Book Image

Applied Geospatial Data Science with Python

By : David S. Jordan
3 (1)
Book Image

Applied Geospatial Data Science with Python

3 (1)
By: David S. Jordan

Overview of this book

Data scientists, when presented with a myriad of data, can often lose sight of how to present geospatial analyses in a meaningful way so that it makes sense to everyone. Using Python to visualize data helps stakeholders in less technical roles to understand the problem and seek solutions. The goal of this book is to help data scientists and GIS professionals learn and implement geospatial data science workflows using Python. Throughout this book, you’ll uncover numerous geospatial Python libraries with which you can develop end-to-end spatial data science workflows. You’ll learn how to read, process, and manipulate spatial data effectively. With data in hand, you’ll move on to crafting spatial data visualizations to better understand and tell the story of your data through static and dynamic mapping applications. As you progress through the book, you’ll find yourself developing geospatial AI and ML models focused on clustering, regression, and optimization. The use cases can be leveraged as building blocks for more advanced work in a variety of industries. By the end of the book, you’ll be able to tackle random data, find meaningful correlations, and make geospatial data models.
Table of Contents (17 chapters)
Part 1:The Essentials of Geospatial Data Science
Free Chapter
Chapter 1: Introducing Geographic Information Systems and Geospatial Data Science
Part 2: Exploratory Spatial Data Analysis
Part 3: Geospatial Modeling Case Studies

Constructing a spatial hypothesis test

In the introduction to this chapter, we mentioned that the second part of ESDA revolves around testing for spatial structure. Before we begin talking about the methods used, let’s first discuss what we mean by this term. A spatial structure in simplest terms is the presence of a pattern within data across geographic space. Data that has no spatial structure is said to have been generated by an independent random process (IRP). This IRP result is data that exhibits complete spatial randomness (CSR). In other literature, you’ll often see IRP and CSR used interchangeably. IRP/CSR must satisfy two conditions in order to construct a valid hypothesis test:

  • Any observation must have an equal probability of occurring in any location. This is known as a first-order effect. As an example, the distribution of an infectious disease will vary across a study area, based on underlying environmental factors.
  • The location of an observation...