[FEA] Add TransformedTargetRegressor to cuML

[esnvidia]

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I wish I could use cuML to do [...]

cuML is missing this API from sklearn:
https://scikit-learn.org/stable/modules/generated/sklearn.compose.TransformedTargetRegressor.html#sklearn.compose.TransformedTargetRegressor

Describe the solution you'd like

from cuml.compose import TransformedTargetRegressor

Describe alternatives you've considered
Doing it manually

Additional context
Add any other context, code examples, or references to existing implementations about the feature request here.
See here why transforming the target is important: https://scikit-learn.org/stable/auto_examples/compose/plot_transformed_target.html#sphx-glr-auto-examples-compose-plot-transformed-target-py

[beckernick]

It should be possible today to use cuML estimators with this scikit-learn wrapper if the data is on the CPU. Would that be useful for you?