A DecisionTree object represents a decision tree, as described in, for
example, the book "Artificial Intelligence" by Russell and Norvig (3rd
edition).
For a given attribute, a Distribution object stores information about a
probability distribution over the possible attribute values in two different
ways: (i) frequencies -- how many times each attribute value was observed,
and (ii) probabilities -- the probability that this attribute has each of the
possible attribute values.