capaci / music-analysis

A toy project to put in practice some concepts of Data Science, analysing songs from Vagalume (vagalume.com.br)

music-analysis

A toy project to put in practice some concepts of Data Science, analysing songs from Vagalume (vagalume.com.br).

Todo

I don't know yet how I'll achieve each step of data pipeline, so as soon as I'll discover, I'll create new tasks here

Structuring the project

• structure the directories
• configure linter
• create automated tests
• create docs about the software architecture
• write instructions about how to run the project properly

Getting the data

• create connection with database
• create database structure
• get all songs from a single artist
• save those songs in a sqlite database

Cleaning

• Remove stopwords?

Exploring

• Create wordcloud?
• Get some insights and document them

Modeling

• ?

Deploy

• ?