implemented concentration measure and took the top 50, 100, 150, 200 words from each category and combined them into files

keras implemented, install tensorflow and keras (probably in a virtual environment, you can read that from the page) and run classifier.py; commented out printing in arr_to_class function of pandas_stuff.py

created simple classes to help along the way, including a very basic ML pipeline to feed preprocessed postings into to see if whatever preprocessing we do works