This README provides instructions for data preparation for the Virtual Health Assistant project. To use the dataset required for this project, follow these steps:
To start data preparation, first download the dataset from Figshare.
- Create a
dataset
folder inside themodel
directory. - Copy both the JSON files and
release_train_patients.csv
from your downloaded dataset into thedataset
folder. - Rename
release_train_patients.csv
totraining.csv
. - Rename
release_conditions.json
todiagnosis_keywords.csv
. - Rename
release_evidences.json
toquestion_keywords.csv
.
Your data is now ready for use in the Virtual Health Assistant project.
- Make sure that the dataset folder and file names match the provided instructions exactly for the project to work as expected.
Feel free to reach out if you have any questions or need further assistance with the project.