Metadata-Version: 2.1
Name: glimix-core
Version: 1.6.0
Summary: Fast inference over mean and covariance parameters for Generalised Linear Mixed Models
Home-page: https://github.com/limix/glimix-core
Author: Danilo Horta
Author-email: horta@ebi.ac.uk
Maintainer: Danilo Horta
Maintainer-email: horta@ebi.ac.uk
License: MIT
Download-URL: https://github.com/limix/glimix-core
Keywords: function,optimisation
Platform: Windows
Platform: MacOS
Platform: Linux
Classifier: Development Status :: 5 - Production/Stable
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Description-Content-Type: text/markdown
Requires-Dist: brent-search (>=1.0.33)
Requires-Dist: cachetools (>=2.1.0)
Requires-Dist: liknorm (>=1.1.12)
Requires-Dist: ndarray-listener (>=1.1.2)
Requires-Dist: numpy-sugar (>=1.2.5)
Requires-Dist: numpy (>=1.14.3)
Requires-Dist: optimix (>=2.0.0)
Requires-Dist: pandas (>=0.23.1)
Requires-Dist: pytest (>=3.6.3)
Requires-Dist: pytest-doctestplus (>=0.1.3)
Requires-Dist: scipy-sugar (>=1.0.7)
Requires-Dist: scipy (>=1.0.1)
Requires-Dist: tqdm (>=4.23.4)

# glimix-core

[![Travis](https://img.shields.io/travis/limix/glimix-core.svg?style=flat-square&label=linux%20%2F%20macos%20build)](https://travis-ci.org/limix/glimix-core) [![AppVeyor](https://img.shields.io/appveyor/ci/Horta/glimix-core.svg?style=flat-square&label=windows%20build)](https://ci.appveyor.com/project/Horta/glimix-core) [![Documentation](https://img.shields.io/readthedocs/glimix-core.svg?style=flat-square&version=stable)](https://glimix-core.readthedocs.io/)

Fast inference over mean and covariance parameters for Generalised Linear Mixed
Models.

It implements the mathematical tricks of
[FaST-LMM](https://github.com/MicrosoftGenomics/FaST-LMM) for the special case
of Linear Mixed Models with a linear covariance matrix and provides an
interface to perform inference over millions of covariates in seconds.
The Generalised Linear Mixed Model inference is implemented via Expectation
Propagation and also makes use of several mathematical tricks to handle large
data sets with thousands of samples and millions of covariates.

## Install

We recommend installing it via
[conda](http://conda.pydata.org/docs/index.html):
```bash
conda install -c conda-forge glimix-core
```

Alternatively, glimix-core can also be installed using
[pip](https://pypi.python.org/pypi/pip):
```bash
pip install glimix-core
```

The second installation option requires from the user to install
[liknorm](https://github.com/limix/liknorm) beforehand.

## Running the tests

After installation, you can test it

```bash
python -c "import glimix_core; glimix_core.test()"
```

as long as you have [pytest](https://docs.pytest.org/en/latest/).

## Usage

Here it is a very simple example to get you started:

```python
>>> from numpy import array, ones
>>> from numpy_sugar.linalg import economic_qs_linear
>>> from glimix_core.lmm import LMM
>>>
>>> X = array([[1, 2], [3, -1], [1.1, 0.5], [0.5, -0.4]], float)
>>> QS = economic_qs_linear(X)
>>> X = ones((4, 1))
>>> y = array([-1, 2, 0.3, 0.5])
>>> lmm = LMM(y, X, QS)
>>> lmm.fit(verbose=False)
>>> lmm.lml()
-2.2726234086180557
```

An extensive documentation of the library can be found at
http://glimix-core.readthedocs.org/.

## Authors

* [Danilo Horta](https://github.com/horta)

## License

This project is licensed under the [MIT License](https://raw.githubusercontent.com/limix/glimix-core/master/LICENSE.md).


