Metadata-Version: 2.1
Name: notip
Version: 0.1.4
Summary: Nonparametric True Discovery Proportion control for brain imaging
Home-page: https://github.com/alexblnn/Notip
Download-URL: https://github.com/alexblnn/Notip/releases/download/Notip_OHBM_v2/notip-0.1.2.tar.gz
Author: Alexandre Blain
Author-email: alexandre.blain@inria.fr
Classifier: Programming Language :: Python :: 3.7
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Description-Content-Type: text/markdown
Requires-Dist: numpy (>=1.15.0)
Requires-Dist: scipy (>=1.0.0)
Requires-Dist: joblib (>=1.0.1)
Requires-Dist: scikit-learn (>=0.22)
Requires-Dist: nilearn
Requires-Dist: sanssouci
Requires-Dist: matplotlib
Requires-Dist: pandas
Requires-Dist: joblib
Requires-Dist: tqdm

# NOTIP: Non-parametric True Discovery Proportion control for brain imaging

This repository contains the code to reproduce all experiments of the Notip paper (https://arxiv.org/abs/2204.10572). The scripts directory contains a script per figure.
Note that the first time you run one of those scripts, the fMRI data fetching from Neurovault will take place, which takes a significant amount of time. This only needs to be done once.

### Installing dependencies

```
python -m pip install -r requirements.txt
```

### Reproducing figures

To reproduce any figure, i.e. figure 2, run:

```
python figure_2.py
```
This will display the corresponding figure as well as save it in ../figures

### Parallelization

To speed up any script using parallelization on CPU cores, use:

```
python figure_2.py 6
```

With any number of CPU cores instead of 6.
