Write a Python program that will build a feature vector dataset according
to the empirical kernel map. Use the blast_like_alignment.py code on
the website for similarity scores and the reference link for reference
proteins. Your program will take the same input as formatdata.py except
that it will use the empirical kernel map instead of the mismatch kernel.

Once this is done then modify run_on_all_data.py to run nearest means,
naive bayes, and linear SVM for each training/test pair.

Submit your assignment by copying it into the directory
/afs/cad/courses/bnfo/f18/bnfo/615/001/<ucid>
For example if your ucid is abc12 then copy your solution into 
/afs/cad/courses/bnfo/f18/bnfo/615/001/abc12

Submit a hardcopy in class as well.

Your completed assignment is due on November 20th 2018