Robin's Blog

What’s the largest building in Southampton? Find out with 5 lines of code

Recently I became suddenly curious about the sizes of buildings in Southampton, UK, where I live. I don’t know what triggered this sudden curiosity, but I wanted to know what the largest buildings in Southampton are. In this context, I’m using “largest” to mean largest in terms of land area covered – ie. the area of the outline when viewed in plan view. Luckily I know about useful sources of geographic data, and also know how to use GeoPandas, so I could answer this question pretty quickly – in fact, in only five lines of code. I’ll take you through this code below, as an example of a very simple GIS analysis.

First I needed to get hold of the data. I know Ordnance Survey release data on buildings in Great Britain, but to make this even easier we can go to Alastair Rae’s website where he has split the OS data up into Local Authority areas. We need to download the buildings data for Southampton, so we go here and download a GeoPackage file.

Then we need to create a Python environment to do the analysis in. You can do this in various ways – with virtualenvs, conda environments or whatever – but you just need to ensure that Jupyter and GeoPandas are installed. Then create a new notebook and you’re ready to start coding.

First, we import geopandas:

import geopandas as gpd

and then load the buildings data:

buildings = gpd.read_file("Southampton_buildings.gpkg")

The buildings GeoDataFrame has a load of polygon geometries, one for each building. We can calculate the area of a polygon with the .area property – so to create a new ‘area’ column in the GeoDataFrame we can run:

buildings[’area’] = buildings.geometry.area

I’m only interested in the largest buildings, so we can now sort by this new area column, and take the first twenty entries:

top20 = buildings.sort_values(’area’, ascending=False).head(20)

We can then use the lovely explore function to show these buildings on a map. This will load an interactive map in the Jupyter notebook:

top20.explore()

If you’d like to save the interactive map to a standalone HTML file then you can do this instead:

top20.explore().save(“map.html”)

I’ve done that, and uploaded that HTML file to my website – and you can view it here.

So, putting all the code together, we have:

import geopandas as gpd
buildings = gpd.read_file("Southampton_buildings.gpkg")
buildings[’area’] = buildings.geometry.area
top20 = buildings.sort_values(’area’, ascending=False).head(20)
top20.explore()

Five lines of code, with a simple analysis, resulting in an interactive map, and all with the power of GeoPandas.

Hopefully in a future post I’ll do a bit more work on this data – I’d like to make a prettier map, and I’d like to try and find some way to test my friends and see if they can work out what buildings they are.

If you found this post useful, please consider buying me a coffee.
This post originally appeared on Robin's Blog.

Tagged with:

Categorised as: Academic, GIS, Programming, Python