analyze.py runs naive bayes classification on the tags directory generated by the testng plugin modification. This is written from scratch and has an accuracy of 60% or so.
analyze2.py uses mlpy D. Albanese, R. Visintainer, S. Merler, S. Riccadonna, G. Jurman, C. Furlanello. mlpy: Machine Learning Python, 2012. arXiv:1202.6548 [bib], classification. It uses different machine learning models to make the predictions. This analyze2.py has a lot of dependencies: On GNU/Linux, OSX and FreeBSD you need the following requirements:
GCC
Python >= 2.6 or 3.X
NumPy >= 1.3.0 (with header files)
SciPy >= 0.7.0
GSL >= 1.11 (with header files)