Data visualization is increasingly central to predictive analytics and data science. The book focuses on all three application areas of data visualization: exploratory data analysis, model diagnostics, and presentation graphics. Built on the same structure and approach as other books in Thomas W. Miller's popular Modeling Techniques series, it has been carefully designed to serve multiple audiences: business managers, analysts, programmers, and students.

Miller begins with core principles, revealing why some data visualizations effectively present information and others don't. He reviews the science of human perception and cognition, proven principles of graphic design, and the growing role of visualization throughout data science -- including examples such as the visualization of time, networks, and maps.

Drawing on his pioneering experience teaching data visualization, Miller begins each chapter by stating a real business problem. He explains why the problem is important, describes a relevant dataset, and guides you through solving it with leading open-source tools such as R, Python, D3, and Gephi. (All R and Python code is set apart, so managers or analysts who aren't interested in programming can easily skip it.)

Like other books in this series, Data Visualization Principles and Practices draws realistic examples from key application areas, including marketing, finance, sports analytics, web and network data science, text analytics, and social network analysis. Examples include cross-sectional data, time series, network, and spatial data. Readers will discover advanced methods for constructing static and interactive graphics, building web-browser-based presentations, and even creating "information art."