https://github.com/explore-platform/s-phot_stellar_classifier
S-Phot stellar classifier with XGBoost
https://github.com/explore-platform/s-phot_stellar_classifier
astronomy classification photometry sed stellar
Last synced: 11 months ago
JSON representation
S-Phot stellar classifier with XGBoost
- Host: GitHub
- URL: https://github.com/explore-platform/s-phot_stellar_classifier
- Owner: explore-platform
- License: mit
- Created: 2023-12-12T08:34:55.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-16T15:30:51.000Z (about 2 years ago)
- Last Synced: 2025-02-05T21:53:58.922Z (about 1 year ago)
- Topics: astronomy, classification, photometry, sed, stellar
- Language: Python
- Homepage:
- Size: 1.02 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# S-Phot Stellar Classifier #
## Description ##
An XGBoost based approach to classification of highly sparse, sampling biased photometric stellar data with extreme class imbalance using Data generated by PySSED.
## File Descriptions ##
1. data/
1. **random\_10perc** PySSED generated labels and data for ten percent SIMBAD sample
2. **ms\_augmented** PySSED generateed labels and data for ten percent SIMBAD sample augmented with additional main sequence star data
2. **tuning\_results\_5foldcv\_2000\_iter\_ms\_augmented/** Contains outputs generated by running _tuning_script.py_ with data from _data/ms_augmented_
3. **tuning\_results\_5foldcv\_2000\_iter\_no\_ms/** Contains outputs generated by running _tuning_script.py_ with data from _data/random_10perc_
4. **tuning\_script.py** Script used to tune XGBoost model hyperparameters
5. **main.py** Script used to load and train XGBoost models using parameters saved from running _tuning_script.py_
6 **create\_imbalance\_plots.py** Used in sparsification experiments
7. **explore\_commons.py** Contains helper functions
8. **XGBoost\_Weighted.py** XGBoost model with additional parameters for tuning of class weights.
9. **requirements.txt** libraries and versions used in order to generate experiment results.