https://github.com/plasmacontrol/bes-ml
BES ML data tools and models
https://github.com/plasmacontrol/bes-ml
Last synced: about 1 year ago
JSON representation
BES ML data tools and models
- Host: GitHub
- URL: https://github.com/plasmacontrol/bes-ml
- Owner: PlasmaControl
- Created: 2022-07-25T11:35:39.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2025-01-26T22:35:54.000Z (about 1 year ago)
- Last Synced: 2025-01-26T23:23:45.960Z (about 1 year ago)
- Language: Jupyter Notebook
- Size: 50.1 MB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# BES ML
**ML models for DIII-D BES data**
To use this repo, clone it and add the repo directory to `$PYTHONPATH`. To contribute to this repo, branch off of `main`, push the feature branch to Github, and submit PRs. Prior to submitting PRs, pull and merge any updates from `main` and run pytest.
`bes_ml/` contains modules and classes to create, train, and analyze BES ML models. `bes_ml.base` contains the base classes, and other modules under `bes_ml` contain specific applications that import `bes_ml.base`. Each application directory should contain `train.py` and `analyze.py` modules. Example usage:
```python
from elm_regression import Trainer, Analyzer
model = Trainer()
model.train()
model_analyzer = Analyzer()
model_analyzer.plot_training()
model_analyzer.run_inference()
model_analyzer.plot_inference()
model_analyzer.show()
```
The primary code objects are:
- Base class `_Trainer` in `bes_ml.base.train_base` and application-specific subclasses like `ELM_Classification_Trainer` in `bes_ml.elm_classification.train`.
- Similarly, base class `_Analyzer` in `bes_ml.base.analyze_base` and applicaiton-specific subclasses like `ELM_Regression_Analyzer` in `bes_ml.elm_classification.analyze`
- Model class `Multi_Features_Model` in `bes_ml.base.models`. `Multi_Features_Model` is composed of different types of features such as CNN features, dense features, FFT features, etc. All feature are a subclass of `_Base_Features` in `bes_ml.base.models`.
`bes_data/` contains small sample datasets (~10 MB HDF5 files) to assist with code development and tools to package BES data on the GA cluster. `test/` contains pytest tests.
Additional examples can be inferred from the test scripts and from `if __name__ == ...` blocks in modules.