Archived · Spring 2023

DS 400 Data Science Capstone

All offerings: Spring 2023Fall 2024Spring 2025 Current course page →
This is the course website as it was published for Spring 2023. Dates, links and policies reflect that semester and may be out of date; see the current course page for the latest version.

Course Info

An advanced research course for Computer Science majors and a prerequisite for Honors in the Discipline.

Instructor:

  • Dr. Peilong Li

Office:

  • Esbenshade 284B

Appointments:

  • By email

Number of Credits

  • 4

Pre-requisites

  • DS 300 - Data Mining
  • DS 315 - Statistical Learning

Course Overview

Course Coverage

This course is a directed project or study requiring faculty acceptance of a proposal with a final report and defense of work. It is intended as an advanced research course for Data Science.

Under the supervision of a faculty mentor, students use their knowledge of data science to complete a high level project contributing to research in an academic area or to solve a problem for a local business. Projects will involve data collection, data cleaning, data analysis, and reporting results both orally and in writing to a domain expert or business leader. All problems are unstructured with no predetermined solution.

Student Learning Outcomes

By the end of the course, students will be able to:

  • Apply knowledge of data science appropriate to the discipline, including advanced skills like big data parallel processing and neural networks
  • Analyze a problem and identify and define the data analytical requirements and procedure appropriate to its solution
  • Design and implement a computer-based system, process, component or program, to address an open data problem (including open data competitions hosted on Kaggle)
  • Communicate effectively with a broad range of audiences
  • Engage in continuing professional development

Course Schedule

Note this tentative schedule is subject to change. Please check the schedule regularly. Last Updated: 01/17/2023

Week Activities Notes
1 Literature search, Finalize topic with instructor Mon: Start proposal
2 Proposal write-up Mon: create Github repository
3 Data collection and preprocessing Mon: Github commit 1
4 Exploratory data analysis Mon: Start Milestone 1, Proposal Due
5 Start model design Mon: Github commit 2
6 Feature extraction Mon: Github commit 3
7 Model implementation Mon: Start Milestone 2, Milestone 1 Due
8 Spring break, no classes
9 Model implementation and training Mon: Github commit 4
10 Parameter tuning Mon: Github commit 5
11 Application design and use cases Mon: Start Milestone 3, Milestone 2 Due, mid-term demo during the week
12 Model evaluation and comparison Mon: Github commit 6
13 Code final revision Mon: Github commit 7
14 Final paper writeup Mon: Start final paper, Milestone 3 Due
15 Final presentation Tue: Present on SCAD Day
16 Code cleanup, packaging, and publishing Mon: Github commit 8
17 Revise the project with instructor feedback Mon: Final paper and code Due

Grading Policies

Grading Weights

The final grade for this course depends upon the grades and scores earned on course components weighted as follows:

  • 20%: Project proposal
  • 10%: Milestone 1
  • 10%: Milestone 2
  • 10%: Milestone 3
  • 30%: Final project
  • 20%: Final paper

Grades will be computed by rounding numerical percentages to the nearest integer and applying the following table:

Letter Range Letter Range Letter Range
A 93-100 B- 80-82 D+ 67-69
A- 90-92 C+ 77-79 D 63-66
B+ 87-89 C 73-76 D- 60-62
B 83-86 C- 70-72 F 0-59

Grades for the proposal, milestones, final project, and final paper will be recorded in Canvas (https://etown.instructure.com/). Students may compute their current average by using these scores with the weights listed above.

Proposal

All work is individual in this course. Each student, working with the instructor, will formulate the outline of a project. The plan for this project including goals should be written up and presented as a formal proposal due on the date specified in the course schedule. It should be turned in as a Word, LaTex, or PDF file and uploaded into Canvas before 11:59pm on the due day.

Milestones

After the project has been proposed and approved, each student will have to present a document and give an oral presentation for each of three milestones. The document should be turned in as a Word, LaTeX, or PDF file. This document should be included in a zip file that also contains appropriate code. This zip file should be uploaded into Canvas before 11:59pm on the due date.

Milestone Content
1 Dataset collection, preprocessing, and exploratory data analysis
Models to be implemented and results to be presented
Expected timeline
2 Continued exploratory data analysis with visuals for demo
Feature study and feature extraction
Model implementation and scoring
Parameter tuning to obtain optimal model performance
3 Final application design with detailed use cases
Models comparison within the project and with literatures
Future works

Final Project and Paper

A working version of the source code will be submitted by compressing it in a zip file and uploading that file onto Canvas before 11:59pm on the final project due date. Likewise, a paper of at least 8 pages (2,000 words) describing the purpose of the project, previous work done in the area, implementation details, successes, failures, and potential future work should be submitted. It should be turned in as a Word, LaTex, or PDF file and uploaded into Canvas before 11:59pm on the final project due date.

Policy Statements

Course Schedule

The most up-to-date course schedule will be posted on course website schedule page: https://peilong.github.io/courses/ds400/schedule/. Students are responsible for checking the schedule regularly. Schedule page will include: 1) teaching topics for each meeting; 2) reading assignments for each week and 3) special notes on specific days.

Course Announcements & Discussion

All course announcements will be sent to your E-Town email accounts via Canvas Announcements. You are responsible for signing up for this service and checking your emails regularly.

I have created a Microsoft Teams channel (link) to facilitate course related discussion. Discussions are encouraged to be posted on the “QA” channel from Teams. Private instant messages can be sent directly to your recipient by search your recipient’s name on the “search” bar.

Attendance Policies

Attendance is expected of every student at every meeting. Students should come to meetings prepared to explain their progress and discuss appropriate technical issues.

Statement on School Closure

In the event that classes do not meet because Elizabethtown College is closed or delayed due to inclement weather or some other emergency, the slides that would have been covered during the missed classes will be posted through Canvas. Students are expected to do the assigned reading, review the slides, and e-mail the instructor with any questions. There will also be an opportunity to ask questions about the material when classes resume.

If a scheduled exam or lab is missed, it will normally be made up on the day that classes resume. If the College is closed on a day when a project is due, the project due date will also normally be extended until the day when classes resume. If circumstances render either of these makeup policies unreasonable, the instructor will send an e-mail explaining an alternative makeup opportunity to each student’s Elizabethtown e-mail account.

Statement on Plagiarism

Check out the up-to-date statement from: Elizabethtown College Catalog, “Academic Judicial System”

Statement on Disability

Full statement can be found at: Course Syllabus on Disability Services, Religious Observances, and COVID related expectations.

Diversity and Inclusivity Statement

I consider this classroom to be a place where you will be treated with respect, and I welcome individuals of all ages, backgrounds, beliefs, ethnicities, genders, gender identities, gender expressions, national origins, religious affiliations, sexual orientations, ability - and other visible and non-visible differences. All members of this class are expected to contribute to a respectful, welcoming and inclusive environment for every other member of the class.

Proposal Requirements

Specifications

For details, please refer to Proposal Requirements.

Archived from Peilong/Peilong.github.io@d41e5ca (2023-01-16).