org.ai_heuristic.algo.classify

Class VarGain

java.lang.Object

org.ai_heuristic.functs.Function

org.ai_heuristic.algo.classify.VarGain

All Implemented Interfaces:

FunctionDef

public class VarGain
extends Function

This class implements an Information Gain style of calculation using a new averaged and scaled variance approach, but vertically not horizontally. The evaluation is a value of how cohesive the combined counts are for each variable. The dataset can store a list of keywords for each variable, for example, and the keyword lists will be combined and counted as a single list. This is then evaluated using a scaled variance value to determine how cohesive it is.

The algorithm is different to InformationGain by the way that it evaluates the dataset and also how the data is presented. Each list in the dataset should be a set of distinct values for a variable. The tabular dataset is again created by adding columns of type MetricValue to a MetricDataset and passing this as the parameter. For example:
dataPoints = new ArrayList();
dataPoints.add("a");
dataPoints.add("b");
dataPoints.add("d");
metricValue = MetricValue.toValue("dp1", valueType, dataPoints);
allDatasets.add(metricValue);
dataPoints = new ArrayList();
dataPoints.add("b");
dataPoints.add("d");
dataPoints.add("e");
metricValue = MetricValue.toValue("dp2", valueType, dataPoints);
allDatasets.add(metricValue);
dataPoints = new ArrayList();
dataPoints.add("a");
dataPoints.add("c");
dataPoints.add("e");
metricValue = MetricValue.toValue("dp3", valueType, dataPoints);
allDatasets.add(metricValue);
...
//repeat for the other data columns
...
MetricDataset evalDataset = MetricDataset.toDataset("ds1", valueType, allDatasets);
//initialise and run the algorithm
VarGain varGain = new VarGain(valueType);
double result = (Double)varGain.evaluate(evalDataset).getValue();

Author:

Kieran Greer

Field Summary

Fields inherited from class org.ai_heuristic.functs.Function

config, mathCompare, valueType

Constructor Summary

Constructors

Constructor and Description
VarGain(java.lang.String thisValueType) Create a new instance of VarGain.

Method Summary

Modifier and Type	Method and Description
ReplySet	evaluate(MetricDataset dataset) Evaluate a cohesive value, similar to an entropy value, for the combined variable list and count.
double	getCohesion() Get the cohesion value.
double	getMean() Get the mean value.
double	getVariance() Get the variance value.
protected void	initialise() Initialise the function values, setting the config parameters or other.
java.util.ArrayList<java.lang.String>	varsWithCount(int freq) Return a list of all variable names with the specified count.

Methods inherited from class org.ai_heuristic.functs.Function

checkValueType, createFunction, createFunction, createFunction, getConfigParams, innerObject, isLegalNumber, setConfigParams, setEvaluator, setValueType

Methods inherited from class java.lang.Object

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

Constructor Detail

VarGain

public VarGain(java.lang.String thisValueType)
        throws java.lang.Exception

Create a new instance of VarGain.

Parameters:

thisValueType - the type of object being evaluated. Can be null if set later or not used.

Throws:

java.lang.Exception - any error.

Method Detail

initialise

protected void initialise()

Initialise the function values, setting the config parameters or other.

Specified by:

initialise in class Function

evaluate

public ReplySet evaluate(MetricDataset dataset)
                  throws java.lang.Exception

Evaluate a cohesive value, similar to an entropy value, for the combined variable list and count.

Specified by:

evaluate in interface FunctionDef

Overrides:

evaluate in class Function

Parameters:

dataset - tabular list of keyword values. This should store a list of MetricValue entities that each store a set of values for any column or variables that are present.

Returns:

the entropy result for the combined tables variable list.

Throws:

java.lang.Exception - any error.

varsWithCount

public java.util.ArrayList<java.lang.String> varsWithCount(int freq)

Return a list of all variable names with the specified count.

Parameters:

freq - the frequency count to check for.

Returns:

a list of all variable names with that count number.

getMean

public double getMean()

Get the mean value.

Returns:

the value of mean.

getVariance

public double getVariance()

Get the variance value.

Returns:

the value of variance.

getCohesion

public double getCohesion()

Get the cohesion value.

Returns:

the value of cohesion.