There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Repository Details
Language: Python Created a naive Bayes text classifier (nblearn.py, nbclassify.py) and compared accuracy with two popular machine learning toolkits. Worked with two datasets (emails and IMDB reviews) and performed binary classification: SPAM or HAM (not spam), and POSITIVE or NEGATIVE (sentiment analysis). Compared three machine learning techniques for making these classifications: naive Bayes classification, maximum entropy modeling, and support vector machines (MegaM and SVM-Light). report.txt - contains detailed instructions about the sequence of scripts to run and what cmd arguments to pass each python script.
