Case Study: Predicting Crop Yields
In our final case study, we will explore the real-world problem of crop yields. To do this, we will demonstrate an Extract, Transform, Load (ETL) workflow that uses many of the Python methods explained in previous chapters – ArcPy, ArcGIS API for Python, Pandas, and scikit-learn – as well as some of the web tools that Python allows you to use. The ETL process combines worldwide agricultural data into a format that can be used to predict crop yields using machine learning and loads it into ArcGIS Online. The resulting combined dataset is geographically enabled and can be updated with the latest data at any time using code.
To top it all off, we will display the final combined data in a simple web app built with HTML, CSS, and JavaScript, to illustrate the kinds of tooling that Python makes possible.
The following topics are covered in this chapter:
- Introducing the problem, data, and study area
- Downloading the...
