Overview

Important dates

• Proposal due Tuesday, October 20
• Exploration due Tuesday, November 3
• Draft product due Thursday, November 19
• Peer review due Friday, November 20
• Final report + product + reproducibility due on Thursday, December 3
• Oral examination on Friday, December 4

Important

The details will be updated as the project date approaches.

Introduction

TL;DR: Create something related to data science.

This is intentionally vague – part of the challenge is to design a project that showcases best your interests and strengths.

One requirement is that your project should feature some element that you had to learn on your own. This could be a package you use that we didn’t teach in class (e.g., a package for building interactive web applications) or a workflow (e.g., making a package) or anything else.

If you’re not sure if your “new” thing counts, just ask!

Ideas

Identify a goal for your project that leverages the skills you develop in this class. Some possible ideas include:

• Develop educational content introducing and presenting a technical topic from statistics or mathematics (e.g. gradient descent, neural networks, decision trees) and publish as a Quarto website
• Create online tutorials for a specific R package or data science technique using Web Assembly and Quarto Live
• Build a Shiny web application for visualizing and exploring a complex dataset
• Create an R package that provides enhanced functionality for {ggplot2}
• Build an R package to provide a straightforward interface to an API
• Analyze a corpus of text data and use generative AI to assist with document labeling
• Develop a machine learning model and deploy it as an API using {plumber}

Most importantly, be prepared to brainstorm a bunch of ideas and discard them until you settle on a topic that makes you happy and feels like a good choice for showcasing what you’ve learned in the class and how you can use that to learn something new and implement for your project.

The project is very open ended. Neatness, coherency, and clarity will count. All computation must be done using R, and all components of the project must be reproducible.

Deliverables

The four primary deliverables for the final project are

1. A project proposal with three ideas.
2. A reproducible product in a format based upon the type of project you propose (e.g. R package, interactive web application, custom-built API), with one required draft along the way.
3. A final report that explains the process and results.
4. An oral examination.

There will be additional submissions throughout the semester to facilitate completion of the project.

Overall grading

The grade breakdown is as follows:

Total	220 pts
Project proposal	10 pts
Exploration	15 pts
Draft	10 pts
Peer review	5 pts
Final report	20 pts
Final product(s)	80 pts
Oral examination	60 pts
Reproducibility + organization	10 pts
Code style	10 pts

Late work policy

There is no late work accepted on this project. Be sure to turn in your work early to avoid any technological mishaps.