hadryan / machine-learning-for-music-genres

A predictive model that is capable of predicting the music genre based on the given set of audio features.

Predictive Modelling for music genres classification

Objective:

Build a predictive model that is capable of predicting the music genres based on the given set of features

Features:

• Acousticness: The relative metric of the track being acoustic
• Danceability: The relative measurement of the track being danceable
• Duration_ms: The length of track in milliseconds(ms)
• Energy: The primary identifier for the track, generated by Spotify
• Instrumentalness: The relative ratio of the track being instrumental
• Liveness: The relative duration of the track sounding as a live performance
• Loudness: Relative loudness of the track in the typical range
• Speedchiness: The relative length of the track containing any kind of human voice
• Tempo: The tempo of the track in Beat Per Minute (BPM)
• Valence:The positivity of the track
• Key: The primary key of the track encoded as integers in between 0 and 11
• Mode: The binary value representing whether the track starts with a major (1) chord progression or not (0)

Target:

The predicting result can have any of the following values:

• Alternative Metal
• Cool Jazz
• Electro House
• Performance
• Salsa
• Texas Country
• Trap

Data Sets:

• See csv files in Data folder