Foundations of Data Science
Fall 2026
Data science gives us tools for learning from data. In this course, we will study how data are represented, modeled, evaluated, and communicated. We will connect mathematical foundations—including linear algebra, probability, statistics, information theory, and optimization—to practical analysis in Python.
- Course
- Foundations of Data Science
- Instructor
- Adam Poliak
- Lecture
- Tuesdays and Thursdays, 10:10–11:30 AM
- Park 337
- Lab
- Tuesdays, 2:40–4:00 PM
- Park 230
- Term
- August 31–December 10, 2026
- Breaks
- Fall Break: October 10–19
- Thanksgiving Break: November 25–30
- Course schedule
- See the Schedule for topics and weekly readings.
- Prerequisites
- Calculus I, Data Structures, and Discrete Mathematics (the latter may be taken concurrently).
- Programming language
- Python 3
Course goals
By the end of the course, students will be able to:
- represent and explore data using Python, NumPy, and visualization tools;
- construct, fit, and evaluate statistical and machine-learning models;
- apply core ideas from probability, linear algebra, optimization, and statistics;
- interpret uncertainty and communicate evidence clearly; and
- recognize the assumptions and limitations of data-driven analysis.
Readings
There is no required textbook purchase. Readings come from free online books, articles, course notes, videos, and research papers:
The schedule is tentative and may change as the semester progresses.
Exams
There will be two in-class midterms and a cumulative final exam:
- Midterm 1: Thursday, October 8, during lecture
- Midterm 2: Thursday, November 19, during lecture
- Final exam: scheduled and announced by the Registrar
Grading
- Homeworks: 10%
- Midterm: 25% (15% for one and 10% for the other)
- Final: 55%
- Participation: 10%
Acknowledgments
The topic sequence and readings are adapted from Thao Nguyen’s Fall 2025 Foundations of Data Science course, with materials originally adapted from Sara Mathieson.