https://github.com/eco786786/spotify-playlist-generator

This project uses machine learning to cluster songs by features like tempo, genre and mood with K-Means. It then creates personalised Spotify playlists based on these clusters, providing dynamic, genre specific track collections. Integrating the Spotify API, it enables users to explore new music within custom groupings.
https://github.com/eco786786/spotify-playlist-generator

flask matplotlib pandas python3 scikit-learn seaborn

Last synced: about 2 months ago
JSON representation

This project uses machine learning to cluster songs by features like tempo, genre and mood with K-Means. It then creates personalised Spotify playlists based on these clusters, providing dynamic, genre specific track collections. Integrating the Spotify API, it enables users to explore new music within custom groupings.

• Host: GitHub
• URL: https://github.com/eco786786/spotify-playlist-generator
• Owner: ECO786786
• Created: 2024-11-14T13:11:33.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-14T14:07:38.000Z (about 2 months ago)
• Last Synced: 2024-11-14T14:34:41.254Z (about 2 months ago)
• Topics: flask, matplotlib, pandas, python3, scikit-learn, seaborn
• Language: Jupyter Notebook
• Homepage:
• Size: 2.45 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Spotify Playlist Generator

## Summary

This project investigates the potential of machine learning to automate playlist generation for Moosic, a startup currently dependent on human curation. As Moosic aims to scale, this project explores whether machine learning can match or enhance the quality of human curated playlists, making playlist creation more efficient and consistent.

## Key Business Questions

- **Can Spotify’s audio features identify similar songs by human perceived criteria?**

- **Is K-Means clustering a suitable approach for playlist creation?**

  - What are the advantages and limitations?

- **Which audio features should be included or excluded and why?**

- **How effective is the prototype at creating cohesive playlists?**

- **What additional data would improve playlist quality?**

- **What are the next steps if this project moves forward?**

By clustering songs based on Spotify’s audio features and auto generating playlists, this project provides insights into the feasibility of machine learning in playlist curation and outlines potential future actions for Moosic’s technology adoption.

## Languages and Libraries Used

- **Python**

- **Flask**

- **pandas** for data manipulation

- **scikit-learn** for machine learning models

- **matplotlib** for data visualization

- **seaborn** for data visualization

- **spotipy** for interacting with the Spotify API