This repository contains a jupyter notebook outlining the preliminary data prep done for my blog post on creating a medical diagnosis bot using rasa.
Part 1 describes how to prepare the input data for the diagnosis portion of the project while part 2 describes how I generated some training data for Rasa's NLU model.
I have separated these from the tutorial source code repository as I thought a notebook was the best way to present the data preparation steps and I did not want to include any jupyter notebooks in the main repository to avoid any confusion.
The used in this was aquired from Kaggle