Skip to content
BranchesTags

Latest commit

 

History

9 Commits

Folders and files

NameName
Last commit message
Last commit date
flask-api
flask-api
 
 
screenshots
screenshots
 
 
.cache
.cache
 
 
.gitignore
.gitignore
 
 
EDA.ipynb
EDA.ipynb
 
 
README.md
README.md
 
 
RNCP - Olivier Babiard - Final Project (Diggerz App).pdf
RNCP - Olivier Babiard - Final Project (Diggerz App).pdf
 
 
RNCP - Slides - Olivier Babiard - Final Project.pdf
RNCP - Slides - Olivier Babiard - Final Project.pdf
 
 
app.py
app.py
 
 
beatport_datasets.ipynb
beatport_datasets.ipynb
 
 
music_recommender.py
music_recommender.py
 
 
music_recommender2.py
music_recommender2.py
 
 
music_recommender3.py
music_recommender3.py
 
 
price_scrapping.ipynb
price_scrapping.ipynb
 
 
spotify_datasets.ipynb
spotify_datasets.ipynb
 
 
version1.ipynb
version1.ipynb
 
 
version2.ipynb
version2.ipynb
 
 
version3.ipynb
version3.ipynb
 
 
version4_clustering.ipynb
version4_clustering.ipynb
 
 

Repository files navigation

Music Recommender App 🎵

Overview

The Music Recommender App is a personalized music recommendation system developed using Python and Streamlit. This app leverages the Spotify and Discogs APIs to provide users with music recommendations based on the analysis of album data. By inputting a Discogs release URL, users receive a detailed analysis of the album, visualizations of audio features, and personalized track recommendations.

✨ Features

  • Discogs and Spotify Integration: Retrieves album information from Discogs and audio features from Spotify
  • Audio Analysis: Provides analysis of audio features like danceability, energy, tempo, and more
  • Album Visualization: Generates visualizations for album audio features and track tempos
  • Music Recommendations: Offers personalized music recommendations based on similarity in audio features, genre, and style
  • Market Price Information: Displays pricing statistics for albums listed on Discogs (when available)

🗂 Project Structure

  • app.py: Main Streamlit app file - manages interface and integrates with MusicRecommender
  • music_recommender3.py: Core recommendation logic, audio feature analysis, and API integrations
  • price_scrapping.ipynb: Jupyter notebook for Discogs price scraping
  • Data directories (not in repo):
    • data/
    • data-extracts/
    • complete/
    • split_by_genre/
    • split_by_genre_no_subgenre/

🛠 Requirements

Technologies

  • Python 3.8+

Libraries

  • Streamlit
  • Spotipy
  • Discogs_client
  • Pandas
  • Scikit-learn
  • Matplotlib
  • Seaborn
  • Requests
  • BeautifulSoup
  • Selenium

APIs

  • Spotify API
  • Discogs API

🚀 Usage

  1. Launch the app
  2. Enter a Discogs release URL
  3. View detailed album information:
    • Artist details
    • Genre and style
    • Release year
    • Market prices
  4. Explore audio analysis visualizations
  5. Get five personalized music recommendations with preview links

🔮 Future Improvements

  • Add genre-specific recommendations
  • Use related artists to expand recommendations
  • Enhance error handling
  • Optimize performance

Links

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

0 stars

Watchers

1 watching

Forks

0 forks
Report repository

Releases

Packages

Used by

Contributors

Languages