Metadata-Version: 2.4
Name: mils_de
Version: 1.0
Summary: The mils-de package implements the the DensityEstimator model used to predict the Plasma density given the Power and Phase of possibly multiple MILS recivers.
Author-email: Piero Coronica <piero.coronica@mpcdf.mpg.de>
License-Expression: MIT
Keywords: MILS,DensityEstimator
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pandas>=2.1
Requires-Dist: numpy>=1.20
Requires-Dist: scikit-learn>=1.3
Provides-Extra: full
Requires-Dist: optuna>=3.6; extra == "full"
Requires-Dist: matplotlib>=3.8; extra == "full"
Requires-Dist: ipykernel; extra == "full"
Provides-Extra: dynamic
Requires-Dist: version; extra == "dynamic"
Dynamic: license-file


# mils-de

The `mils-de` package contains the models and tools necessary for performing analysis in the [`Intensity Refractometry`](https://gitlab.mpcdf.mpg.de/dataanalytics-public/intensity_refractometry) project. Specifically, it implements:

- The `DensityEstimator` model for predicting plasma density based on power and phase measurements from multiple receivers.
- Weighting functions and evaluation metrics.
- Constraints for the design space.
- Data loading and data manipulation tools, including synthetic design creation.

## Installation

To install the package, run:

```bash
pip install mils-de
```

### Optional Dependencies

To reproduce the analysis from the [`Intensity Refractometry`](https://gitlab.mpcdf.mpg.de/dataanalytics-public/intensity_refractometry) project, install the optional dependencies:

```bash
pip install mils-de[full]
```

## Usage

For usage examples and detailed guides, refer to the notebooks in the [`Intensity Refractometry`](https://gitlab.mpcdf.mpg.de/dataanalytics-public/intensity_refractometry) repository. A good starting point is [this notebook](https://gitlab.mpcdf.mpg.de/dataanalytics-public/intensity_refractometry/tools/notebooks/density_estimator.ipynb), which demonstrates how to fit a density estimator for a specific design and assess its performance.
