Rotation argument for scikit-learn's factor analysis

Question

One of the hallmarks of factor analysis is that it allows for non-orthogonal latent variables.

In R for example this feature is accessible via the rotation parameter of factanal. Is there any such provision for sklearn.decomposition.FactorAnalysis? Clearly it's not among the arguments - but maybe there is another way to achieve this?

Sadly I have been unable to find many examples of usage for this function.

Erection

Answer 1

Interesting question. I think there are no rotations implemented indeed - see this issue.

Maybe this implementation is what you are looking for.

Daugavpils

Answer 2

It appears this is now implemented.

Example: https://scikit-learn.org/stable/auto_examples/decomposition/plot_varimax_fa.html

rotation{‘varimax’, ‘quartimax’}, default=None

If not None, apply the indicated rotation. Currently, varimax and 
quartimax are implemented. See “The varimax criterion for analytic 
rotation in factor analysis” H. F. Kaiser, 1958.

New in version 0.24.

Source: https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.FactorAnalysis.html

Sienese