magpie.statistics.performance

Class ClustererStatistics

java.lang.Object

magpie.statistics.performance.ClustererStatistics

All Implemented Interfaces:

java.io.Serializable, Printable

public class ClustererStatistics
extends java.lang.Object
implements java.io.Serializable, Printable

Characterize the results from a clusterer. For now, this class will measure:

• How many entries where clustered.
• Number of attributes used during clustering
• Number of clusters formed
• Number of entries in each cluster
• Mean in each attribute for each cluster, sorted by which attribute has the greatest deviation between classes

Developer's Note: This class is not yet Commandable

Implemented Print Commands:

dist - Print fraction of entries entries in each cluster

attr [<number>] - Prints out clustering power of attributes (ordered by power)
number: Number of top attributes to print (default = all of them)

clust [<number attr>] - Print out the mean of each attribute of all entries in each cluster
number attr: Number of attributes to print (default = all of them)

See Also:

BaseClusterer, Serialized Form

Constructor Summary

Constructors

Constructor and Description
ClustererStatistics()

Method Summary

Modifier and Type	Method and Description
java.lang.String	about() Prints a simple status message about this object
void	evaluate(Dataset[] Clusters) Characterize the performance of a cluster
boolean	isTrained()
java.lang.String	printAttributes() Print the name and separation power of all attributes used during clustering
java.lang.String	printAttributes(int number) Print the name and separation power of a certain number of attributes
java.lang.String	printClusters() Print out attributes name, separation power, and mean for each cluster for all attributes used in clustering
java.lang.String	printClusters(int numAttributesToPrint) Print out attributes name, separation power, and mean for each cluster for a certain number of attributes
java.lang.String	printCommand(java.util.List<java.lang.String> Command) Handles more complicated printing commands.
java.lang.String	printDescription(boolean htmlFormat) Print full name of object, and a simple description of the options.
java.lang.String	printDistribution() Print the distribution between each cluster

Methods inherited from class java.lang.Object

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

Constructor Detail

ClustererStatistics

public ClustererStatistics()

Method Detail

isTrained

public boolean isTrained()

Returns:

Whether this object has evaluated at Clusterer.

evaluate

public void evaluate(Dataset[] Clusters)

Characterize the performance of a cluster

Parameters:

Clusters - Clusters formed by clusterer during training

about

public java.lang.String about()

Description copied from interface: Printable

Prints a simple status message about this object

Specified by:

about in interface Printable

Returns:

Short status message

printDescription

public java.lang.String printDescription(boolean htmlFormat)

Description copied from interface: Printable

Print full name of object, and a simple description of the options. This description should print enough information to reproduce how this object was created, but not necessarily enough to run it (e.g., coefficients for the model).

Example: For a model training a separate WekaRegression for intermetallics

magpie.models.regression.SplitRegression

Splitter: AllMetalsSplitter
All Metals: magpie.models.regression.WekaRegression trees.REPTree
Contains Nonmetal: magpie.regression.LASSORegreession -maxterms 2

Specified by:

printDescription in interface Printable

Parameters:

htmlFormat - Whether format for output to an HTML page (e.g., <div> to create indentation) or for printing to screen.

Returns:

String describing the model

See Also:

#printModel()

printDistribution

public java.lang.String printDistribution()

Print the distribution between each cluster

Returns:

String accounting for distribution between each cluster

printAttributes

public java.lang.String printAttributes()

Print the name and separation power of all attributes used during clustering

Returns:

Table listing all of that information

printAttributes

public java.lang.String printAttributes(int number)

Print the name and separation power of a certain number of attributes

Parameters:

number - Number to print

Returns:

Table listing all of that information

printClusters

public java.lang.String printClusters()

Print out attributes name, separation power, and mean for each cluster for all attributes used in clustering

Returns:

Table with all of this information

printClusters

public java.lang.String printClusters(int numAttributesToPrint)

Print out attributes name, separation power, and mean for each cluster for a certain number of attributes

Parameters:

numAttributesToPrint - Number of attributes to print (storing with most powerful)

Returns:

Table with all of this information

printCommand

public java.lang.String printCommand(java.util.List<java.lang.String> Command)
                              throws java.lang.Exception

Description copied from interface: Printable

Handles more complicated printing commands.

Specified by:

printCommand in interface Printable

Parameters:

Command - Command specifying what to print

Returns:

String formatted as requested

Throws:

java.lang.Exception - If command not understood