How to run the ethnicity-inferrer project:

If modifying the model, locate these two variables in preprocessing.py VCF_DIR, METADATA_FILE and fill in the appropriate paths in your machine where your 1000 genome project DNA samples are and the metadata file containing the ethnicities.

If not modifying the model and prefer to to use the pre-trained model, run the app.py file and use a tool like postman to send a 'file' multipart via the request body to the /classify endpoint.