de.jstacs.sequenceScores.statisticalModels.trainable.discrete
Class Constraint

java.lang.Object
  de.jstacs.sequenceScores.statisticalModels.trainable.discrete.Constraint

All Implemented Interfaces:

Storable

Direct Known Subclasses:

HomogeneousTrainSM.HomCondProb, InhConstraint

public abstract class Constraint
extends Object
implements Storable

The main class for all constraints on models. This class centralizes all specific constraints (e.g. P(X₁=A,X₂=A)) from a partitioning constraint (e.g. all specific constraints for some given positions).

Author:

Jens Keilwagen

Field Summary

protected double[]	counts The counts for each specific constraint.
protected double[]	freq The frequencies estimated from the counts.
protected int[]	usedPositions The used positions.

Constructor Summary

protected	Constraint(int[] usedPositions, int n) The main constructor.
protected	Constraint(StringBuffer xml) The standard constructor for the interface Storable.

Method Summary

void	add(int index, double weight) Adds the given weight to the count with index index.
void	add(Sequence seq, int start, double weight) This method determines the specific constraint that is fulfilled by the Sequence seq and adds the weight to the specific counter.
protected abstract void	appendAdditionalInfo(StringBuffer xml) This method appends additional information that is not stored in the base class to the StringBuffer.
protected Constraint	clone()
abstract void	estimate(double ess) Estimates the (smoothed) relative frequencies using the ess (equivalent sample size).
protected void	estimateUnConditional(int start, int end, double pc, boolean exceptionWhenNoData) Estimates unconditionally.
protected abstract void	extractAdditionalInfo(StringBuffer xml) This method parses additional information from the StringBuffer that is not parsed in the base class.
double	getCount(int index) Returns the current count with index index.
abstract String	getDescription(AlphabetContainer con, int i) Returns the decoded symbol for the encoded symbol i.
double	getFreq(int index) Returns the current frequency with index index.
double	getFreq(Sequence seq, int start) This method determines the specific constraint that is fulfilled by the Sequence seq beginning at position start.
String	getFreqInfo(AlphabetContainer con) Returns an information about the stored frequencies.
int	getMarginalOrder() Returns the marginal order, i.e. the number of used random variables.
int	getNumberOfSpecificConstraints() Returns the number of specific constraints.
int	getPosition(int index) Returns the position with index index.
int[]	getPositions() Returns a clone of the array of used positions.
protected abstract String	getXMLTag() Returns the XML tag that is used for the class to en- or decode.
void	reset() This method resets all member variables that are in some way counters, frequencies, ...
void	resetCounts() This method allows to reset the internal field counts that is used for estimating the probabilities.
abstract int	satisfiesSpecificConstraint(Sequence seq, int start) This method returns the index of the specific constraint that is fulfilled by the Sequence seq beginning at position start.
abstract String	toString()
StringBuffer	toXML() This method returns an XML representation as StringBuffer of an instance of the implementing class.

Methods inherited from class java.lang.Object

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

Field Detail

counts

protected double[] counts

The counts for each specific constraint.

freq

protected double[] freq

The frequencies estimated from the counts.

usedPositions

protected int[] usedPositions

The used positions.

Constructor Detail

Constraint

protected Constraint(int[] usedPositions,
                     int n)
              throws IllegalArgumentException

The main constructor. Creates a new Constraint and checks that each position is used maximally once.

Parameters:

usedPositions - the used positions (will be cloned), have to be non-negative

n - the number of specific constraints

Throws:

IllegalArgumentException - if there are some fundamental errors in the arguments for the positions

Constraint

protected Constraint(StringBuffer xml)
              throws NonParsableException

The standard constructor for the interface Storable. Creates a new Constraint out of its XML representation.

Parameters:

xml - the XML representation as StringBuffer

Throws:

NonParsableException - if the Constraint could not be reconstructed out of the XML representation (the StringBuffer could not be parsed)

See Also:

Storable, extractAdditionalInfo(StringBuffer)

Method Detail

add

public final void add(int index,
                      double weight)

Adds the given weight to the count with index index.

