public abstract class ScoreClassifierParameterSet extends SequenceScoringParameterSet
Parameter
s for any
ScoreClassifier
.ParameterSet.ParameterList
alphabet, length
errorMessage, parameters, parent
Constructor and Description |
---|
ScoreClassifierParameterSet(Class<? extends ScoreClassifier> instanceClass,
AlphabetContainer alphabet,
int length,
byte algo,
AbstractTerminationCondition tc,
double lineps,
double startD,
boolean free,
OptimizableFunction.KindOfParameter kind)
The constructor for a simple, instantiated parameter set.
|
ScoreClassifierParameterSet(Class<? extends ScoreClassifier> instanceClass,
AlphabetContainer alphabet,
int length,
byte algo,
double eps,
double lineps,
double startD,
boolean free,
OptimizableFunction.KindOfParameter kind)
The constructor for a simple, instantiated parameter set.
|
ScoreClassifierParameterSet(Class<? extends ScoreClassifier> instanceClass,
boolean simple,
AlphabetContainer.AlphabetContainerType type,
boolean variableLength)
Creates a new
ScoreClassifierParameterSet with empty parameter
values. |
ScoreClassifierParameterSet(StringBuffer xml)
The standard constructor for the interface
Storable . |
Modifier and Type | Method and Description |
---|---|
String |
getInstanceComment()
Returns a comment (a textual description) of the class that can be
constructed using this
ParameterSet . |
String |
getInstanceName()
Returns the name of an instance of the class that can be constructed
using this
ParameterSet . |
AbstractTerminationCondition |
getTerminantionCondition()
This method returns the
AbstractTerminationCondition for stopping the training, e.g., if the
difference of the scores between two iterations is smaller than a given
threshold the training is stopped. |
boolean |
useOnlyFreeParameter()
This method indicates if only the free parameters shall be used.
|
clone, equals, fromXML, getAlphabetContainer, getLength, getNumberOfParameters, getParameterAt, hasDefaultOrIsSet, reset, toXML
getInstance, getInstanceClass
fromGalaxy, getAllParameterNames, getComment, getComment, getErrorMessage, getIndex, getName, getName, getParameterForName, getParent, initParameterList, initParameterList, isAtomic, isComparable, parametersLoaded, setParent, toGalaxy
public ScoreClassifierParameterSet(Class<? extends ScoreClassifier> instanceClass, boolean simple, AlphabetContainer.AlphabetContainerType type, boolean variableLength) throws Exception
ScoreClassifierParameterSet
with empty parameter
values.instanceClass
- the class of the instancesimple
- indicates whether the AlphabetContainer
shall be
simpletype
- the type of the AlphabetContainer
variableLength
- indicates whether the corresponding classifier can handle
sequences of arbitrary lengthException
- if the parameters could not be loadedSequenceScoringParameterSet.SequenceScoringParameterSet(Class,
de.jstacs.data.AlphabetContainer.AlphabetContainerType, boolean, boolean)
public ScoreClassifierParameterSet(StringBuffer xml) throws NonParsableException
Storable
.
Creates a new ScoreClassifierParameterSet
out of its XML
representation.xml
- the XML representation as StringBuffer
NonParsableException
- if the ScoreClassifierParameterSet
could not be
reconstructed out of the XML representation (the
StringBuffer
could not be parsed)SequenceScoringParameterSet.SequenceScoringParameterSet(StringBuffer)
,
Storable
public ScoreClassifierParameterSet(Class<? extends ScoreClassifier> instanceClass, AlphabetContainer alphabet, int length, byte algo, double eps, double lineps, double startD, boolean free, OptimizableFunction.KindOfParameter kind) throws Exception
instanceClass
- the class of the instancealphabet
- the alphabetlength
- the length of the sequences, 0 for homogeneousalgo
- the choice of algorithmeps
- the threshold for stopping the algorithmlineps
- the threshold for stopping the line search in the algorithmstartD
- the start distance for the line search in the algorithmfree
- indicates whether only the free parameters or all parameters
should be usedkind
- indicates the kind of class parameter initializationException
- if something went wrongSequenceScoringParameterSet.SequenceScoringParameterSet(Class, AlphabetContainer, int, boolean)
,
ScoreClassifierParameterSet(Class, AlphabetContainer, int, byte, AbstractTerminationCondition, double, double, boolean, de.jstacs.classifiers.differentiableSequenceScoreBased.OptimizableFunction.KindOfParameter)
,
SmallDifferenceOfFunctionEvaluationsCondition
public ScoreClassifierParameterSet(Class<? extends ScoreClassifier> instanceClass, AlphabetContainer alphabet, int length, byte algo, AbstractTerminationCondition tc, double lineps, double startD, boolean free, OptimizableFunction.KindOfParameter kind) throws Exception
instanceClass
- the class of the instancealphabet
- the alphabetlength
- the length of the sequences, 0 for homogeneousalgo
- the choice of algorithmtc
- the termination condition for stopping the algorithmlineps
- the threshold for stopping the line search in the algorithmstartD
- the start distance for the line search in the algorithmfree
- indicates whether only the free parameters or all parameters
should be usedkind
- indicates the kind of class parameter initializationException
- if something went wrongSequenceScoringParameterSet.SequenceScoringParameterSet(Class,
AlphabetContainer, int, boolean)
public boolean useOnlyFreeParameter()
true
if only the free parameters shall be used,
false
otherwisepublic String getInstanceName()
InstanceParameterSet
ParameterSet
.getInstanceName
in class InstanceParameterSet
public String getInstanceComment()
InstanceParameterSet
ParameterSet
.getInstanceComment
in class InstanceParameterSet
public AbstractTerminationCondition getTerminantionCondition() throws ParameterSetParser.NotInstantiableException
AbstractTerminationCondition
for stopping the training, e.g., if the
difference of the scores between two iterations is smaller than a given
threshold the training is stopped.AbstractTerminationCondition
for stopping the trainingParameterSetParser.NotInstantiableException
- if the AbstractTerminationCondition
could not be created from its ParameterSet