Skip to content

Week 2 - Cluster Analysis

Learning Objectives

After today's class, you should be able to:

  • Understand and apply cluster analysis techniques, including the k-Means algorithm, to segment data into a set of homogeneous clusters of records for the purpose of generating insight.
  • Create a new Conda environment and install required Python libraries.
  • Use GitHub Desktop (or Git) to clone a repository and download starter Jupyter notebooks for in class demos.
  • Develop and implement cluster analysis models in Python.
  • Apply the k-Means algorithm manually to a small dataset to understand how cluster assignments and centroid updates occur in each iteration.

Class Agenda

Task List

  • Optional Reading: Chapters 3-4 - Data Visualization and Dimension Reduction
  • Required Reading: Chapter 16 - Cluster Analysis
  • Complete and Submit CP1_Cluster_Analysis on Canvas.
  • Complete and Submit PA1_Wine_Customer_Segmentation on Canvas/Gradescope.

Additional Resources