Metadata-Version: 2.1
Name: carsdata
Version: 0.1
Summary: Package to apply MCR-ALS on CARS images
Home-page: https://gitlab.xlim.fr/datacart/cars-data
Author: D. Boildieu
Author-email: damien.boildieu@xlim.fr
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: End Users/Desktop
Classifier: Intended Audience :: Developers
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: pymcr
Requires-Dist: matplotlib
Provides-Extra: test
Requires-Dist: pytest ; extra == 'test'
Provides-Extra: torch
Requires-Dist: pytorch ; extra == 'torch'

# CARS Data

CARS Data is a package providing multivariate curve resolution algorithms and utilities functions for CARS cartographies.
The package provides: 
* a Simplisma algorithm implementation
* MCR-ALS based on [pymcr](https://pages.nist.gov/pyMCR/) package:
  * ALS and NNLS regressions
  * the classical normalization (sum-to-one) and non-negative constraints
  * a new segmentation constraint based on Chan-Sandberg-Vese algorithm
* fit unknown spectra onto fixed signature spectra using ALS or NNLS and apply MCR constraints on the results
* Autoencoders based on [PyTorch](https://pytorch.org/) packages.
## Dependencies
**Note**: These are the developmental system specs. Others versions of certain packages may work.

* python 3
  * Tested with 3.8.10
* numpy
  * Tested with 1.16.5
* pymcr
  * Tested with 0.3.2
* matplotlib
  * Tested with 3.4.2

## Optional depencies
* torch
  * Tested with 1.9.0 

## Installation
```
pip install .
```


