The main methodology that was going into this tool was to provide it with a large enough sample set so
that the features that are found from the sample set and then applied to the classifier provided great
accuracy. Unfortunately, my script was not interacting well with the NLTK and I has unable to use their
functions to enhance accuracy of the classifier. Therefore, I had to change the way my classier was
going to be made and change how I wanted to format my sample set.