Spotifire is a machine learning project that predicts song likability using a Random Forest classifier. Leveraging the Spotify API and scikit-learn, Spotifire provides personalized recommendations based on diverse musical features. With seamless integration and real-time predictions, Spotifire enhances the music discovery experience, making it more accurate and tailored to individual preferences.
- Predict song likability with a Random Forest classifier.
- Utilize the Spotify API for real-time user interaction.
- Enhance music streaming experiences through personalized recommendations.
Give Spotifire a spin and let the music find you! 🎶
Download the user_song_data.csv dataset containing user song likes and dislikes along with music attributes.
Upload the user_song_data.csv file to your Google Drive. This ensures convenient access to the dataset during the project.
- Go to the Spotify Developer Dashboard.
- Log in or create a new account.
- Create a new app to obtain Spotify API credentials.
- Copy the client ID and client secret for future use.
Open the provided Jupyter Notebook on your local machine or in a Google Colab environment.
In the notebook, replace placeholder values for client_id and client_secret with the credentials obtained from the Spotify Developer Dashboard.
Run the entire Jupyter Notebook (Spotifire.ipynb). This will execute all necessary steps, including connecting to Google Drive, loading the dataset, preprocessing the data, training the model, and creating an interactive interface for likability prediction.
- Experiment with different features, models, or preprocessing techniques.
- Iterate on the project to enhance its capabilities.
If you encounter any issues or wish to suggest improvements for this project, kindly submit an issue using the "Issues" tab above. In case you'd like to contribute a fix, please submit a pull request (PR) and reference the corresponding issue you created.