Lyrics Match

Preprocessing 380k data

The data preprocessed in this file can be found at this Kaggle repository

Original data when unzipped will give a lyrics.zip file and we will preprocess it to be used for the project in this notebook.

Use Preprocess380kMusicData.pynb file to get the following two csvs

The output files have been uploaded to this link: bit.ly/lm-dir

Name		Name	Last commit message	Last commit date
Latest commit History 48 Commits
Scraping_giitaayan		Scraping_giitaayan
Scraping_lyricsia		Scraping_lyricsia
Scraping_pratik		Scraping_pratik
assets		assets
data		data
heroku		heroku
models		models
.DS_Store		.DS_Store
.gitignore		.gitignore
BA_NMF.ipynb		BA_NMF.ipynb
LICENSE		LICENSE
NG_LDA.ipynb		NG_LDA.ipynb
Preprocess380kMusicData.ipynb		Preprocess380kMusicData.ipynb
SV_SVD.ipynb		SV_SVD.ipynb
SongClassification.ipynb		SongClassification.ipynb
index.html		index.html
polyglot_transliterate.ipynb		polyglot_transliterate.ipynb
readme.md		readme.md