Improve Data Engineering

[Greyisheep]

Add code in preprocessors.py file to automatically grab new data from the google sheets of responses and append to the data.csv file.

[Bwhiz]

So, I have solved this, so the solution reads the data directly from the google sheet and then we can split into test inside the script, instead of having a seperate stand alone file. Once this has been made into a pipeline, whenever we run the pipeline, the model is automatically updated with new training data directly from the Google sheet.