def decision_tree_learning(examples, attrs, parent_examples=()):
if len(examples) == 0:
return plurality_value(parent_examples)
if all_same_class(examples):
return DecisionLeaf(examples[0][target])
if len(attrs) == 0:
return plurality_value(examples)
A = choose_attribute(attrs, examples)
tree = DecisionFork(A, dataset.attr_names[A], plurality_value(examples))
for (v_k, exs) in split_by(A, examples):
subtree = decision_tree_learning(exs, remove_all(A, attrs), examples)
tree.add(v_k, subtree)
return tree
def set_problem(self, target, inputs=None, exclude=()):
"""
Set (or change) the target and/or inputs.
This way, one DataSet can be used multiple ways. inputs, if specified,
is a list of attributes, or specify exclude as a list of attributes
to not use in inputs. Attributes can be -n .. n, or an attr_name.
Also computes the list of possible values, if that wasn't done yet.
"""
self.target = self.attr_num(target)
exclude = list(map(self.attr_num, exclude))
if inputs:
self.inputs = remove_all(self.target, inputs)
else:
self.inputs = [a for a in self.attrs if a != self.target and a not in exclude]
if not self.values:
self.update_values()
self.check_me()
def information_content(values):
"""Number of bits to represent the probability distribution in values."""
probabilities = normalize(remove_all(0, values))
return sum(-p * math.log2(p) for p in probabilities)
