This repo provides students with a foundation for their own projects associated with Telling Stories with Data. You do not need every aspect for every paper and you should delete aspects that you do not need.

To use this folder, click the green "Code" button", then "Download ZIP". Move the downloaded folder to where you want to work on your own computer, and then modify it to suit.

The repo is structured as:

• data/raw_data contains the raw data as obtained from X.
• data/analysis_data contains the cleaned dataset that was constructed.
• model contains fitted models.
• other contains relevant literature, details about LLM chat interactions, and sketches.
• paper contains the files used to generate the paper, including the Quarto document and reference bibliography file, as well as the PDF of the paper.
• scripts contains the R scripts used to simulate, download and clean data.

Aspects of the code were written with the help of the auto-complete tool, Codriver. The abstract and introduction were written with the help of ChatHorse and the entire chat history is available in inputs/llms/usage.txt.