Geographic Data Science with Python

Who this book is for

For geographers adding computational analysis and data scientists who need to take spatial relationships seriously. It suits undergraduate project work after introductory coding and statistics, particularly when an ordinary table hides the neighborhood relationships or geographic scale that shape an apparent pattern.

Prerequisites

Know basic Python, data tables and descriptive statistics. Some GIS or geography background helps; review regression before the later modeling chapters and learn to work in a reproducible notebook environment.

What it covers

The book organizes spatial thinking around data, spatial weights and exploratory analysis before moving to inequality dynamics, regionalization, regression and feature engineering. Python examples make it possible to examine how the definition of neighboring observations affects the result. Its emphasis is geographic interpretation and spatial statistical analysis, complementing a guide centered on basic GIS operations.

How to use it

Start with a small dataset and a map that lets you inspect individual observations. Construct more than one plausible spatial-weights definition and compare the resulting patterns. Reproduce an example before substituting your own data, keeping preprocessing decisions in the notebook. Treat a detected cluster as a prompt for investigation; explain what the analysis tests and what it leaves unanswered about the underlying social process.

Edition and sources

This record selects the 2023 first-edition paperback, ISBN 9781032445953, checked in the publisher catalogue. The authors provide a free current online book; its web title page displays 2020, while the publisher identifies the print edition as 2023. The landing page, computational-tools discussion and contents were inspected. Software and chapter numbering can change between online renderings and print. Publisher or author record Official online resource

Open the official resource