Statistical break down of words by morpheme, tested on English, French, Turkish, Zulu and Swahili
main.py runs a user-interface
use option 1 to see results based on different language's pre-defined datasets
choice are : Turkish, Zulu, Swahili, English
option 2 gets its dataset from wikipedia articles, but the current analyzation methods are too naive to accomodate this much data in a reasonable runtime... stick to option 1 for now