Last active
November 28, 2019 21:29
-
-
Save danjgale/3988f424c1a86051b2aa84b429ffd84d to your computer and use it in GitHub Desktop.
A real-world example of a searchlight analysis with nilearn
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from nilearn.decoding import Searchlight | |
from nilearn.datasets import load_mni152_brain_mask | |
from nilearn.image import new_img_like | |
from sklearn.pipeline import make_pipeline | |
from sklearn.preprocessing import StandardScaler | |
from skearn.svm import LinearSVC | |
from sklearn.model_selection import LeaveOneGroupOut | |
imgs = # 4D NIfTI image or list of 3D NIfTI images | |
y = # array-like of condition labels for each volume in `imgs` | |
run_labels = # array-like of run labels for each volume of `imgs` | |
pipeline = make_pipeline(StandardScaler(), LinearSVC()) | |
brain_mask = load_mni152_brain_mask() | |
searchlight = Searchlight(mask_img=brain_mask, radius=4, estimator=pipeline, | |
cv=LeaveOneGroupOut()) | |
searchlight.fit(imgs, y, groups=run_labels) | |
results = new_img_like(brain_mask, searclight.scores_) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment