def decision_tree_learning(examples, attributes, parent_examples=()):
if len(examples) == 0:
return plurality_value(parent_examples)
elif same_classification(examples):
return DecisionLeaf(examples[0][target])
elif len(attributes) == 0:
return plurality_value(examples)
elif percent_error(examples) < error_threshold:
return plurality_value(examples)
else:
a = importance(attributes, examples)
tree = DecisionTree(a, dataset.attrnames[a])
for (val_i, exs_i) in split_by(a, examples):
subtree = decision_tree_learning(exs_i, removeall(a, attributes), examples)
tree.add(val_i, subtree)
return tree
def decision_tree_learning(examples, attributes, m, parent_examples=()):
if len(examples) == 0:
return majority_value(parent_examples)
elif same_classification(examples):
return DecisionLeaf(examples[0][target])
elif len(attributes) == 0:
return majority_value(examples)
elif misclass_error(examples) < m:
return majority_value(examples)
else:
A = pick_attribute(attributes, examples)
tree = DecisionTree(A, dataset.attrnames[A])
nonlocal internal_nodes
internal_nodes += 1
for (val_i, exs_i) in split(A, examples):
subtree = decision_tree_learning(exs_i,
removeall(A, attributes), m,
examples)
tree.add(val_i, subtree)
return tree