def _create_tree(self,
instances,
candidate_attribute_indexes,
target_attribute_index=0,
default_class=None):
class_labels_and_counts = Counter(
[instance[target_attribute_index] for instance in instances])
if not instances or not candidate_attribute_indexes:
return default_class
elif len(class_labels_and_counts) == 1:
class_label = class_labels_and_counts.most_common(1)[0][0]
return class_label
else:
default_class = simple_ml.majority_value(instances,
target_attribute_index)
best_index = simple_ml.choose_best_attribute_index(
instances, candidate_attribute_indexes, target_attribute_index)
tree = {best_index: {}}
partitions = simple_ml.split_instances(instances, best_index)
remaining_candidate_attribute_indexes = [
i for i in candidate_attribute_indexes if i != best_index
]
for attribute_value in partitions:
subtree = self._create_tree(
partitions[attribute_value],
remaining_candidate_attribute_indexes,
target_attribute_index, default_class)
tree[best_index][attribute_value] = subtree
return tree
def _create(self,
instances,
candidate_attribute_indexes,
target_attribute_index=0,
default_class=None,
trace=0,
max_height=None,
min_support=0,
epsilon=1.0,
parent_id=-1,
parent_value=None,
parent_node=None):
'''
Returns a new decision tree by recursively selecting and splitting instances based on
the highest information_gain of the candidate_attribute_indexes.
The class label is found in target_attribute_index.
The default class is the majority value for that branch of the tree.
A positive trace value will generate trace information with increasing levels of indentation.
max_height is the maximum levels the tree can have. Assume trace is non-zero.
min_support is the minimum number of records needed to make a split. Otherwise the node becomes a leaf.
epsilon budget
Derived from the simplified ID3 algorithm presented in Building Decision Trees in Python by Christopher Roach,
http://www.onlamp.com/pub/a/python/2006/02/09/ai_decision_trees.html?page=3
'''
instances = instances[:]
self._id_tracker += 1
class_labels_and_counts = dict(
Counter(
[instance[target_attribute_index] for instance in instances]))
#print( "class_labels_and_counts = "+str(class_labels_and_counts) )
if epsilon is not None:
class_labels_and_counts = simple_ml.add_laplace_noise(
class_labels_and_counts, 1., epsilon) # sensitivity = 1
#print( "new class_labels_counts = "+str(class_labels_and_counts) )
partitionSize = 0
for k, v in class_labels_and_counts.items():
partitionSize += v
#print("noisy partitionSize = "+str(partitionSize))
class_label = Counter(class_labels_and_counts).most_common(1)[0][0]
# If the dataset is empty or the candidate attributes list is empty, return the default value.
if partitionSize == 0:
#if trace:
# print( '{}Using default class {}'.format('< ' * trace, default_class) )
return node.Node(self._id_tracker,
trace,
None,
"_Leaf",
parent_id,
parent_value,
parent_node, {default_class: 1},
children=None) #default_class
# If the dataset is empty or the candidate attributes list is empty, return the default value.
elif not candidate_attribute_indexes:
#if trace:
# print( '{}Using default class {}'.format('< ' * trace, default_class) )
return node.Node(self._id_tracker,
trace,
None,
"_Leaf",
parent_id,
parent_value,
parent_node,
class_labels_and_counts,
children=None) #default_class
# If all the records have the same class label, return that class label
elif len(Counter(class_labels_and_counts)) == 1:
#if trace:
# print( '{}All {} records have label {}'.format('< ' * trace, partitionSize, class_label) )
return node.Node(self._id_tracker,
trace,
None,
"_Leaf",
parent_id,
parent_value,
parent_node,
class_labels_and_counts,
children=None) #class_label
# If there aren't enough records in the node to make another split, return the majority class label
elif partitionSize < min_support:
#if trace:
# print( '{} {} records is below the minimum support required for more splits. The majority label is {}'.format('< ' * trace, partitionSize, class_label) )
return node.Node(self._id_tracker,
trace,
None,
"_Leaf",
parent_id,
parent_value,
parent_node,
class_labels_and_counts,
children=None) #class_label
# If the tree has reached the maximum number of levels (depth), return the majority class label. Assumes trace is non-zero.
