Cloud-Based Spam Detection System using ETL Workflow with AWS EMR and TF-IDF Counting

Project information

Developed a robust spam detection system on AWS using an ETL workflow with an EMR cluster (PySpark, Hive, Pig) for efficient data processing. Implemented TF-IDF counting for spam and ham classification. Utilized S3 for data storage, CloudWatch for monitoring, and Cloud9 as the collaborative IDE. Achieved streamlined and accurate classification of spam and ham accounts.

58 Commits
1 Branch
0 Tags

README

Created on

November 12, 2023

Copy SSH clone URLgit@gitlab.computing.dcu.ie:sudames2/shree_sudame_ca675_assignment.git
Copy HTTPS clone URLhttps://gitlab.computing.dcu.ie/sudames2/shree_sudame_ca675_assignment.git