Song_Classification_Project[DS203]

This project aims to classify songs based on various features using machine learning techniques. The main tasks involve feature extraction, exploratory data analysis (EDA), model development, and evaluation. The dataset consists of audio features of songs, and the project uses MFCC (Mel Frequency Cepstral Coefficients) as a feature extraction technique to predict different classes of songs.

Repository Contents

E7-DS203_FINAL.pdf - The final report documenting the methodology, findings, and results of the song classification project.

E7_Project_3_Classification.ipynb - A Jupyter Notebook for developing and training classification models using k-means clustering, svm and randomforest classification models. The notebook includes data preprocessing, feature extraction (MFCC), model training, and evaluation.

EDA-E7.ipynb - A Jupyter Notebook dedicated to the exploratory data analysis (EDA) of the dataset. It includes visualizations and analysis to understand the data better before applying machine learning models.

MFCC_Creation.ipynb - A Jupyter Notebook that demonstrates how we extracted Mel Frequency Cepstral Coefficients (MFCC) from audio files. These features are used for classification in this project.