ofir-frd / Prediction-of-Music-Genre

Classify music into genres by classical machine learning models

Prediction of Music Genre

A Kaggle dataset.

In this project a dataset of songs needs to be classified by their genre.

About Data collection methodology

No early description is given on the feature collection methods, quality, or any other type of data.

Description of the data

Directory description:

Root Dir/
  - Prediction_of_music_genre.ipynb
  - classification_report_plot.ipynb
  - music_genre.csv
  - README.md
  - LICENSE.md
  - .gitignore

Features review:

music_genre.csv/
  - Labels
    - music_genre
  -  Numerical
    - instance_id
    - popularity
    - acousticness
    - danceability
    - duration_ms
    - energy
    - instrumentalness
    - liveness
    - loudness
    - speechiness
    - tempo
    - valence
  -Categorical
    - key
    - mode
  - Other
    - artist_name - text
    - track_name - text
    - obtained_date - irrelevant

File formats

Code writen in Python on Jupyter '.ipynb'.

The data provided in this project is a '.csv' file with no separation between train and test datasets.

-50,000 songs, format csv.

Online Repository link

• DataRepository

Author

• ofir-frd

License

This project is licensed under the Apache License 2.0 - see the LICENSE.md file for details

Acknowledgments

• Inspired by the Shazam app