def plurality_value(examples):
"""Return the most popular target value for this set of examples.
(If target is binary, this is the majority; otherwise plurality.)"""
popular = argmax_random_tie(values[target],
key=lambda v: count(target, v, examples))
return DecisionLeaf(popular)
def plurality_value(examples):
major = None
i = 0
for v in values[target]:
if (count(target, v, examples) > i):
i = count(target, v, examples)
major = v
return DecisionLeaf(major)
def majority_value(examples):
"""Selects the most common output value among a setof examples, breaking ties randomly."""
i = 0
for v in values[target]:
if (count(target, v, examples) > i):
i = count(target, v, examples)
major = v
return DecisionLeaf(major)
def decision_tree_learning(examples, attrs, parent_examples=()):
if len(examples) == 0:
return plurality_value(parent_examples)
elif all_same_class(examples):
return DecisionLeaf(examples[0][target])
elif len(attrs) == 0:
return plurality_value(examples)
else:
A = choose_attribute(attrs, examples)
tree = DecisionFork(A, dataset.attrnames[A], plurality_value(examples))
for (v_k, exs) in split_by(A, examples):
subtree = decision_tree_learning(
exs, removeall(A, attrs), examples)
tree.add(v_k, subtree)
return tree
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
def decision_tree_learning_continuos(examples,
attributes,
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)
else:
A, treshold = pick_attribute_continuos(attributes, examples)
tree = DecisionTreeContinuos(A, treshold, dataset.attrnames[A])
less_equal, greater_than = split_continuous(A, treshold, examples)
subtree_le = decision_tree_learning_continuos(
less_equal, removeall(A, attributes), examples)
tree.add(treshold, False, subtree_le)
subtree_gt = decision_tree_learning_continuos(
greater_than, removeall(A, attributes), examples)
tree.add(treshold, True, subtree_gt)
return tree
def plurality_value(examples):
"""Return the most popular target value for this set of examples"""
popular = argmax_random_tie(values[target],
key=lambda v: count(target, v, examples))
return DecisionLeaf(popular)