Data Preparation, Visualization, and Modeling

This unit advances students’ practical skills in preparing, visualizing, and modeling data for data science workflows. Learners will validate and transform datasets, create features, apply dimensionality reduction and clustering, build and evaluate supervised models, and assemble secure, performant pipelines and environments.

Learning Objectives

• Validate and preprocess structured and unstructured datasets by applying data cleaning, categorical manipulation, array operations, and secure handling procedures to ensure data integrity for analysis
• Apply feature engineering and transformative functions, including scaling, encoding, time-series formatting, and dimensionality reduction (PCA/factor analysis) to produce informative inputs for models
• Demonstrate advanced visualization techniques—custom axes, ticks, grids, scatterplots, line styling, and time-series plots—to explore data patterns and communicate analytic findings
• Analyze and evaluate supervised and unsupervised models (hierarchical clustering, logistic and regularized linear models, random forests, k-NN approaches) using cross-validation, regularization, performance timing, and reproducible pipelines in an Anaconda environment