This project is aimed at college students. The main issue with college students is that they don't get enough time to go through the previous years' question papers which is very important as there is a high chance that questions may be repeated and that's exactly where this project comes into place. This project uses the basics of Natural Language Processing (NLP) and OCR and creates a simple predictive machine learning model which suggests only the important topics from the syllabus to study. Just upload the PDFs of the syllabus and previous ear question paper and voilà!!! you get the most repeated topics from which questions have been asked in past years

To run this program type the following commands

pip install -r requirements

Confirm the installations and then type the following to migrate the data:

python manage.py migrate

Confirm the migration is error free, and then type the following in command prompt and follow the instructions in terminal to create a superuser:

python manage.py createsuperuser

Now type the following to start the website server in localhost:

python manage.py runserver

Now type the following in your browser to access the website:

localhost:8000

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate