Day 3: Working with Data
Goal
How tools like Quarto and Python can make report-writing ‘easy’.
Introductory session:
Applied session:
- Pandas (Right+Click to download file)
- Geopandas (Right+Click to download file)
- Linking data (Right+Click to download file)
Advanced topic:
If you’d like to dig into something that really stretches your understanding, then here are relevant links to some work that we did with using machine learning to predict neighbourhood change.
- The published article which presents our rationale and findings.
- The GitHub repository which shows how we obtained our results.
- Because we had made that work public, this allowed other researchers to take it further. And they also made their code open as well.
You can also, if you really want to do more with the built environment, explore the GlobalMLBuildingFootprints data set. It looks to me like you need to look in the dataset-links.csv file to find the files for your area; however, I haven’t yet been able to make sense of how you can only get what you need for, say, India rather than having to download all of India!