Scikit learn has a
make_regression data generator. Can someone explain it to me like I'm 5 what is meant in the help docs by "The input set can either be well conditioned (by default) or have a low rank-fat tail singular profile"?
Well-conditioned: the data is well formatted for the regression task.
Low rank: the input has low dimensional data.
Fat tail: the dataset has a lot of extreme values, which could be challenging as the distribution is unbalanced.
Singular profile: specific distribution.
On a whole, make_regression is able to make many kinds of random regressions problems, from simple distributions (well-conditioned) to very complex ones (singular).