Search code examples
machine-learningmahoutbayesian

What does '-c' parameter do in Mahout trainnb commant?

I cannot understand for what -c parameter stands for in this Mahout command, when I am training Naive Bayes model:

mahout trainnb -i train-vectors -el -li labelindex -o model -ow -c

Does it turn on Complementary naive Bayes algorithm ?

If no, is there any possibility to use it while I am training a model ?

Solution

  • From TrainNaiveBayesJob.java you can see that indeed, it is used to control the use of complementary naive Bayes algorithm, that is disabled by default.