Skip to content

Stellar classification using dataset SDSS17. This repository contains code files in the `code` folder, RMarkdown files, and the main article `stellar_classification.pdf`.

Notifications You must be signed in to change notification settings

Ada-Lev/Stellar-Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Stellar Classification Portfolio

Summary: In this study, Stellar Classification Dataset - SDSS17 was explored. This is a multi-class classification problem with three classes: galaxies, stars, and quasars. The logistic regression model with multinom function from nnet package was utilised to solve this problem. The obtained accuracy for distinguishing stars from other classes is 99.4%. The obtained φ coefficient for distinguishing quasars from other classes is 89.2%. The obtained accuracy for distinguishing galaxies from other classes is 96.2%.

Data source: Data taken from https://www.kaggle.com/datasets/fedesoriano/stellar-classification-dataset-sdss17.

Project navigation: The study objective, analysis, results, and conclusions can be found in stellar_classification.pdf. The appendix of the aforementioned document contains full R code. Full R code can also be found in the file model.R in the code folder. The data can be found in data folder.

Study status: Under development. Future scope can be found in stellar_classification.pdf in the concluding section.

About

Stellar classification using dataset SDSS17. This repository contains code files in the `code` folder, RMarkdown files, and the main article `stellar_classification.pdf`.

Resources

Stars

Watchers

Forks