Graduate Project
Introduction
The graduate project is offered only to students enrolled in Data C200, CS C200A, or Data 200S. Other students are welcome to explore the questions and datasets in the project for personal learning, but their work will not be graded or counted towards their final grades.
The purpose of the project is to give students experience in both open-ended data science analysis and research in general.
Teamwork
You must work in groups of two or three students. In order to give everyone experience in collaborating on a data science project, individual projects are not allowed. Everyone in the same group will receive the same grade (except for exceptional circumstances).
Milestones and Grading Breakdown
| Milestones | Deadline (11:59 PM Pacific) | Event | Deliverables | Submission Link | Grading Weight |
|---|---|---|---|---|---|
| Milestone 1 | October 14 | Group Formation + Research Proposal | Project Proposal Form | Google Form | 5% |
| Milestone 2 | October 28 | EDA + Internal Peer Review 1 | EDA Write-Up + Notebook, Internal Peer Review 1 | EDA Gradescope Peer Review Gradescope |
10% |
| Milestone 3 | November 8 | Mandatory Check-In | One-Page Progress Report | Gradescope | 7.5% |
| Milestone 4 | November 22 | Internal Peer Review 2 | Second Internal Peer Review | Gradescope | 2% |
| Milestone 5 | December 2 | Project Report First Draft | Final Report Draft Write-Up + Notebook | Gradescope | 18% |
| Milestone 6 | December 6 | External Peer-Review | External Peer Review | OpenReview | 7.5% |
| Final Submission | December 13 | Final Project Report | Final Project Report + Presentation Video | Final Report Gradescope CV Predictions Gradescope NLP Predictions Gradescope |
50% |
For each milestone listed above, detailed expectations can be found in the “Milestone” section under each of the project topics (Computer Vision or Natural Language Processing) which is explained above. Please refer to these sections for specific requirements and guidelines related to your chosen project topic.
Late Policy
- No Extensions for Milestones: Must be submitted on time; no extensions are permitted. Milestones cannot be submitted late as they are crucial for the peer review process.
- Final Report and Presentation Video: Late submissions incur a 10% daily penalty, up to a maximum of two days. Submissions are rounded to the nearest day (e.g., 2 minutes late counts as 1 day late).
Accessing Datasets
All of the provided datasets can be found in the Datahub directory shared/course/data100-shared-readwrite/fa24_grad_project_data. You can access the data directly from Datahub. If you wish to work on the project locally, you can also download the files containing the datasets for each topic by right-clicking on the file in JupyterLab and select “Copy Download Link”. If you choose to train more complex models, DataHub might not have enough hardware resources or memory, in which case you can use Google Colab or your local machine. If you would like to use Google Colab, feel free to check out this link to get started.
Project Topics
Please choose one of the following projects (CV or NLP) and its associated datasets to work on. You will be expected to complete all (2) tasks provided for your chosen dataset. Click the below links to go to the project description pages.