The topic of the Hackathon was Health and Healthcare. In recent years, mental health and wellness has come to the forefront of health discussions. With our project, our team wanted to provide value and problem solving to the healthcare field involving those affected by mental health problems through data analysis. As one of our teammates is a former music educator, we were drawn to the idea of exploring the connection between music and mental health.
What it does
Our project is a data analysis which aims to identify the correlations, if any, between an individual’s music tastes, listening habits, and self reported mental health. With our findings, we aim to provide useful insight for professional music therapists in order to better understand the relation between music and their patients.
How we built it
We began by obtaining a public dataset from Kaggle and then cleaned and analyzed it using Python in Jupyter Labs. We utilized numerous Python libraries including Pandas, Numpy, Seaborn, and Matplotlib in order to manipulate data and create various visualizations. We then summarized our findings and how they could inform music therapy.
Challenges we ran into
We are all very new and ran into numerous issues setting up our coding environment. Git/Github caused us hours of headache. The built-in Git functionality in Jupyter did not work as smoothly as we had desired at the start. We originally planned on creating an interactive dashboard with widgets using Panel, but could not understand the documentation to set up the necessary pipelines and then were unable to incorporate static charts made with matplotlib/seaborn. Some of us had a hard time figuring out how to access and isolate the data from our csv file that we were interested in charting. Lastly, our data set ended up being more restrictive than we initially realized and its lack of varied numerical data greatly limited the graphs/charts we could make. Additional demographic data columns as well as a larger pool of people surveyed would have allowed for more possibilities in data exploration.
Accomplishments that we're proud of
We were able to collaborate using all new tools! Jupyter labs was new to us all, we knew very little about Git and Github, and we had little to no experience using additional python libraries such as Pandas, Seaborn, and Matplotlib. So the fact that we produced this Jupyter Notebook was a massive accomplishment for our team. We achieved working experience reading through documentation for new technologies and contributing to a collaborative project in a time sensitive environment.
What we learned
We learned a boatload during this project. We all became a bit more comfortable collaborating with Github and can create simple Jupyter notebooks. Everyone in our team learned how to work with csv files and access, drop, replace specific data in the dataframe. Each one of us learned how to produce various graphs/charts using Pyplot and Seaborn. We also have a better understanding of what makes a good data set and what sorts of visualizations work for differing types of data.
What's next for Music and Mental Health
Organizing and hosting our findings in a web app would provide a better user experience in synthesizing our data analysis and push us to become familiar with more useful technologies and workflows. If we had more time, we would have loved to get our charts interactive using Panel. This would allow us to create an interactive dashboard with widgets such as radio buttons, sliders, and drop down menus. While we created all of these widgets successfully we had to table them for a later date as we experienced other Panel issues.