This project is a comparative analysis of two Spotify playlists using R, focusing on data wrangling, statistical testing, and visualization to derive actionable insights into musical attributes such as BPM, energy, danceability, loudness, and more.
The analysis explores differences between playlists to understand their musical profiles. By leveraging advanced statistical techniques and intuitive visualizations, this project highlights key trends and relationships in the data.
- Data Wrangling:
- Combined and cleaned datasets using Tidyverse for streamlined analysis.
- Statistical Analysis:
- Conducted t-tests to assess statistically significant differences in track features.
- Visualizations:
- Created density plots and boxplots to display feature distributions.
- Built radar charts for side-by-side comparison of playlist characteristics.
- Generated correlation heatmaps to identify relationships between musical attributes.
- Technologies Used:
- Languages: R
- Libraries: ggplot2, dplyr, gridExtra, GGally, reshape2, fmsb
- Uncovered differences in musical attributes such as BPM, energy, and valence between playlists.
- Provided insights for playlist curation and audience engagement using data-driven decisions.
- Delivered a reproducible analysis pipeline with visually compelling outputs.
- Proficiency in data analysis and statistical modeling.
- Expertise in creating visual narratives with ggplot2 and related libraries.
- Experience in applying data visualization techniques for exploratory and comparative analysis.
This project highlights the ability to extract meaningful insights from raw data and transform them into actionable recommendations through advanced data analysis and visualization techniques.