COM 1015 Data Management and Visualization

Empirical data sets are common in all the sciences, ranging from numerical tables to networks, maps, and tensor fields. Such data sets are increasingly common in all professions as more and more data is captured in all industries. Visualization and statistics are two complementary ways to figure out the stories an empirical data set is trying to tell. Statistics engages rigorous mathematical reasoning, while visualization harnesses the innate pattern-detection power of the human visual cortex. This course trains students to prepare data sets for visual interpretation and to build visual data models of increasing complexity using Python libraries. Selected topics covered in this course: Data management: characterization, collection, storage, and cleaning of data sets, Visual channels in the brain: pre-attentive processing, accuracy of estimation, levels of discrimination, Visual data exploration: graphical tools to complement exploratory statistics, Telling the truth: visual distortion of data, how to detect it, how to avoid it, Telling a story with data: choosing a visual language to enlighten or persuade. Prerequisite(s): COM 1001 or COM 1300 or COM 1300C.

Credits

3