Inspiration
Being in Texas, Tacos & Burritos are everyday go to food which inspired me to dive into this project.
What it does
My analysis helps predict how to successfully setup a Taco & Burrito restaurant chain around the country based on the sales and consumption ratio in different cities.
How I built it
I have used Python programming language for the analysis and used pandas, matplotlib, numpy, seaborn libraries.
Challenges I ran into
The data was messy and took a lot of time to be cleaned. There were around 236 columns at the start out of which only 26 of them were useful, all the others were just noisy data that needed to be cleaned.
Out of those 26 columns, there were a lot of NaN values present, so those columns were needed to be dropped for accuracy purposes.
After considering all the aspects, I finalized around 10 data columns to be used for my analysis.
Accomplishments that I'm proud of
I have completed 3 sets of analysis which are as follows:
- What are the top 5 cities having most number of Tacos & Burritos restaurants,
- How many restaurants are added in each month-year which can help us predicts sales vs consumption ratio in future
- What type of tacos and burritos are consumed most and in which cities they are consumed most.
What I learned
I learned to take a closer look at data to analyze it which can be used for predictive analytics.
What's next for TB Analysis and Visualizations
Currently my analysis is not using any Machine Learning models but it's using available data for analyzing my queries. I would like to use available data to predict sales in the future.
Log in or sign up for Devpost to join the conversation.