As PyCaret allows incorporating custom models Link I would appreciate any help in enabling PLS (partial least squares), so it can be used along with other models available in PyCaret (for comparisons, tuning, blending, predictions).
PLS is a part of sklearn, so should be compatible with PyCaret, but my naïve attempt
mypls = PLSRegression(n_components=5)
plsmodel = create_model(mypls)
returns an error... Apparently a custom class has to be defined, I am not sure how.