This course will introduce you to the nascent field of Geographic Data Science using the industry standard, the Python programming language. We will cover key steps involved in solving practical problems with spatial data, from manipulation and processing, to exploration. These topics will be explored from a “hands-on” perspective using a modern Python stack (e.g. geopandas, seaborn, scikit-learn, PySAL), and examples using real-world spatial data.

We will start with an overview of the main ways to manipulate and visualise data in Python. Then we will move on to spatial data, learning to perform traditional GIS operations and to visualise data in a geographic context (e.g. choropleths). The course will then move into explicitly spatial analysis, delving into spatial weights matrices, which will give way to exploratory spatial data analysis. In this context, we will cover both global and local approaches. We will finish the course covering more advanced topics such as the analysis of points and spatially constrained clustering.

NOTE: bring your own data!!!

  • 9:00/10:00: the Scientific Python stack: Jupyter and the Notebook []
  • 10:00/11:00: manipulating tabular data []
  • 11:00/12:00: visualising tabular data []
  • 9:00/11:00: Introduction to spatial data []
  • 11:00/12:00: Visualizing spatial data []
  • 9:00/10:30: Spatial weights []
  • 10:30/12:00: Spatial autocorrelation []
  • 9:00/10:00: interacting with raster data []
  • 10:00/11:00: combining raster and vector data visually []
  • 11:00/12:00: analysis combining raster and vector []
  • 9:00/10:00: reading and manipulating satellite imagery []
  • 10:00/12:00: creating a land-cover classification []

BONUS: data preparation in .

This course can be run using the Docker container.

Before starting the installation, make sure you have access to a reliable and reasonably fast internet connection. The software required takes up quite a bit of space and hence involves heavy downloads.

If you have administration rights on the machine you will use for the course, Docker is the safest and most stable route.

Note: that you will need at least 10GB of space in your machine.

  • Install (follow instructions for macOS, Windows 10 or earlier, Ubuntu)

  • Open a command prompt (ie. on macOS, on Windows)

  • Run the following command. This will download about 10GB of data, so it might take a while (particularly on slow connections). Be patient 😃

  • Installation is ready!

  • To test that it is correctly installed, you can run from the same command line, the following command:

  • This should list, at least, the following:

    [Note the may vary]

Once installed, you can run the Docker container with the following command:

This will print out something similar to:

Then you can go to a browser and access , replacing by the token printed in the command line (in the case above, ).

by is licensed under a .

Clones Terminal Edit
Showing 7 notebooks