MovieLens with Spark
Recommendation models and distributed analysis of MovieLens ratings.
Overview
A practical study of recommendation and large-scale data analysis using the MovieLens dataset and Apache Spark. The notebooks cover data loading with RDDs and DataFrames, exploratory analysis, and a comparison of local and cluster execution.
Modeling exercises include alternating least squares, feature engineering, and a decision-tree model. The project brings together data processing, predictive modeling, and computing-system evaluation.