“Hot’n’Pop Song Machine”: end-to-end Machine Learning classificator project

“Hot’n’Pop Song Machine”: end-to-end Machine Learning classificator project

This is an article where I describe from concept to deployment the “Hot’n’Pop Song Machine” project, a Machine Learning song popularity predictor I created that uses the Streamlit app framework and web hosting on Heroku.

This is an article where I describe from concept to deployment the “Hot’n’Pop Song Machine” project, a Machine Learning song popularity predictor I created that uses the Streamlit app framework and web hosting on Heroku. I hope it can be useful to other Data Science enthusiasts.

The Github repository of the full “Hot’n’Pop Song Machine” project can be found here.

You can play with a live demo of the “Hot’n’Pop Song Machine” web app here.

Table of Contents

Introduction

Methodology

Requirements

Execution Guide

Data Acquisition

Data Preparation

Raw Data Description

Data Exploration

Modeling

Summary

Front-end

Conclusions

References

About Me

Introduction

My idea for this project started when I found out about the existence since 2010 of the Million Song Dataset, a freely-available collection of audio features and metadata for a million contemporary popular music tracks. Since music is one of my passions, it seemed appropriate to base one of my first Data Science projects on this subject. The core of the dataset was provided by the company The Echo Nest. Its creators intended it to perform music identification, recommendation, playlist creation, audio fingerprinting, and analysis for consumers and developers. In 2014 The Echo Nest was acquired by Spotify, which incorporated that song information into their systems. Now those audio features and metadata are available through the free Spotify Web API. Finally I chose to use this API instead of the Million Song Dataset for the project, thanks to it is flexibility and my will to practice working with APIs.

Music information retrieval (MIR) is the interdisciplinary science of retrieving information from music. MIR is a small but growing field of research with many real-world applications. Those involved in MIR may have a background in musicology, psychoacoustics, psychology, academic music study, signal processing, informatics, machine learning, optical music recognition, computational intelligence or some combination of these. MIR applications include:

  • Recommender systems
  • Track separation and instrument recognition
  • Automatic music transcription
  • Automatic categorization
  • Music generation

According to the International Federation of the Phonographic Industry (IFPI), for the full year 2019 total revenues for the global recorded music market grew by 8.2 % to US$ 20.2 billion. Streaming for the first time accounted for more than half (56.1 %) of global recorded music revenue. Growth in streaming more than offset a -5.3 % decline in physical revenue, a slower rate than 2018.

Being able to predict what songs have the traits needed to be popular and stream well is an asset to the music industry, as it can be influential to music companies while producing and planning marketing campaigns. It is beneficial even to artists, since they may focus on songs that can be promoted later by the music companies, or can become more popular amongst the general public.

State-of-the-art papers on MRI verse on audio signal processing, music discovery, music emotion recognition, polyphonic music transcription, using Deep Learning tools. Recent papers (2019) on MRI may be found on the International Society of Music Information Retrieval website.

python streamlit machine-learning music data-science

Bootstrap 5 Complete Course with Examples

Bootstrap 5 Tutorial - Bootstrap 5 Crash Course for Beginners

Nest.JS Tutorial for Beginners

Hello Vue 3: A First Look at Vue 3 and the Composition API

Building a simple Applications with Vue 3

Deno Crash Course: Explore Deno and Create a full REST API with Deno

How to Build a Real-time Chat App with Deno and WebSockets

Convert HTML to Markdown Online

HTML entity encoder decoder Online

Data Science Projects | Data Science | Machine Learning | Python

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.

Data Science Projects | Data Science | Machine Learning | Python

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.

Data Science Projects | Data Science | Machine Learning | Python

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.

Data Science Projects | Data Science | Machine Learning | Python

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.

Data Science Projects | Data Science | Machine Learning | Python

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.