sequence File
format



Thanks

Prabhu



*From:* Prabhu Prakash Ganesh [mailto:prabhu@mediaiqdigital.com]
*Sent:* 13 September 2013 18:07
*To:* user@mahout.apache.org
*Subject:* Decision Forest predictions output format



Hi all,

   I have a quick question. I am trying to build a decision forest using
Mahout’s partial implementation and then predict using that.

I run the command like this



$HADOOP_HOME/bin/hadoop jar …/mahout-examples-<version>-job.jar
org.apache.mahout.classifier.df.mapreduce.TestForest -i <test_data> -ds
<descriptor_file> -m ob -a -mr -o predictions



It works fine and outputs the confusion matrix in the log and creates a
folder called predictions in HDFS with a file called testing.out. Now can
someone please tell me what the format of this file is it doesn’t seem to
be a text file.

It seems to be a binary file, but not sure in what format. How do I read
this predictions output file?



Thanks

Prabhu