in this repo , i will try to publish a new machine learning model , with some documentation and mathematical proof for the model i am going to talk about
the file contains an implementaion of the spam filtering project using compression method .
the intuition for this method to work came from the fact that spam message are more closer to each other , so the case for the ham type .
so if you put all of the message of the ham in one file , and all the spam ones in another file , then if you add other message to the spam and the ham file then the message would compress more in the file that belongs to that message .