def dt_learn(dataset, attrs, parent_dist=None):
if not dataset:
return Dt.Leaf(parent_dist.get_most_common())
dist = Distribution(dataset)
if dist.is_leaf() or not attrs:
return Dt.Leaf(dist.get_most_common())
else:
attr = max_gain(dataset, dist, attrs)
tree = Dt.Node(attr)
for v in attr.domain:
dv = [d for d in dataset if d.x[attr.index] == v]
child_attrs = [a for a in attrs if a != attr]
subtree = dt_learn(dv, child_attrs, dist)
tree.add_child(subtree, v)
return tree