Parameters:

index - the index

weight - the weight

add

public void add(Sequence seq,
                int start,
                double weight)

This method determines the specific constraint that is fulfilled by the Sequence seq and adds the weight to the specific counter.

Parameters:

seq - the sequence

start - the start position

weight - the weight for the sequence

See Also:

satisfiesSpecificConstraint(Sequence, int), add(int, double)

clone

protected Constraint clone()
                    throws CloneNotSupportedException

Overrides:

clone in class Object

Throws:

CloneNotSupportedException

estimate

public abstract void estimate(double ess)

Estimates the (smoothed) relative frequencies using the ess (equivalent sample size).

Parameters:

ess - the ess

estimateUnConditional

protected void estimateUnConditional(int start,
                                     int end,
                                     double pc,
                                     boolean exceptionWhenNoData)

Estimates unconditionally.

Parameters:

start - the start index

end - the end index

pc - the pseudocount for each parameter

exceptionWhenNoData - indicates if an (runtime) exception is thrown if no data was available to estimate the parameters

appendAdditionalInfo

protected abstract void appendAdditionalInfo(StringBuffer xml)

This method appends additional information that is not stored in the base class to the StringBuffer.

Parameters:

xml - the StringBuffer that is used for appending additional information

getCount

public double getCount(int index)

Returns the current count with index index.

Parameters:

index - the index

Returns:

the current count

getFreq

public double getFreq(int index)

Returns the current frequency with index index.

Parameters:

index - the index

Returns:

the current frequency

getFreq

public double getFreq(Sequence seq,
                      int start)

This method determines the specific constraint that is fulfilled by the Sequence seq beginning at position start.

Parameters:

seq - the Sequence

start - the start position

Returns:

the according frequency

See Also:

satisfiesSpecificConstraint(Sequence, int), getFreq(int)

getMarginalOrder

public int getMarginalOrder()

Returns the marginal order, i.e. the number of used random variables.

Returns:

the marginal order

getNumberOfSpecificConstraints

public int getNumberOfSpecificConstraints()

Returns the number of specific constraints.

Returns:

the number of specific constraints

getPosition

public int getPosition(int index)

Returns the position with index index.

Parameters:

index - the index

Returns:

the position with index index

getPositions

public int[] getPositions()

Returns a clone of the array of used positions.

Returns:

a clone of the array of used positions

getXMLTag

protected abstract String getXMLTag()

Returns the XML tag that is used for the class to en- or decode.

Returns:

the XML tag that is used for the class to en- or decode

reset

public void reset()

This method resets all member variables that are in some way counters, frequencies, ...

satisfiesSpecificConstraint

public abstract int satisfiesSpecificConstraint(Sequence seq,
                                                int start)

This method returns the index of the specific constraint that is fulfilled by the Sequence seq beginning at position start.

Parameters:

seq - the sequence

start - the start position

Returns:

the index of the fulfilled, specific constraint

extractAdditionalInfo

protected abstract void extractAdditionalInfo(StringBuffer xml)
                                       throws NonParsableException

This method parses additional information from the StringBuffer that is not parsed in the base class.

Parameters:

xml - the StringBuffer to be parsed

Throws:

NonParsableException - if something with the parsing went wrong

toString

public abstract String toString()

Overrides:

toString in class Object

toXML

public StringBuffer toXML()

Description copied from interface: Storable

This method returns an XML representation as StringBuffer of an instance of the implementing class.

Specified by:

toXML in interface Storable

Returns:

the XML representation

getDescription

public abstract String getDescription(AlphabetContainer con,
                                      int i)

Returns the decoded symbol for the encoded symbol i.

Parameters:

con - the AlphabetContainer

i - the encoded symbol

Returns:

the decoded symbol for the encoded symbol i

getFreqInfo

public String getFreqInfo(AlphabetContainer con)

Returns an information about the stored frequencies.

Parameters:

con - the AlphabetContainer

Returns:

an information about the stored frequencies

resetCounts

public void resetCounts()

This method allows to reset the internal field counts that is used for estimating the probabilities.

See Also:

add(int, double), add(Sequence, int, double), estimate(double)