Applied Machine Learning and Data Engineering

This unit teaches practical applied machine learning techniques, model selection, and feature engineering using Python tools and libraries. Students will also learn data engineering and visualization practices — including handling dates, relational data, multiple data sources, scaling workflows, and setting up performant Python environments — to prepare reproducible analyses on real datasets.

Learning Objectives

• Analyze and compare clustering and classification algorithms (e.g., DBScan, Naïve Bayes, KNN, SVM, boosting) by measuring performance, assumptions, and suitability for specific problems
• Apply Python data-science libraries and tools to preprocess and integrate data from relational databases and multiple sources, handle date/time fields, and produce exploratory visualizations (including maps, labels, and annotations)
• Demonstrate techniques for scaling and accelerating data workflows — including chunked processing, parallel execution across cores, hardware acceleration, and environment setup (Anaconda) — to process large datasets efficiently
• Evaluate model quality by performing feature selection, hyperparameter tuning, and overfitting mitigation, and document reproducible experiments using provided datasets and example code