lightcurvedistanceclassification

This repository contains all the code (in the form of Jupyter Notebooks) to reproduce the results in our paper, "Light Curve Classification with DistClassiPy: a new distance-based classifier"

https://github.com/sidchaini/lightcurvedistanceclassification

Science Score: 49.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 2 DOI reference(s) in README
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (11.5%) to scientific vocabulary

Keywords

astroinformatics astronomy astrostatistics light-curves machine-learning variable-stars
Last synced: 6 months ago · JSON representation

Repository

This repository contains all the code (in the form of Jupyter Notebooks) to reproduce the results in our paper, "Light Curve Classification with DistClassiPy: a new distance-based classifier"

Basic Info
  • Host: GitHub
  • Owner: sidchaini
  • License: other
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 171 MB
Statistics
  • Stars: 2
  • Watchers: 3
  • Forks: 2
  • Open Issues: 2
  • Releases: 0
Topics
astroinformatics astronomy astrostatistics light-curves machine-learning variable-stars
Created over 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

Repository Details

This repository contains all the code (in the form of Jupyter Notebooks) to reproduce the results in our paper, "Light Curve Classification with DistClassiPy: a new distance-based classifier".

The accompanying package, DistClassiPy can be found on GitHub at sidchaini/DistClassiPy and can be installed from PyPI by the command pip install distclassipy.

Notebooks

The Jupyter Notebooks are in the notebooks/ directory. There are a total of 10 base notebooks with subvariants for each classification depending on the notebook.

  1. Download Data
  2. Distance Metrics
  3. Preprocess Data (a,b,c)
  4. Classification (a,b,c)
  5. Analysis (a,b,c)
  6. RFC Comparison (a,b,c)
  7. Hidden Set Results (a,b,c)
  8. Computational Complexity
  9. Confidence Comparison (a,b,c)
  10. Robustness (a,b,c)

Note that a denotes the one-vs-rest classification problem (EA vs notEA), b denotes the binary classification problem (RSCVn vs BYDra) and c denotes the multi-class classification problem (CEP vs DSCT vs RR vs RRc).

Citation

If you use DistClassiPy in your research or project, please consider citing the paper:

Chaini, S., Mahabal, A., Kembhavi, A., & Bianco, F. B. (2024). Light Curve Classification with DistClassiPy: a new distance-based classifier. arXiv. https://doi.org/10.48550/arXiv.2403.12120

Bibtex

bibtex @ARTICLE{chaini2024light, author = {{Chaini}, Siddharth and {Mahabal}, Ashish and {Kembhavi}, Ajit and {Bianco}, Federica B.}, title = "{Light Curve Classification with DistClassiPy: a new distance-based classifier}", journal = {arXiv e-prints}, keywords = {Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Solar and Stellar Astrophysics, Computer Science - Machine Learning}, year = 2024, month = mar, eid = {arXiv:2403.12120}, pages = {arXiv:2403.12120}, archivePrefix = {arXiv}, eprint = {2403.12120}, primaryClass = {astro-ph.IM}, adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240312120C}, adsnote = {Provided by the SAO/NASA Astrophysics Data System} }

Authors

Siddharth Chaini, Ashish Mahabal, Ajit Kembhavi and Federica B. Bianco.

Owner

  • Name: Siddharth Chaini
  • Login: sidchaini
  • Kind: user
  • Location: Newark, DE
  • Company: University of Delaware

GitHub Events

Total
  • Push event: 4
  • Fork event: 1
Last Year
  • Push event: 4
  • Fork event: 1

Dependencies

.github/workflows/deploy-book.yml actions
  • actions/checkout v3 composite
  • actions/deploy-pages v2 composite
  • actions/setup-python v4 composite
  • actions/upload-pages-artifact v2 composite