RR Recommender

Inspiration

We were inspired the number of food borne illnesses caused by restaurants, which are more then double the number cases at a private house. We were also inspired by, how many of us are unable to think of recipes at the top of our heads when we cook.

What it does

Our website has two main functions. First, the user can input what ingredients they have and get a recommendation of what recipes they can make in a particular cuisine. Our second feature is takes in a violation description and an inspection score and outputs whether or not it is a good restaurant.

How I built it

We built the website using HTML, Java and Python.

Challenges I ran into

Halfway through building our website, we doubted the usefulness of our website. However, we realized that the refrigerator dilemma is a widespread, everyday issue and that the restaurants' ratings could provide potential businesspeople valuable information on where they should build their startups based on the popularity - a factor affected by the ratings of buildings nearby - of each area. We also ran into several problems trying to learn new languages and APIs but, with the support of the mentors, persevered and created a product.

Accomplishments that I'm proud of

We are satistfied that we managed to expand our knowledge on building websites with HTML and CSS. We also dabbled in Python while trying to use Machine Learning and R while creating our heat map.

What I learned

We learned much of the information we listed above on-the-spot today. For instance, some of us had no idea how to use APIs; others had no idea what APIs were!

What's next for Foods

We want to broaden our views by offering more recipes to users and supplying them with more options for restaurants. We also want to be able to utilize all the data we were offered by the John Snow Labs spreadsheets by using Machine Learning, and we want to we able to add a scanning feature to use image detection for the inside of the refrigerator.