An Open-Source Active Learning Curriculum for Data Science in Engineering

Abstract

This work provides open-source content for an active learning curriculum in data science. The scope of the content is sufficient for a full-semester introduction to scientifically reproducible statistical computation, data wrangling, visualization, basic statistical literacy, and data-driven modeling. The content is broken into short exercises that introduce new concepts, and longer challenges that encourage students to develop those skills in an open-ended context.