NLP program that analyses College Humor's gross words list and generates new ones!
Naggelderp was a funny word once generated by this program.
make
#or
python main.py To run specific modes:
make analysis
make generate
#or
python main.py analysis
python main.py generate Upon running "analysis," you should expect 3 lists of 10 iteams each. These are 1grams, 2grams, and 3grams. Really, these are the counts of letters (or groups of letters) that are most common in all the words in the video.
On some ngrams, the "<" represents the start of a word, and ">" represents the end of a word.
For "generate," you will see a random word that has been generated based on these analytics and some random factors.
Maybe create a webapp with flair and data viz.