Machine Learning techniques that classificate Black hole or Neutron star power spectra.
Report Bug
Table of Contents
power-spectrum-classification is a project focused on automating the classification of power spectra sources.
The project is built with python, with the help of the following libraries.
To classificate a new source or observation, the observation file (.asc) should be placed in data directory. The file should indicate the binning after the file extension (e.g., .asc_100 for rebin=100).
To train the Random Forest Model write in the terminal
python PSC.py --RF --n_estimators=N_ESTIMATORS min_samples_leaf=MIN_SAMPLES_LEAF min_samples_split=MIN_SAMPLES_SPLITwhere the optional arguments n_estimators, min_samples_leaf and min_samples_split are by default 200,20 and 50 respectively.
To train the Long Short Term Memory model write in the terminal
python PSC.py --RNN --batch_size=BATCH_SIZE --epochs=EPOCHSSimilary, to traub the CNN model
python PSC.py --CNN --batch_size=BATCH_SIZE --epochs=EPOCHSThere are also intrinsic parameter of the models that have to be modified specifically in the function that builds the specific model. These function can be found at models/models.py.
- Add Sources
- Black Holes
- Neutron Stars
- Galaxies
- Add Neural Network
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the GNU GPLv3 License. See LICENSE for more information.
Emmanuel A. Tassone - @EmmanuelTassone - emmanueltassone@gmail.com
Project Link: https://github.com/Emmatassone/power-spectrum-classification
A special thanks should be done to the following open-source projects.