Inspiration

They say rats run the city...but is that true? By analyzing a rat sighting dataset, we can determine the underlying needs of certain communities by figuring out which zip codes are underserved. We can pair this with another dataset that includes information about restaurant inspections to find patterns in under met zip codes.

What it does

The dashboard we created with Databricks aims to display the service gap, in terms of zip codes, for complaints made for rodent activity.

How we built it

We first analyzed the data before cleaning it. We checked for any non normalized values, duplicated data, null values, etc. Then, we joined both tables using the zip code column and then analyzed the resulting table.

Challenges we ran into

Both datasets contained duplicated information and columns that weren't normalized. So, figuring out what data was useful was a challenge.

Accomplishments that we're proud of

Around 44% of the rat sighting data had an issue with it, in that the elapsed closure time was 0. This meant that the claim was closed immediately. Figuring out how to use this data in a clever way was something we're proud of.

What we learned

From analyzing the dataset, we learned the importance of attentiveness when analyzing a dataset. Any wrong conclusions usually stems from this portion, so we made sure to spend alot of time on this.

What's next for The NYC Rodent Gap

“If I worked for the city, I would prioritize neighborhoods with high rodent complaints and lower inspection activity, because our data shows that service activity is not consistent across ZIP codes.”