Search code examples
machine-learningmahout

Preprocessing on mahout classifier training data


I am training mahout classifier.Do i need to do stemming,lower casing and stop word removal on my training data or mahout will take care of this as a part of training process. Below command i am using for training.

$MAHOUT_HOME/bin/mahout trainclassifier -i category-training-data -o category-bayes-model -type bayes -ng 1 -source hdfs

Solution

  • It does no preprocessing of that kind, no.