https://github.com/ammaraskar/black-holes-black-boxes

The supporting code behind "Finding Black Holes With Black Boxes"
https://github.com/ammaraskar/black-holes-black-boxes

astronomy blackhole globular-clusters machine-learning

Last synced: 4 months ago
JSON representation

The supporting code behind "Finding Black Holes With Black Boxes"

• Host: GitHub
• URL: https://github.com/ammaraskar/black-holes-black-boxes
• Owner: ammaraskar
• License: mit
• Created: 2018-08-26T18:18:12.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2024-06-17T22:48:13.000Z (over 1 year ago)
• Last Synced: 2025-07-19T10:30:28.913Z (4 months ago)
• Topics: astronomy, blackhole, globular-clusters, machine-learning
• Language: Python
• Homepage: https://ui.adsabs.harvard.edu/#abs/2019MNRAS.tmp..615A/abstract
• Size: 129 KB
• Stars: 5
• Watchers: 0
• Forks: 1
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
[![Build Status](https://travis-ci.org/ammaraskar/black-holes-black-boxes.svg?branch=master)](https://travis-ci.org/ammaraskar/black-holes-black-boxes)

[![Code Coverage](https://codecov.io/gh/ammaraskar/black-holes-black-boxes/branch/master/graph/badge.svg)](https://codecov.io/gh/ammaraskar/black-holes-black-boxes)

# Finding Black Holes with Black Boxes

This repository contains the supporting code and machine learning classifier

used in the "Finding Black Holes with Black Boxes" paper. There is also an

interactible Jupyter notebook which contains an interface that end users may

provide with observational values to get predictions based on MOCCA simulations.

## Use Interactively

To provide observational features and use the code interactively, click here:

[![Binder](https://mybinder.org/badge.svg)](https://mybinder.org/v2/gh/ammaraskar/black-holes-black-boxes/master?filepath=notebook.ipynb)

Once launched just click "Run" in the top and scroll down to the form.

## Directory Structure

- `tests/` - Folder containing some basic tests.

- `simulations.csv` - CSV file containing data form MOCCA simulations.

- `classifier.py` - Python code to generate and train the classifier.

- `notebook.ipnyb` - Interactible Jupyter notebook.

## Running Tests

You may run the unit tests with:

`python -m pytest`