Different Factors that Contribute to Overall Health

Inspiration

We wanted to look at how different factors of health effect

What it does

We load and categorize a large number of categorical features from the BRFSS dataset. Then we perform novel EDA on the dataset and then extract features from each category and fit a regression to look at how they predict overall health. We then use all of these features to fit a novel, final model of health prediction.

How I built it

Python, scikitlearn

Challenges I ran into

Dealing with a dataset with convoluted encoding, switching projects halfway through

Accomplishments that I'm proud of

Meeting new people and having fun. Trying to do a project that isn't just optimizing a predictive model.

What I learned

How in general chronic illnesses affect overall health. How to parse unstructured data.

What's next for Different Factors that Contribute to Overall Health

Better feature selection process, causal

Built With

• pandas
• python
• scikit-learn