de.jstacs.classifier.scoringFunctionBased.sampling
Class SamplingScoreBasedClassifierParameterSet

java.lang.Object
  de.jstacs.parameters.ParameterSet
      de.jstacs.parameters.InstanceParameterSet
          de.jstacs.parameters.SequenceScoringParameterSet
              de.jstacs.classifier.scoringFunctionBased.sampling.SamplingScoreBasedClassifierParameterSet

All Implemented Interfaces:

GalaxyConvertible, RangeIterator, Storable, Cloneable

Direct Known Subclasses:

SamplingGenDisMixClassifierParameterSet

public abstract class SamplingScoreBasedClassifierParameterSet
extends SequenceScoringParameterSet

ParameterSet to instantiate a SamplingScoreBasedClassifier.

Author:

Jan Grau

Nested Class Summary

Nested classes/interfaces inherited from class de.jstacs.parameters.ParameterSet

ParameterSet.ParameterList

Field Summary

Fields inherited from class de.jstacs.parameters.SequenceScoringParameterSet

alphabet, length

Fields inherited from class de.jstacs.parameters.ParameterSet

errorMessage, parameters, parent, ranged

Constructor Summary

SamplingScoreBasedClassifierParameterSet(Class<? extends SamplingScoreBasedClassifier> instanceClass, AlphabetContainer alphabet, int length, int numStarts, int testSamplings, int stationarySamplings, String outfilePrefix)
Create a new SamplingScoreBasedClassifierParameterSet with a grouped sampling scheme, sampling all parameters (and not only the free ones), and adaption of the variance.

SamplingScoreBasedClassifierParameterSet(Class<? extends SamplingScoreBasedClassifier> instanceClass, AlphabetContainer alphabet, int length, int numStarts, SamplingScoreBasedClassifier.SamplingScheme scheme, int testSamplings, int stationarySamplings, boolean freeParameters, boolean adaptVariance, String outfilePrefix)
Create a new SamplingScoreBasedClassifierParameterSet.

Method Summary

SamplingScoreBasedClassifierParameterSet	clone() Creates a full clone (deep copy) of this ParameterSet.
boolean	getAdaptVariance() Returns true if the sampling variance shall be adapted to the size of the event space of a random variable
boolean	getFreeParameters() Returns true if only free parameters shall be used
int	getNumberOfStarts() Returns the number of independent sampling starts
int	getNumberOfStationarySamplings() Returns the number of samplings steps in the stationary phase
int	getNumberOfTestSamplings() Returns the number of samplings between checks for the stationary phase
String	getOutfilePrefix() Returns the prefix of the temporary files for storing sampled parameter values
SamplingScoreBasedClassifier.SamplingScheme	getSamplingScheme() Returns the sampling scheme
protected void	loadParameters() Loads the parameters for this ParameterSet.
void	setNumberOfStarts(int i) Sets the number of starts to i

Methods inherited from class de.jstacs.parameters.SequenceScoringParameterSet

equals, fromXML, getAlphabetContainer, getLength, getNumberOfParameters, getParameterAt, hasDefaultOrIsSet, replaceParametersWithRangedInstance, reset, toXML

Methods inherited from class de.jstacs.parameters.InstanceParameterSet

getInstance, getInstanceClass, getInstanceComment, getInstanceName

Methods inherited from class de.jstacs.parameters.ParameterSet

fromGalaxy, getErrorMessage, getId, getIndex, getNumberOfValues, getParent, initParameterList, initParameterList, isAtomic, isRanged, makeRanged, next, parametersLoaded, propagateId, recieveId, resetToFirst, setParent, simplify, toGalaxy, valuesToString

Methods inherited from class java.lang.Object

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

Constructor Detail

SamplingScoreBasedClassifierParameterSet

public SamplingScoreBasedClassifierParameterSet(Class<? extends SamplingScoreBasedClassifier> instanceClass,
                                                AlphabetContainer alphabet,
                                                int length,
                                                int numStarts,
                                                SamplingScoreBasedClassifier.SamplingScheme scheme,
                                                int testSamplings,
                                                int stationarySamplings,
                                                boolean freeParameters,
                                                boolean adaptVariance,
                                                String outfilePrefix)
                                         throws Exception

Create a new SamplingScoreBasedClassifierParameterSet.

