search

Niketkumardheeryan / ML-CaPsule

ML-capsule is a Project for beginners and experienced data science Enthusiasts who don't have a mentor or guidance and wish to learn Machine learning. Using our repo they can learn ML, DL, and many related technologies with different real-world projects and become Interview ready.
MIT License
365 stars 311 forks source link

Song genre classifier using NLP #498

Closed TANYA-CHAN closed 2 years ago

TANYA-CHAN commented 2 years ago
  1. This project aims to identify which genre a song belongs to on the basis of its lyrics
  2. The dataset contains 62155 songs
  3. Each song is classified into 5 genres- Country, Rock, Hip-Hop, Pop and Rhythm and Blues
  4. Two major text classification methods were tested- Logistic Regression and Naïve Bayes
  5. Under Naïve Bayes, 3 models were tested- Count Vectorizer, TF-IDF, and Text Cleaning
  6. Upon testing, Multinomial Naïve Bayes with Text Cleaning was found to give the highest accuracy
  7. Further analysis was also done to find top songs and generate WordClouds

I'll be implemented using Jupyter Notebook

TANYA-CHAN commented 2 years ago

@Rutikab12 is this okay?

Rutikab12 commented 2 years ago

@Rutikab12 is this okay?

Yeah. Go for it

TANYA-CHAN commented 2 years ago

2022-05-21 (64) @Rutikab12 what does this error specify?

Rutikab12 commented 2 years ago

Try to relogin to your account. Change github password. LAst login session might have been stopped.

Rutikab12 commented 2 years ago

2022-05-21 (64) @Rutikab12 what does this error specify?

You can also take help of this link

TANYA-CHAN commented 2 years ago

2022-05-21 (64) @Rutikab12 what does this error specify?

You can also take help of this link

Done I've created the PR, thank you so much. Please review it.

TANYA-CHAN commented 2 years ago

@Rutikab12 2022-05-21 (106) How do I add the .csv because it is too large

Rutikab12 commented 2 years ago

@Rutikab12 2022-05-21 (106) How do I add the .csv because it is too large

Just post link of it, if its from kaggle . PRefer to use Github desktop, it is quite handy in terms of use.

TANYA-CHAN commented 2 years ago

@Rutikab12 please tell me the status of this project sir