Teaching Parallelism without Programming: A Data Science Curriculum for Non-CS Students

Abstract

The goal of our work is to develop an open and modular course for data science and big data analytics that is accessible to non-programmers. The course is designed to cover major concepts that are useful to understand the benefits of parallel and distributed programming while not relying on a programming background. These key concepts focus more on algorithmic aspects rather than architecture and performance issues. A key aspect of our work is the use of workflows to illustrate key concepts and to allow the students to practice.