[FEA] Add all_estimators function

[sarahyurick]

In scikit-learn, I'm able to do this:

from sklearn.utils import all_estimators

all_estimators()

[('ARDRegression', sklearn.linear_model._bayes.ARDRegression),
 ('AdaBoostClassifier', sklearn.ensemble._weight_boosting.AdaBoostClassifier),
 ('AdaBoostRegressor', sklearn.ensemble._weight_boosting.AdaBoostRegressor),
 ('AdditiveChi2Sampler', sklearn.kernel_approximation.AdditiveChi2Sampler),
 ('AffinityPropagation',
  sklearn.cluster._affinity_propagation.AffinityPropagation),
 ('AgglomerativeClustering',
  sklearn.cluster._agglomerative.AgglomerativeClustering),
 ('BaggingClassifier', sklearn.ensemble._bagging.BaggingClassifier),
...

I don't see a similar cuML function, although I think the implementation would be fairly similar to how scikit-learn does it. Would this utility feature be something cuML is willing to add support for?