TODO: Out of bag error

[CorySimon]

It would be awesome if we could compute the out of bag error in the process of training the random forest. We can naturally do a sort of cross validation in random forests by testing on the data that we leave out in the process of training each tree through bagging.

[CorySimon]

I will try to implement this. I just can't figure out how to perform TWO reductions inside a parallel for loop so that we can compute the out of bag error... http://stackoverflow.com/questions/28803782/julia-parallel-for-loop-with-two-reductions

[bensadeghi]

This sounds like a great idea, and let's thank Iain for sorting out the reduction scheme. Unfortunately I don't have much free time right now, but feel free to implement the OOB error metric yourself, without breaking the API. Thanks