Data Analytics pipeline using Apache Spark | Build multi-class classification models | Test the model using test data and compute accuracy of each method

Football shots visualization and player prices prediction. Built with Spark for distributed computation and Streamlit for the frontend

Big Data Analysis of Amazon Toys & Games Reviews using PySpark, Hive & MLlib

This project builds a parallel ML app to predict wine quality using Apache Spark's MLlib on AWS. It involves training on 4 EC2 instances, validating and optimizing the model, and testing its F1 score. The app is packaged in Docker for deployment, showcasing Spark's scalability and AWS's distributed computing power.

An Image classification approach using BigData (spark) machine learning and data manipulation libraries.