Metadata-Version: 2.1
Name: nilearn-extra
Version: 0.1.0
Summary: Drop-in extra functionalities for nilearn (statistics for neuroimaging in Python)
Home-page: https://github.com/morteza/nilearn-extra
License: BSD 3-Clause
Keywords: neuroimaging,nilearn,machine learning
Author: Morteza Ansarinia
Author-email: ansarinia@me.com
Requires-Python: >=3.9,<3.11
Classifier: License :: Other/Proprietary License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Dist: nilearn (>=0.9.1,<0.10.0)
Requires-Dist: scipy (>=1.8,<2.0)
Project-URL: Repository, https://github.com/morteza/nilearn-extra
Description-Content-Type: text/markdown

# nilearn-extra

**Nilearn Extra** is a small add-on for *[Nilearn](https://nilearn.github.io/) (Statistics for NeuroImaging in Python)*. It currently adds some functional connectivity measures to the mix.

## Installation

```bash
pip install nilearn-extra
```

## Usage

```diff
- from nilearn.connectome import ConnectivityMeasure
+ from nilearn_extra.connectome import ConnectivityMeasure
```

## Extra Connectivity Matrices

Nilearn Extra supports two additional connectivity matrices:
- Chatterjee XiCorr (`kind="chatterjee"`) is a new correlation coefficient as described in [Chatterjee (2019)](https://arxiv.org/abs/1909.10140).
- Transfer Entropy (`kind="transfer entropy"`) between regions X and Y is amount of uncertainty reduced in Y by knowing the past values of X. Note that transfer entropy is a asymmetric measure, so is the connectivity matrix.

# Optional dependencies

```bash
# for transfer entropy connectivity
pip install pyinform
```

## Contributing

We use GitHub to fork and manage pull requests.

## License

BSD 3-Clause License. See the [LICENSE](LICENSE) file.

