Practical Data Science 🛠️
EECS 398, Winter 2025 at the University of Michigan
4 credits • Open to all majors • ULCS for Computer Science majors, Advanced Technical Elective or Application Elective for Data Science majors, Flexible Technical Elective for Electrical Engineering majors
Welcome to Practical Data Science in Winter 2025! This site is currently under construction. Until this disclaimer is removed, all information here is subject to change.
If you’re interested in taking the course in Winter 2025, you may want to look at last semester’s course website, linked here; it contains links to all lectures, assignments, etc. from Fall 2024, though note that many aspects of the syllabus will change. Read below for more details about the course.
Fall 2024 Evaluations
Since this is a relatively new course, we’ve provided the complete set of course evaluations from Fall 2024 here to help inform your decision on whether to enroll. The document contains dozens of written comments from students who took the course.
Some useful summary statistics:
- This course advanced my understanding of the subject matter: 4.8 / 5.
- Overall, this was an excellent course: 4.8 / 5.
- Overall, Suraj Rampure was an excellent teacher: 4.9 / 5.
- As compared with other courses of equal credit, the workload for this course was: 2.6 / 5 (lower values mean more work).
Regarding workload, we also ran our own internal survey:
Content
Skills and tools for building practical data science projects, along with their theoretical underpinnings.
pandas,numpy,scikit-learn,BeautifulSoup, and Jupyter Notebooks, and also the math behind loss functions, gradient descent, linear and logistic regression, and other key ideas in machine learning.
This course will train students to use industry-standard tools to solve real-world problems, while giving them an understanding of how these tools work under the hood. After taking this course, students will be prepared to build data science portfolios, participate in research across campus, succeed in data science internships, reason about abstract mathematical problems, and understand the foundations of machine learning models.
Students will be expected to complete weekly homework assignments, which will comprise of a mix of programming and theoretical questions distributed in Jupyter Notebooks, along with a longer “Portfolio Homework” that requires using topics from the entire semester to perform an end-to-end analysis.
The course will have in-person, on-paper midterm and final exams that involve a mix of multiple choice, short answer, fill in the blank code, math, and English problems (for context, see the Fall 2024 Midterm Exam and solutions here).
The exams are scheduled for the following times:
- Midterm Exam: Tuesday, February 25th, 7-9PM (tentative and subject to change)
- Final Exam: Monday, April 28th, 10:30AM-12:30PM
Other materials from the Fall 2024 offering can be found at the Fall 2024 website.
Prerequisites
The course is open to students from all majors.
The enforced prerequisites are discrete math (EECS 203), programming (EECS 280), calculus I, calculus II, and linear algebra. A probability and statistics course is an advisory prerequisite. Options include DATASCI 101, STATS 206, STATS 250, STATS 280, STATS 412, IOE 265, or ECON 451.
If you’re interested in the class but don’t meet one of the prerequisites, email me and we can chat about your background and a potential override. I encourage students of all backgrounds who are curious about data science to reach out!
In particular, students without prior linear algebra experience will be directed to a linear algebra review website that we’ve created specifically for this course.
Enrollment Logistics
If you’d like to enroll in the course, sign up for these EECS 398 sections:
- lecture LEC 002 or LEC 003, and
- discussion DIS 021, 022, 023, or 024.
There is only one live, in-person lecture, Monday and Wednesday 3-4:30PM in 1670 BBB (as is listed for LEC 002), and lecture attendance is not required.
- All students, regardless of section, will have access to lecture recordings.
- All students, regardless of enrolled section, can also attend the in-person lectures, space permitting on the day of the attendance. Usually, enough students consume material remotely that we don’t anticipate in-person space to be a bottleneck for anyone wishing to attend the class in-person.
In-person discussion attendance will be required or incentivized: make sure you can attend your enrolled discussion section.
Office hours will largely be in-person, but there will be some remote options as well.