DATA 311 - Lab 7: PCA and Clustering

Introduction

In this lab, you’ll use unsupervised machine learning techniques to shed light on the properties of feature extractors commonly used in computer vision.

Collaboration Policy

You are required to complete this lab in pairs. Pairs are assigned randomly, and can be found in the Lab 7 Groups groupset on Canvas. I highly recommend collaborating synchronously, as each partner will be responsible for understanding (and being able to independently explain) every aspect of your submission. As a reminder, here’s the collaboration policy for labs done in pairs from the syllabus:

For labs done in pairs, any and all collaboration is permissible between members of the same pair. That said, both members must understand and be able to explain in detail all aspects of their submission. For this reason, “pair programming” is highly recommended - you should not split the tasks up for each group member complete independently. I reserve the right to meet with any student one-on-one and ask them to explain any part of their submission to me in detail.Getting Started

Getting Started

This lab has a starter notebook; start by downloading lab7.ipynb and uploading it to Colab to begin working.

The starter notebook contains background and specifics for your tasks. Read the notebook carefully: the harder part of this lab is probably figuring out what I’m asking you to do, not actually doing it.

I strongly recommend reading through the notebooks for both parts and consulting the TA during lab time to make sure you understand the tasks. If you’re stuck, ask questions early and often.

Submitting your work

Please make sure you have results for all parts; I’ve put “TODO” in the notebook in each place you need to do some work. Make sure that all your cells have been run and have the output you intended, then download a copy of the notebook in .ipynb format and submit that file on Canvas.

Survey

Finally, fill out the Week 7 Survey on Canvas (both group members). Your submission will not be considered complete until both group members have submitted the survey.

Rubric

Part 1 is worth 20 points:

• 1.1 - PCA Scatterplots
  • 4 points: correctness
  • 2 points: visualization quality
• 1.2 - Short answer question
  • 4 points: correctness and clarity of justification
• 1.3 - Plots of explained variance
  • 4 points: correctness
  • 2 points: visualization quality
• 1.4 - Intrinsic dimensionality estimates
  • 4 points: correctness

Part 2 is worth 15 points:

• 2.1 - Confusion matrix calculation
  • 5 points - correctness
• 2.2 - Confusion matrix production
  • 4 points - correctness
• 2.3 - Plot of classification accuracy
  • 4 points - correctness
  • 2 points - visualizatoin quality