gov.sandia.cognition.learning.algorithm.tree

Class AbstractDecisionTreeLearner<InputType,OutputType>

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.algorithm.AbstractIterativeAlgorithm

gov.sandia.cognition.learning.algorithm.tree.AbstractDecisionTreeLearner<InputType,OutputType>

Type Parameters:

InputType - The input type for the decision tree.

OutputType - The output type for the decision tree.

All Implemented Interfaces:

IterativeAlgorithm, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

Direct Known Subclasses:

CategorizationTreeLearner, RegressionTreeLearner

public abstract class AbstractDecisionTreeLearner<InputType,OutputType>
extends AbstractIterativeAlgorithm
implements java.io.Serializable

The AbstractDecisionTreeLearner implements common functionality for learning algorithms that learn a decision tree.

Since:

2.0

Author:

Justin Basilico

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected DeciderLearner<? super InputType,OutputType,?,?>	deciderLearner The learning algorithm for the decision function.

Fields inherited from class gov.sandia.cognition.algorithm.AbstractIterativeAlgorithm

DEFAULT_ITERATION, iteration

Constructor Summary

Constructors

Constructor and Description
AbstractDecisionTreeLearner() Creates a new instance of AbstractDecisionTreeLearner
AbstractDecisionTreeLearner(DeciderLearner<? super InputType,OutputType,?,?> deciderLearner) Creates a new instance of AbstractDecisionTreeLearner.

Method Summary

Modifier and Type	Method and Description
boolean	areAllOutputsEqual(java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data) Determines if all of the output values in the collection are equal.
AbstractDecisionTreeLearner<InputType,OutputType>	clone() This makes public the clone method on the Object class and removes the exception that it throws.
DeciderLearner<? super InputType,OutputType,?,?>	getDeciderLearner() Gets the learner for the decision function.
protected <DecisionType> void	learnChildNodes(AbstractDecisionTreeNode<InputType,OutputType,DecisionType> node, java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data, Categorizer<? super InputType,? extends DecisionType> decider) Learns the child nodes for a node using the given data at the node plus the decision function for the node.
protected abstract AbstractDecisionTreeNode<InputType,OutputType,?>	learnNode(java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data, AbstractDecisionTreeNode<InputType,OutputType,?> parent) Recursively learns the decision tree using the given collection of data, returning the created node.
void	setDeciderLearner(DeciderLearner<? super InputType,OutputType,?,?> deciderLearner) Sets the learner for the decision function.
<DecisionType> java.util.Map<DecisionType,java.util.LinkedList<InputOutputPair<? extends InputType,OutputType>>>	splitData(java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data, Categorizer<? super InputType,? extends DecisionType> decider) Splits the data into new lists based on the given decision function.

Methods inherited from class gov.sandia.cognition.algorithm.AbstractIterativeAlgorithm

addIterativeAlgorithmListener, fireAlgorithmEnded, fireAlgorithmStarted, fireStepEnded, fireStepStarted, getIteration, getListeners, removeIterativeAlgorithmListener, setIteration, setListeners

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

deciderLearner

protected DeciderLearner<? super InputType,OutputType,?,?> deciderLearner

The learning algorithm for the decision function.

Constructor Detail

AbstractDecisionTreeLearner

public AbstractDecisionTreeLearner()

Creates a new instance of AbstractDecisionTreeLearner

AbstractDecisionTreeLearner

public AbstractDecisionTreeLearner(DeciderLearner<? super InputType,OutputType,?,?> deciderLearner)

Creates a new instance of AbstractDecisionTreeLearner.

Parameters:

deciderLearner - The learner for the decision function

Method Detail

clone

public AbstractDecisionTreeLearner<InputType,OutputType> clone()

Description copied from class: AbstractCloneableSerializable

This makes public the clone method on the Object class and removes the exception that it throws. Its default behavior is to automatically create a clone of the exact type of object that the clone is called on and to copy all primitives but to keep all references, which means it is a shallow copy. Extensions of this class may want to override this method (but call super.clone() to implement a "smart copy". That is, to target the most common use case for creating a copy of the object. Because of the default behavior being a shallow copy, extending classes only need to handle fields that need to have a deeper copy (or those that need to be reset). Some of the methods in ObjectUtil may be helpful in implementing a custom clone method. Note: The contract of this method is that you must use super.clone() as the basis for your implementation.

Specified by:

clone in interface CloneableSerializable

Overrides:

clone in class AbstractIterativeAlgorithm

Returns:

A clone of this object.

learnNode

protected abstract AbstractDecisionTreeNode<InputType,OutputType,?> learnNode(java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data,
                                                                              AbstractDecisionTreeNode<InputType,OutputType,?> parent)

Recursively learns the decision tree using the given collection of data, returning the created node.

Parameters:

data - The set of data to learn a node from.

parent - The parent node.

Returns:

The decision tree node learned from the given data.

learnChildNodes

protected <DecisionType> void learnChildNodes(AbstractDecisionTreeNode<InputType,OutputType,DecisionType> node,
                                              java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data,
                                              Categorizer<? super InputType,? extends DecisionType> decider)

Learns the child nodes for a node using the given data at the node plus the decision function for the node. It recursively calls the learnNode method on each child and then adds the child to the given node.

Type Parameters:

DecisionType - The type of decision function.

Parameters:

node - The node to learn the children for. The child nodes are added by this method.

data - The data at the node to learn the children for.

decider - The decision function to use.

splitData

public <DecisionType> java.util.Map<DecisionType,java.util.LinkedList<InputOutputPair<? extends InputType,OutputType>>> splitData(java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data,
                                                                                                                                  Categorizer<? super InputType,? extends DecisionType> decider)

Splits the data into new lists based on the given decision function.

Type Parameters:

DecisionType - The type of decision function.

Parameters:

data - The data to split.

decider - The decision function.

Returns:

A mapping of category decided by the decision function to a list of examples that have that value as indicated by the decision function.

areAllOutputsEqual

public boolean areAllOutputsEqual(java.util.Collection<? extends InputOutputPair<? extends InputType,OutputType>> data)

Determines if all of the output values in the collection are equal. It does this in a fast way by getting the first value and then checking it against the subsequent values and failing if one does not match.

Parameters:

data - The data to check for equality on the outputs.

Returns:

True if all the output values are equal; otherwise, false.

getDeciderLearner

public DeciderLearner<? super InputType,OutputType,?,?> getDeciderLearner()

Gets the learner for the decision function.

Returns:

deciderLearner The learner for the decision function

setDeciderLearner

public void setDeciderLearner(DeciderLearner<? super InputType,OutputType,?,?> deciderLearner)

Sets the learner for the decision function.

Parameters:

deciderLearner - The learner for the decision function