There are 3 repositories under million-song-dataset topic.
Using machine learning to predict if a given song will be popular or not
Mining Million Song Dataset
Project for CMU 15-780 Graduate Artificial Intelligence
Predict whether a song is 'hot' or not, through analysis of the Million Song Dataset.
Notebooks and data to accompany Python instruction for Data in Social Context Fall 2018
Recommendation system on Million Song Dataset
Data Mining course project - Million Songs Dataset exploration
Discovery Recommender System
Classification of audio features using different ML algorithms on the MSD. The project was done for Machine Learning module at Coventry University.
Tools to run text-based experiments for large scale cover detection.
Design and implementation from scratch of different models for a musical recommendation system
An R project that investigates whether different genres of songs have significantly different durations through the use of a one-way ANOVA test and post hoc significance tests conducted over an excerpt of a dataset consisting of 1 million popular songs compiled by The Echo Nest and a lab at Columbia University.
Trend analysis of pop music and prediction of release year.
Language clustering of the musicXmatch dictionary in the Million Song Dataset
A command line tool to load the lyrics subset of the Million Song Dataset into an H2 SQL database
Example code for processing the Million Song Dataset and other big music datasets
Classying music genre based on audio features and lyrics (using the Million Song Dataset).
Machine Learning Final Project
An online song recommender based on a K-means model using the Spotify API and the MillionSongSubset
Using recommendation systems on the million-songs-dataset
Who would you listen to?: A Frequent Itemset Mining and Recommender System approach on the Million Song Dataset
For this project, we plan to build a basic music recommendation system using the MLlib libraries that are part of the Spark installation. Our dataset will be the Million Song Dataset, which is a collection of audio features and metadata for one million contemporary popular music tracks.
Analyze music history using Apache Cassandra.
This repository is inspired from Million Song Dataset Challenge from Kaggle. We aim to predict the year of song release by using timbre features' average and covariance.
Predicting Year in Million Song Dataset with Linear Regression using Pyspark
Parses the million song dataset/subset from h5 files to two txt files that can easily be used in Pandas, NumPy, or MapReduce
This repository implements pre-processing operations of the MELON PLAYLIST DATASET released by Ferraro et al.