Coursera mod 3

For this project I built a simple spam-vs-ham email classifier using the SpamAssassin public corpus. I walk through how I loaded the raw email files, cleaned the text, created a term–document representation, trained a model, and evaluated how well it separates spam from legitimate (ham) email. This was my first hands-on experience with document classification, so I also include a short reflection on what I learned and the questions it raised for me about how spam filters work in the real world.

Proyecto Final Estadistica Inferencial

Universidad de La Salle Actividad en el marco de la materia de ciencia de datos.