Living in Sao Paulo - one of the most polluted cities in Brazil - since we were born, we have always been bothered by the tremendous amount of pollution in the city, especially air pollution. Coming from cars, factories, and many other sources, these pollutants that end up sticking in the air make us feel that the air in our city is not "pure" and "clean", but actually a contaminated version of it. With that in mind, and aiming to increase air pollution awareness in the world, we decided to create a website containing a model that accurately predicts the Air Quality Index (AQI) of a given country.
What it does
When entering our website, the user will be able to use our model to see the prediction of the AQI of the country he wants with an incredibly high accuracy.
How we built it
Firstly, we got a dataset from Kraggle which contained all countries in the world with their respective AQI and air quality status. We then cleaned this dataset (and ensured it was cleaned) and split it into training and testing sets for two machine-learning algorithms: Logistic Regression and Random Forest Classifier. We also tested the accuracy of both of these methods and compared the results of each of them - in the end, both of them were proved to be 100% accurate.
Challenges we ran into
The main challenge we faced during the Hackathon was to integrate our code into our Velo by Wix website. However, after some research, we managed to do it successfully.
Accomplishments that we're proud of
One of our accomplishments that we are the proudest of is that we were able to use not only one, but actually two different machine-learning algorithms in our program, which, in our opinion, makes it even better and more complete than it already was.
What we learned
From this experience, one of the things we learned the most was to use the Velo by Wix website. We believe that with this experience we were able to maximize our knowledge and understanding of all features and tools from this website.
What's next for Air Quality Index
We plan to advertise our program to others interested and curious about the air quality situation in the world, and, with that, reassure our main goal which is to increase awareness over air pollution (and why not other types of pollution too!) all around the world.
Log in or sign up for Devpost to join the conversation.