This project aims to classify songs into 'Hip-Hop' or 'Rock' genres based solely on their audio features, without listening to them. It involves preparing, exploring, and visualizing music data, followed by applying machine learning algorithms for classification.
Data and Approach:
Data: The dataset comprises track metadata and audio features like 'danceability' and 'acousticness', sourced from The Echo Nest (Spotify). Approach: The project includes data cleaning, exploratory data visualization, feature reduction, and the implementation of machine learning algorithms such as decision trees and logistic regression.
Technologies Used: Python Pandas for data manipulation Matplotlib/Seaborn for visualization Scikit-learn for machine learning models
Key Insights: The project reveals insights into the distinguishing features of the 'Hip-Hop' and 'Rock' genres. Demonstrates the effectiveness of feature reduction in enhancing model performance.
Acknowledgments: This project is a guided project from DataCamp, designed to apply practical data science skills in an engaging context.