Hi Suneel,
Thanks for the information. I converted the .sgm files to text files and
ran the seqdirectory job. However, I still get the exception
"java.lang.ClassNotFoundException:
org.apache.mahout.common.AbstractJob".
hadoop jar
/Users/rohitp/Desktop/rohitp/Downloads/mahout-distribution-0.9/maho
You need to first convert *.sgm from reuters download to text files (this
shuld happen before running seqdirectory).
To convert .sgm to text run - "$MAHOUT
org.apache.lucene.benchmark.utils.ExtractReuters ${WORK_DIR}/reuters-sgm
${WORK_DIR}/reuters-out"
Then run seqdirectory on the output of the
Hi All,
I am trying to run LDA from Mahout and as a first step I wanted to run the
"SequenceFilesFromDirectory" job to convert the text files into sequence
files. Following is the command I am using:
hadoop jar
/Users/rohitp/Desktop/rohitp/Downloads/mahout-distribution-0.9/mahout-examples-0.9-job