This project is an email classifier that uses k-NN statistical analysis to classify emails as spam or ham. It uses the Parallel Java 2 library to run the analysis in parallel thus increasing throughput. The dataset used is the enron email dataset which contains 0.5 million email records.

1. src : Contains the source files
2. sampleFiles: Contains sample files that can be used to run the program.
3. dataFiles: Contains data files used to train and test the system.
4. scripts: Contains python scripts used to clean the data files.
5. Report.pdf: Contains the report of the entire project along with conclusions, results and how to install and run the system.

Parallel Java 2 Library

Detailed installation and running guide can be found in the Report.pdf file.

• Cliffton Fernandes (https://github.com/cliffton)
• Nikhil Keswaney (https://github.com/nikhilkeswaney)