elif trace >= max_height:
#if trace:
# print( '{}The maximum tree depth has been reached. The {} records in this leaf have majority label {}'.format('< ' * trace, partitionSize, class_label) )
return node.Node(self._id_tracker,
trace,
None,
"_Leaf",
parent_id,
parent_value,
parent_node,
class_labels_and_counts,
children=None) #class_label
# MAKE MORE SPLITS
default_class = class_label #simple_ml.majority_value(instances, target_attribute_index)
# Choose the next best attribute index to best classify the records
worst_case_sens = 1. - ((partitionSize / (partitionSize + 1))**2 +
(1 / (partitionSize + 1))**2)
#print( "worst_case_sens="+str(worst_case_sens) )
if trace == 1: # if root node
candi = [
i for i in candidate_attribute_indexes
if i not in self._previous_roots
]
best_index = simple_ml.choose_best_attribute_index(
instances,
candi,
target_attribute_index,
epsilon=epsilon,
sensitivity=worst_case_sens)
else:
best_index = simple_ml.choose_best_attribute_index(
instances,
candidate_attribute_indexes,
target_attribute_index,
epsilon=epsilon,
sensitivity=worst_case_sens)
#if trace:
# print( '{}Creating tree node for attribute index {}'.format('> ' * trace, best_index) )
# Create a new decision tree node with the best attribute index and an empty dictionary object (for now)
#tree = {best_index:{}}
current_node = node.Node(self._id_tracker,
trace,
best_index,
self._attribute_names[best_index],
parent_id,
parent_value,
parent_node,
class_labels_and_counts,
children=[])
# Create a new decision tree sub-node (branch) for each of the values in the best attribute field
partitions = simple_ml.split_instances(instances, best_index)
# Remove that attribute from the set of candidates for further splits
remaining_candidate_attribute_indexes = [
i for i in candidate_attribute_indexes if i != best_index
]
''' For every value in the chosen attribute, make a subtree '''
tracecopy = trace + 1
curr_id = self._id_tracker
for attribute_value in partitions:
#if trace:
# print( '{}Creating subtree for value {} ({}, {}, {}, {})'.format(
# '> ' * trace,
# attribute_value,
# len(partitions[attribute_value]),
# len(remaining_candidate_attribute_indexes),
# target_attribute_index,
# default_class)
# )
# Create a subtree for each value of the the best attribute
subtree = self._create(partitions[attribute_value],
remaining_candidate_attribute_indexes,
target_attribute_index, default_class,
tracecopy if trace else 0, max_height,
min_support, epsilon, curr_id,
attribute_value, current_node)
# Add the new subtree to the empty dictionary object in the new tree/node we just created
#tree[best_index][attribute_value] = subtree
current_node.add_child(subtree)
self._node_list.append(subtree)
#print('.', end='')
return current_node #tree
def _create_tree(self,
instances,
candidate_attribute_indexes,
target_attribute_index=0,
default_class=None,
trace=0):
class_labels_and_counts = Counter(
[instance[target_attribute_index] for instance in instances])
# If the dataset is empty or the candidate attributes list is empty,
# return the default class label
if not instances or not candidate_attribute_indexes:
if trace:
print('{}Using default class {}'.format(
'< ' * trace, default_class))
return default_class
# If all the instances have the same class label, return that class label
elif len(class_labels_and_counts) == 1:
class_label = class_labels_and_counts.most_common(1)[0][0]
if trace:
print('{}All {} instances have label {}'.format(
'< ' * trace, len(instances), class_label))
return class_label
# Otherwise, create a new subtree and add it to the tree
else:
default_class = majority_value(instances, target_attribute_index)
# Choose the next best attribute index to best classify the instances
best_index = choose_best_attribute_index(
instances, candidate_attribute_indexes, target_attribute_index)
if trace:
print('{}Creating tree node for attribute index {}'.format(
'> ' * trace, best_index))
# Create a new decision tree node with the best attribute index
# and an empty dictionary object (for now)
tree = {best_index: {}}
# Create a new decision tree sub-node (branch)
# for each of the values in the best attribute field
partitions = split_instances(instances, best_index)
# Remove that attribute from the set of candidates for further splits
remaining_candidate_attribute_indexes = [
i for i in candidate_attribute_indexes if i != best_index
]
for attribute_value in partitions:
if trace:
print('{}Creating subtree for value {} ({}, {}, {}, {})'.
format('> ' * trace, attribute_value,
len(partitions[attribute_value]),
len(remaining_candidate_attribute_indexes),
target_attribute_index, default_class))
# Create a subtree for each value of the the best attribute
subtree = self._create_tree(
partitions[attribute_value],
remaining_candidate_attribute_indexes,
target_attribute_index, default_class)
# Add the new subtree to the empty dictionary object
# in the new tree/node created above
tree[best_index][attribute_value] = subtree
return tree
def _create(self,
instances,
candidate_attribute_indexes,
target_attribute_index=0,
default_class=None,
trace=0):
'''
Returns a new decision tree by recursively selecting and splitting instances based on
the highest information_gain of the candidate_attribute_indexes.
The class label is found in target_attribute_index.
The default class is the majority value for that branch of the tree.
A positive trace value will generate trace information with increasing levels of indentation.
Derived from the simplified ID3 algorithm presented in Building Decision Trees in Python by Christopher Roach,
http://www.onlamp.com/pub/a/python/2006/02/09/ai_decision_trees.html?page=3
'''
instances = instances[:]
class_labels_and_counts = Counter(
[instance[target_attribute_index] for instance in instances])
# If the dataset is empty or the candidate attributes list is empty, return the default value.
if not instances or not candidate_attribute_indexes:
if trace:
print '{}Using default class {}'.format(
'< ' * trace, default_class)
return default_class
# If all the instances have the same class label, return that class label
elif len(class_labels_and_counts) == 1:
class_label = class_labels_and_counts.most_common(1)[0][0]
if trace:
print '{}All {} instances have label {}'.format(
'< ' * trace, len(instances), class_label)
return class_label
else:
default_class = simple_ml.majority_value(instances,
target_attribute_index)
# Choose the next best attribute index to best classify the instances
best_index = simple_ml.choose_best_attribute_index(
instances, candidate_attribute_indexes, target_attribute_index)
if trace:
print '{}Creating tree node for attribute index {}'.format(
'> ' * trace, best_index)
# Create a new decision tree node with the best attribute index and an empty dictionary object (for now)
tree = {best_index: {}}
# Create a new decision tree sub-node (branch) for each of the values in the best attribute field
partitions = simple_ml.split_instances(instances, best_index)
# Remove that attribute from the set of candidates for further splits
remaining_candidate_attribute_indexes = [
i for i in candidate_attribute_indexes if i != best_index
]
for attribute_value in partitions:
if trace:
print '{}Creating subtree for value {} ({}, {}, {}, {})'.format(
'> ' * trace, attribute_value,
len(partitions[attribute_value]),
len(remaining_candidate_attribute_indexes),
target_attribute_index, default_class)
# Create a subtree for each value of the the best attribute
subtree = self._create(partitions[attribute_value],
remaining_candidate_attribute_indexes,
target_attribute_index, default_class,
trace + 1 if trace else 0)
# Add the new subtree to the empty dictionary object in the new tree/node we just created
tree[best_index][attribute_value] = subtree
return tree
