This exploratory data analysis project was completed loosely following guidelines from the Data Analysis with Python: Zero to Pandas Course Project notebook on Jovian.
Dataset is from Music & Mental Health Survey Results on Kaggle, which reports results on preference of different music genres and self-reported mental health conditions (anxiety, depression, insomnia and obsessive-compulsive disorder).
Due to personal interest on music therapy, I was curious to see if there were any potential correlations between music preference and self-reported mental health conditions. However, due to the survey being self-reported, especially in terms of the mental health conditions, this might not be an accurate observation as we are not sure whether the respondents have actually been officially diagnosed with those mental health conditions. Besides that, the usage of a numeric rating scale (from 0-10) for self-reported mental health conditions has certain limitations, e.g. respondents might differ in subjective views on severity despite providing similar ratings. Regardless, this dataset was able to provide preliminary insights towards how one's mental health might be affected by/affecting one's preference in music, opening possibilities to deep dive into this topic and inform future approaches in music therapy.
As the practical objective of completing this project was to learn how to use pandas and matplotlib through hands-on experience, I appreciate any feedback and suggestions towards improving the exploratory data analysis of the dataset.