Geography is a longstanding academic discipline, so why do we need fancy new concepts, methods, and algorithms? Indeed, why is this book about geographic data science and not some other kind of quantitative study in geography, such as geocomputation or Geographic Information Science? This section addresses these questions by outlining the conceptual and practical fundamentals of geographic data science, as well as a few of the innovations and important new frames of reference that make geographic data science distinct from its precursors.

First, in Chapter 1, we discuss the fundamental differences in how data science is done. Reproducible, literate and interactive programming environments have seriously changed the game for how analysis is done. Second, we outline the fundamentals of geographic theory for data scientists. The main distinctions between geographic models and the data structures that represent them are explained in Chapter 2. The linkages between these models and structures are also discussed. Then, starting in Chapter 3, we show how these notions translate into patterns to read/write/represent geographic data formats. Finally, we close this part by discussing how to represent and store geographical relationships in an efficient data structure. Together, this provides a comprehensive overview of the main models of geographical processes, as well as the nuts and bolts of how to interact with geographical data.