Welcome
Imago training
Hands-on training for working with imagery-derived data
This site brings together training materials produced by Imago, part of the Smart Data Research UK family. Our trainings are designed for two audiences: policy and analyst users working with prepared indicators in tools like Excel, and researchers working with raw and processed data in R or Python.
Each training is self-contained. You can work through them in order or pick the topics relevant to your needs.
Before you start
If you are new to the kinds of data Imago produces, start with these orientation pages:
- Data sets — what’s available and where it comes from
- From grids to areas — how raw satellite data becomes area-level indicators
- Geo-spatial and statistical packages — reference for the R and Python tooling we use
1. Policy trainings
For analysts and policy users. No coding required — these trainings work with prepared indicators in spreadsheet tools.
| Training | Topic | Format |
|---|---|---|
| Data Insights with Excel | Exploring climate and vulnerability indicators in Excel | Excel |
2. Research trainings
For researchers comfortable with R or Python. These trainings work with raw and processed data and assume basic familiarity with at least one of the two languages.
Each training has a written walkthrough you can read, and a runnable notebook you can launch directly in your browser via JupyterLite — no installation required.
| Training | Topic | Read | Run in browser |
|---|---|---|---|
| 1. The basics | Cross-sectional foundations: distribution, mapping, IMD merge, OLS | Notebook | Launch |
| 2. Panel data | Building the 2015–2024 MSOA panel and inspecting trajectories | Notebook | Launch |
| 3. Climate inequality | Has the deprivation–heat gap widened? Two-way fixed effects | Notebook | Launch |
| 4. Bivariate maps | Mapping the joint geography of heat and health deprivation | Notebook | Launch |
| Precipitation | Working with precipitation indicators | Coming soon | Coming soon |
| SPF: Sun probability framework | Joining and aggregating spatial data | Coming soon | Coming soon |
Contributing
These materials are openly developed on GitHub. We welcome corrections, suggestions, and new training contributions — please open an issue or pull request.
License
This repository uses a dual-licensing approach:
- MIT License for all software code (see LICENSE)
- Creative Commons Attribution 4.0 International (CC BY 4.0) for documentation, data, and non-code content
See the LICENSE file for full details.