nz.ac.waikato.mcennis.rat.graph.algorithm.evaluation
Class MeanErrorEvaluation

java.lang.Object
  nz.ac.waikato.mcennis.rat.graph.model.ModelShell
      nz.ac.waikato.mcennis.rat.graph.algorithm.evaluation.MeanErrorEvaluation

All Implemented Interfaces:

java.io.Serializable, Component, Algorithm, Model

public class MeanErrorEvaluation
extends ModelShell
implements Algorithm

Utilizes Given(user->artist) as ground truth and Derived(user->artist) as predicted values. Error is calculated from difference between derived and given link strengths. Derived links with no given are compared against link strength of 0 while the reverse are ignored. Herlocker, J., J. Konstan, L. Terveen, J. Reidl. 2004. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems 22(1):5-53

See Also:

Serialized Form

Field Summary

Fields inherited from class nz.ac.waikato.mcennis.rat.graph.model.ModelShell

listener

Constructor Summary

MeanErrorEvaluation()
Creates a new instance of Evaluation

Method Summary

void	execute(Graph g) Calculate all the evaluation metrics against the given graph.
java.util.List<IODescriptor>	getInputType() The input type describes all the different kinds of graph objects that are utilized (and hence required) by this object.
java.util.List<IODescriptor>	getOutputType() The output type describes all the different kinds of graph objects that are created during the execution of this algorithm.
Properties	getParameter() List of all parameters this component accepts.
Parameter	getParameter(java.lang.String param) Returns the specific parameter identified by its key-name.
void	init(Properties map) Parameters to be initialized 'name' - name of this instance of this algorithm.
protected void	meanError(Graph g, ActorQuery mode, LinkQuery source, LinkQuery derived)
protected void	meanSquaredError(Graph g, ActorQuery mode, LinkQuery source, LinkQuery derived)
MeanErrorEvaluation	prototype() All Components implement the prototype pattern.
protected void	rootMeanSquaredError(Graph g, ActorQuery mode, LinkQuery source, LinkQuery derived)
protected void	scaleRecommendations(Graph g, ActorQuery mode, LinkQuery source, LinkQuery derived)

Methods inherited from class nz.ac.waikato.mcennis.rat.graph.model.ModelShell

addListener, fireChange

Methods inherited from class java.lang.Object

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

Methods inherited from interface nz.ac.waikato.mcennis.rat.graph.model.Model

addListener

Constructor Detail

MeanErrorEvaluation

public MeanErrorEvaluation()

Creates a new instance of Evaluation

Method Detail

execute

public void execute(Graph g)

Calculate all the evaluation metrics against the given graph. TODO: add F-measure stastic

Specified by:

execute in interface Algorithm

Parameters:

g - graph to be modified

scaleRecommendations

protected void scaleRecommendations(Graph g,
                                    ActorQuery mode,
                                    LinkQuery source,
                                    LinkQuery derived)

meanError

protected void meanError(Graph g,
                         ActorQuery mode,
                         LinkQuery source,
                         LinkQuery derived)

meanSquaredError

protected void meanSquaredError(Graph g,
                                ActorQuery mode,
                                LinkQuery source,
                                LinkQuery derived)

rootMeanSquaredError

protected void rootMeanSquaredError(Graph g,
                                    ActorQuery mode,
                                    LinkQuery source,
                                    LinkQuery derived)

getInputType

public java.util.List<IODescriptor> getInputType()

Description copied from interface: Component

The input type describes all the different kinds of graph objects that are utilized (and hence required) by this object. This result is only guaranteed to be fixed if structural parameters are not modified. This is an empty array if there is no input.

Specified by:

getInputType in interface Component

Returns:

IODescriptor array for this component

See Also:

IODescriptor

getOutputType

public java.util.List<IODescriptor> getOutputType()

Description copied from interface: Component

The output type describes all the different kinds of graph objects that are created during the execution of this algorithm. The result is only guaranteed to be fixed if structural parameters are not modified. This is an empty array if there is no output.

Specified by:

getOutputType in interface Component

Returns:

IODescriptor array for this component

See Also:

IODescriptor

getParameter

public Properties getParameter()

Description copied from interface: Component

List of all parameters this component accepts. Each parameter also has a distinct key-name used when initializing the object using the init method. If there are no parameters, null is returned.

Specified by:

getParameter in interface Component

Returns:

read-only array of Parameters

getParameter

public Parameter getParameter(java.lang.String param)

Description copied from interface: Component

Returns the specific parameter identified by its key-name. If no parameter is found with this key-name, null is returned.

Specified by:

getParameter in interface Component

Parameters:

param - key-name of the parameter

Returns:

named parameter

init

public void init(Properties map)

Parameters to be initialized

1. 'name' - name of this instance of this algorithm. Deafult 'Evaluation'
2. 'relationGroundTruth' - type (relation) of link that describes ground truth relations between two actor types (modes). Default 'Given'
3. 'relationDerived' - type (relation) of link that describes calculated references to be evaluated between two modes. Deafult 'Derived'.
4. 'propertyPrefix' - prefix for the property names generated. Default 'Evaluation '.

Input 1 - Link
Input 2 - Link
Output 1-12 - Graph Property

Specified by:

init in interface Component

Parameters:

map - map of the given properties naming parameters and their values in a string

prototype

public MeanErrorEvaluation prototype()

Description copied from interface: Component

All Components implement the prototype pattern. The new parameter has no common resources to the original that are not static resources o the class.

Specified by:

prototype in interface Component

Specified by:

prototype in interface Algorithm

Returns:

default-parameter version of the same class as the original.