def _build_tree_recursively(dataset):
"""
Private function used to build the decision tree in a recursive fashion.
Args:
dataset: model.DataSet
The data at the current level of the tree. Lower levels of the tree
have filtered subsets of the original data set.
Returns:
current_root: Node
The node which is the root of the level being processed. For
example, on the first/outermost call to this function the root
node will be returned. Subsequent calls will return the various
child nodes.
"""
label_set = set(dataset.get_labels())
if len(label_set) == 1:
# All remaining samples have the same label, no need to split further
return Node(label_set.pop())
if len(dataset.feature_list()) == 0:
# No more features to split on
return Node(get_most_common(dataset.get_labels()))
# We can still split further
split_feature = choose_feature_to_split(dataset)
node = Node(split_feature)
for value in dataset.get_feature_values(split_feature):
subset = dataset.value_filter(
split_feature, value).drop_column(split_feature)
node.add_child(value, _build_tree_recursively(subset))
return node
def test_get_all_descendants(self):
root_node = Node("Root")
child1 = Node("Child1")
child2 = Node("Child2")
root_node.add_child("child1", child1)
root_node.add_child("child2", child2)
grandchild1 = Node("GC1")
grandchild2 = Node("GC2")
child2.add_child("child1", grandchild1)
child2.add_child("child2", grandchild2)
assert_that(
root_node.get_all_descendants(),
contains_inanyorder(
child1, child2, grandchild1, grandchild2))
def _build_tree_recursively(dataset):
"""
Private function used to build the decision tree in a recursive fashion.
Args:
dataset: model.DataSet
The data at the current level of the tree. Lower levels of the tree
have filtered subsets of the original data set.
Returns:
current_root: Node
The node which is the root of the level being processed. For
example, on the first/outermost call to this function the root
node will be returned. Subsequent calls will return the various
child nodes.
"""
label_set = set(dataset.get_labels())
if len(label_set) == 1:
# All remaining samples have the same label, no need to split further
return Node(label_set.pop())
if len(dataset.feature_list()) == 0:
# No more features to split on
return Node(get_most_common(dataset.get_labels()))
# We can still split further
split_feature = choose_feature_to_split(dataset)
node = Node(split_feature)
for value in dataset.get_feature_values(split_feature):
subset = dataset.value_filter(split_feature,
value).drop_column(split_feature)
node.add_child(value, _build_tree_recursively(subset))
return node
def create_tree_tennis(self):
"""
Creates a tree matching the play_tennis.data data's decision tree.
"""
root_node = Node("Outlook")
humidity_node = Node("Humidity")
high_humidity_node = Node("No")
normal_humidity_node = Node("Yes")
humidity_node.add_child("High", high_humidity_node)
humidity_node.add_child("Normal", normal_humidity_node)
root_node.add_child("Sunny", humidity_node)
overcast_node = Node("Yes")
root_node.add_child("Overcast", overcast_node)
wind_node = Node("Wind")
strong_wind_node = Node("No")
weak_wind_node = Node("Yes")
wind_node.add_child("Strong", strong_wind_node)
wind_node.add_child("Weak", weak_wind_node)
root_node.add_child("Rain", wind_node)
return Tree(root_node)
def create_tree_tennis(self):
"""
Creates a tree matching the play_tennis.data data's decision tree.
"""
root_node = Node("Outlook")
humidity_node = Node("Humidity")
high_humidity_node = Node("No")
normal_humidity_node = Node("Yes")
humidity_node.add_child("High", high_humidity_node)
humidity_node.add_child("Normal", normal_humidity_node)
root_node.add_child("Sunny", humidity_node)
overcast_node = Node("Yes")
root_node.add_child("Overcast", overcast_node)
wind_node = Node("Wind")
strong_wind_node = Node("No")
weak_wind_node = Node("Yes")
wind_node.add_child("Strong", strong_wind_node)
wind_node.add_child("Weak", weak_wind_node)
root_node.add_child("Rain", wind_node)
return Tree(root_node)
def test_get_all_descendants_empty(self):
root_node = Node("Root")
self.assertListEqual(root_node.get_all_descendants(), [])
def test_get_branches_no_children(self):
node = Node("test")
self.assertListEqual(node.get_branches(), [])
def create_tree(self):
"""
Creates play_tennis.data decision tree.
Returns:
tree: Tree
leaf_nodes: list(Node)
"""
root_node = Node("Outlook")
humidity_node = Node("Humidity")
high_humidity_node = Node("No")
normal_humidity_node = Node("Yes")
humidity_node.add_child("High", high_humidity_node)
humidity_node.add_child("Normal", normal_humidity_node)
root_node.add_child("Sunny", humidity_node)
overcast_node = Node("Yes")
root_node.add_child("Overcast", overcast_node)
wind_node = Node("Wind")
strong_wind_node = Node("No")
weak_wind_node = Node("Yes")
wind_node.add_child("Strong", strong_wind_node)
wind_node.add_child("Weak", weak_wind_node)
root_node.add_child("Rain", wind_node)
leaves = [high_humidity_node, normal_humidity_node, overcast_node,
strong_wind_node, weak_wind_node]
return Tree(root_node), leaves
def test_get_all_descendants_empty(self):
root_node = Node("Root")
self.assertListEqual(root_node.get_all_descendants(), [])
def test_get_all_descendants(self):
root_node = Node("Root")
child1 = Node("Child1")
child2 = Node("Child2")
root_node.add_child("child1", child1)
root_node.add_child("child2", child2)
grandchild1 = Node("GC1")
grandchild2 = Node("GC2")
child2.add_child("child1", grandchild1)
child2.add_child("child2", grandchild2)
assert_that(
root_node.get_all_descendants(),
contains_inanyorder(child1, child2, grandchild1, grandchild2))
def test_get_branches_no_children(self):
node = Node("test")
self.assertListEqual(node.get_branches(), [])
def create_tree(self):
"""
Creates play_tennis.data decision tree.
Returns:
tree: Tree
leaf_nodes: list(Node)
"""
root_node = Node("Outlook")
humidity_node = Node("Humidity")
high_humidity_node = Node("No")
normal_humidity_node = Node("Yes")
humidity_node.add_child("High", high_humidity_node)
humidity_node.add_child("Normal", normal_humidity_node)
root_node.add_child("Sunny", humidity_node)
overcast_node = Node("Yes")
root_node.add_child("Overcast", overcast_node)
wind_node = Node("Wind")
strong_wind_node = Node("No")
weak_wind_node = Node("Yes")
wind_node.add_child("Strong", strong_wind_node)
wind_node.add_child("Weak", weak_wind_node)
root_node.add_child("Rain", wind_node)
leaves = [
high_humidity_node, normal_humidity_node, overcast_node,
strong_wind_node, weak_wind_node
]
return Tree(root_node), leaves
