/ActSNClass

Active Learning for SN photometric classification

Primary LanguagePython

crp4 Paper DOI arXiv

ActSNClass

Active Learning for Supernova Photometric Classification

This repository holds the code and data used in Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning, by Ishida, Beck, Gonzalez-Gaitan, de Souza, Krone-Martins, Barrett, Kennamer, Vilalta, Burgess, Quint, Vitorelli, Mahabal and Gangler, 2018.

This is one of the products of COIN Residence Program #4, which took place in August/2017 in Clermont-Ferrand (France).

We kindly ask you to include the full citation if you use this material in your research: Ishida et al, 2019, MNRAS, 483 (1), 2–18.

Full documentation can be found at readthedocs.

Dependencies

For code:

  • Python>=3.7
  • argparse>=1.1
  • matplotlib>=3.1.1
  • numpy>=1.17.0
  • pandas>=0.25.0
  • setuptools>=41.0.1
  • scipy>=1.3.0
  • scikit-learn>=0.20.3
  • seaborn>=0.9.0
  • xgboost>=1.6.2

For documentation:

  • sphinx>=2.1.2

Install

The current version runs in Python-3.7 or latter.

We recommend you use a virtual environment to ensure the correct package versions.

Once your environment is created, you can source it :
>> source <path_to_venv>/bin/activate

You will notice a (ActSNCLass) to the left of your terminal line. This means everything is ok!

In order to install this code you should clone this repository and do::

(ActSNClass) >> pip install --upgrade pip
(ActSNClass) >> pip install -r requirements.txt
(ActSNClass) >> python setup.py install