track-twin is a project that creates personalized Spotify playlists based on the similarity to a given track using machine learning. Simply input a song, and track-twin will webscrape cosine.club and create a Spotify playlist on your account containing the results!
- For use, reach out to me and I will send client_id and key, and add you to my spotify dev team so that you can give it a spin. If requests for this go up then I will make the app readily available to everyone!
- Only works well with edm genres ex: House - Dubstep - DNB
- If you want to hear some funny music I recommend trying a country or rap song
- Personalized Spotify playlists
- Input a song to get similar track recommendations
- Utilizes web scraping for track similarity
- Input a song
- track-twin scrapes cosine.club for similar tracks
- Generates a Spotify playlist with the results
- Clone the repository:
git clone https://github.com/J-Bills/track-twin.git
- Navigate to the project directory:
cd track-twin - Install the necessary dependencies:
pip install -r requirements.txt
- Create a config.py:
touch config.py
- add client_id and client_key vars to config.py:
client_id = #Spotify Client id client_key = #Spotify Client key
To run TrackMatch, use the following command:
python3 track_twin.py