Parameters:

instanceClass - the class, which must be a subclass of SamplingScoreBasedClassifier

alphabet - the alphabet of the classifier

length - the length of the sequences that can be classified

numStarts - the number of independent samplings

scheme - the sampling scheme

testSamplings - the number of samplings between checks for the lenght of the burn-in phase

stationarySamplings - the number of samplings in the stationary phase

freeParameters - if only free parameters shall be used

adaptVariance - if the variance shall be adapted to the size of the event space of a random variable

outfilePrefix - the prefix of the temporary files for storing the parameters

Throws:

Exception - if the parameters could not be created

See Also:

SamplingScoreBasedClassifier

SamplingScoreBasedClassifierParameterSet

public SamplingScoreBasedClassifierParameterSet(Class<? extends SamplingScoreBasedClassifier> instanceClass,
                                                AlphabetContainer alphabet,
                                                int length,
                                                int numStarts,
                                                int testSamplings,
                                                int stationarySamplings,
                                                String outfilePrefix)
                                         throws Exception

Create a new SamplingScoreBasedClassifierParameterSet with a grouped sampling scheme, sampling all parameters (and not only the free ones), and adaption of the variance.

Parameters:

instanceClass - the class, which must be a subclass of SamplingScoreBasedClassifier

alphabet - the alphabet of the classifier

length - the length of the sequences that can be classified

numStarts - the number of independent samplings

testSamplings - the number of samplings between checks for the lenght of the burn-in phase

stationarySamplings - the number of samplings in the stationary phase

outfilePrefix - the prefix of the temporary files for storing the parameters

Throws:

Exception - if the parameters could not be created

See Also:

SamplingScoreBasedClassifier

Method Detail

clone

public SamplingScoreBasedClassifierParameterSet clone()
                                               throws CloneNotSupportedException

Description copied from class: ParameterSet

Creates a full clone (deep copy) of this ParameterSet. As a convenience-method the user can use fillWithStandardFieldsForClone(ParameterSet) on a newly created instance of a subclass of ParameterSet to obtain a clone/copy of all standard member variables (those already defined in ParameterSet) in the passed ParameterSet. Using this method, the cloning process becomes merely three-step:

• Create a new instance of your subclass of ParameterSet, most likely with an empty constructor or the one taking just the instance class.
• Call this.fillWithStandardFieldsForClone on this instance.
• Return the instance.

This method fulfills the conventions of Object's method Object.clone().

Overrides:

clone in class SequenceScoringParameterSet

Returns:

a deep clone/copy of this ParameterSet

Throws:

CloneNotSupportedException

loadParameters

protected void loadParameters()
                       throws Exception

Description copied from class: ParameterSet

Loads the parameters for this ParameterSet. This is in most cases done by calling ParameterSet.initParameterList() or ParameterSet.initParameterList(int) to initialize ParameterSet.parameters and afterwards filling ParameterSet.parameters with instances of subclasses of Parameter.

Specified by:

loadParameters in class ParameterSet

Throws:

Exception - if the parameters could not be loaded

See Also:

Parameter, ParameterSet.parameters, ParameterSet.initParameterList(), ParameterSet.initParameterList(int)

getNumberOfStarts

public int getNumberOfStarts()

Returns the number of independent sampling starts

Returns:

the number of starts

getSamplingScheme

public SamplingScoreBasedClassifier.SamplingScheme getSamplingScheme()

Returns the sampling scheme

Returns:

the scheme

getNumberOfTestSamplings

public int getNumberOfTestSamplings()

Returns the number of samplings between checks for the stationary phase

Returns:

te number of samplings

getNumberOfStationarySamplings

public int getNumberOfStationarySamplings()

Returns the number of samplings steps in the stationary phase

Returns:

the number of steps

getFreeParameters

public boolean getFreeParameters()

Returns true if only free parameters shall be used

Returns:

if only free parameters shall be used

getAdaptVariance

public boolean getAdaptVariance()

Returns true if the sampling variance shall be adapted to the size of the event space of a random variable

Returns:

if the sampling variance shall be adapted

See Also:

SamplingScoreBasedClassifier

getOutfilePrefix

public String getOutfilePrefix()

Returns the prefix of the temporary files for storing sampled parameter values

Returns:

the prefix

setNumberOfStarts

public void setNumberOfStarts(int i)
                       throws SimpleParameter.IllegalValueException

Sets the number of starts to i

Parameters:

i - the new number of starts

Throws:

SimpleParameter.IllegalValueException - if this value is not allowed