It is mentioned on this page that Label Propagation of scikit-learn can be used for regression also. However, nothing is mentioned on its API page.
How can I do semi-supervised learning for regression with Label Propagation or any other method?
It seems to be an error in the documentation as the target is validated to be a classification target.
check_classification_targets(y)
The default label propagation would however just propagate the existing 'labels' i.e. regression values, so not much would be gained in this case.
