<p>Where should you buy a house to get the most value for your money? Your first step might be to make a map, but spatial analysis in R can be intimidating because of the complicated objects the data often live in.</p><p>This course will introduce you to spatial data by starting with objects you already know about, data frames, before introducing you to the special objects from the sp and raster packages used to represent spatial data for analysis in R. You'll learn to read, explore, and manipulate these objects with the big payoff of being able to use the tmap package to make maps.</p><p>By the end of the course you will have made maps of property sales in a small town, populations of the countries of the world, the distribution of people in the North East of the USA, and median income in the neighborhoods of New York City.</p>
Basic mapping with ggplot2 and ggmapFree
We'll dive in by displaying some spatial data -- property sales in a small US town -- using ggplot2 and we'll introduce you to the ggmap package as a quick way to add spatial context to your plots. We'll talk about what makes spatial data special and introduce you to the common types of spatial data we'll be working with throughout the course.
You can get a long way with spatial data stored in data frames, but it makes life easier if they are stored in special spatial objects. In this chapter we'll introduce you to the spatial object classes provided by the sp package, particularly for point and polygon data. You'll learn how to explore and subset these objects by exploring a world map. The reward for learning about these object classes: we'll show you the package tmap which requires spatial objects as input, but makes creating maps really easy! You'll finish up by making a map of the world's population.
While the sp package provides some classes for raster data, the raster package provides more useful classes. You'll be introduced to these classes and their advantages and then learn to display them. The examples continue with the theme of population from Chapter 2, but you'll look at some much finer detail datasets, both spatially and demographically. In the second half of the chapter you'll learn about color -- an essential part of any visual display, but especially important for maps.
Data import and projections
In this chapter you'll follow the creation of a visualization from raw spatial data files to adding a credit to a map. Along the way, you'll learn how to read spatial data into R, more about projections and coordinate reference systems, how to add additional data to a spatial object, and some tips for polishing your maps.
In the following tracksSpatial Data
Assistant Professor at Oregon State University
Charlotte is an Assistant Professor in the Department of Statistics at Oregon State University and an avid R programmer with a passion for teaching. Her interests lie in spatiotemporal data, statistical graphics and computing, and environmental statistics.