I did not do any conversion, correct. I followed this guide and the instructions for running the data on a hadoop cluster: http://cwiki.apache.org/confluence/display/MAHOUT/TwentyNewsgroups
I used the following command: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-0.4-SNAPSHOT.job org.apache.mahout.classifier.bayes.TrainClassifier -i 20news-input -o newsmodel -ng 3 -type bayes -source hdfs -- View this message in context: http://n3.nabble.com/Not-a-file-issue-with-TwentyNewsGroups-tp698023p708859.html Sent from the Mahout User List mailing list archive at Nabble.com.
