edu.illinois.cs.cogcomp.lbjava.learn

Class SparseAveragedPerceptron.AveragedWeightVector

java.lang.Object

edu.illinois.cs.cogcomp.lbjava.learn.SparseWeightVector

edu.illinois.cs.cogcomp.lbjava.learn.SparseAveragedPerceptron.AveragedWeightVector

All Implemented Interfaces:

Serializable, Cloneable

Enclosing class:

SparseAveragedPerceptron

public static class SparseAveragedPerceptron.AveragedWeightVector
extends SparseWeightVector

This implementation of a sparse weight vector associates two doubles with each Feature. The first plays the role of the usual weight vector, and the second accumulates multiples of examples on which mistakes were made to help implement the weighted average.

Author:

Nick Rizzolo

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
edu.illinois.cs.cogcomp.core.datastructures.vectors.DVector	averagedWeights Together with SparseWeightVector.weights, this vector provides enough information to reconstruct the average of all weight vectors arrived at during the course of learning.
protected int	examples Counts the total number of training examples this vector has seen.

Fields inherited from class edu.illinois.cs.cogcomp.lbjava.learn.SparseWeightVector

defaultCapacity, defaultWeight, weights

Constructor Summary

Constructors

Constructor and Description
AveragedWeightVector() Simply instantiates the weight vectors.
AveragedWeightVector(double[] w) Simply initializes the weight vectors.
AveragedWeightVector(edu.illinois.cs.cogcomp.core.datastructures.vectors.DVector w) Simply initializes the weight vectors.

Method Summary

Modifier and Type	Method and Description
Object	clone() Returns a copy of this AveragedWeightVector.
void	correctExample() Increments the examples variable.
double	dot(int[] exampleFeatures, double[] exampleValues) Takes the dot product of this AveragedWeightVector with the argument vector, using the hard coded default weight.
double	dot(int[] exampleFeatures, double[] exampleValues, double defaultW) Takes the dot product of this AveragedWeightVector with the argument vector, using the specified default weight when one is not yet present in this vector.
SparseWeightVector	emptyClone() Returns a new, empty weight vector with the same parameter settings as this one.
double	getAveragedWeight(int featureIndex, double defaultW) Returns the averaged weight of the given feature.
int	getExamples() Returns the examples variable.
void	read(edu.illinois.cs.cogcomp.core.datastructures.vectors.ExceptionlessInputStream in) Reads the representation of a weight vector with this object's run-time type from the given stream, overwriting the data in this object.
void	scaledAdd(int[] exampleFeatures, double[] exampleValues, double factor) Performs pairwise addition of the feature values in the given vector scaled by the given factor, modifying this weight vector, using the specified default weight when a feature from the given vector is not yet present in this vector.
void	scaledAdd(int[] exampleFeatures, double[] exampleValues, double factor, double defaultW) Performs pairwise addition of the feature values in the given vector scaled by the given factor, modifying this weight vector, using the specified default weight when a feature from the given vector is not yet present in this vector.
double	simpleDot(int[] exampleFeatures, double[] exampleValues) Takes the dot product of the regular, non-averaged, Perceptron weight vector with the given vector, using the hard coded default weight.
double	simpleDot(int[] exampleFeatures, double[] exampleValues, double defaultW) Takes the dot product of the regular, non-averaged, Perceptron weight vector with the given vector, using the specified default weight when a feature is not yet present in this vector.
protected void	updateAveragedWeight(int featureIndex, double w) Adds a new value to the current averaged weight indexed by the supplied feature index.
void	write(edu.illinois.cs.cogcomp.core.datastructures.vectors.ExceptionlessOutputStream out) Writes the weight vector's internal representation in binary form.
void	write(PrintStream out) Outputs the contents of this SparseWeightVector into the specified PrintStream.
void	write(PrintStream out, Lexicon lex) Outputs the contents of this SparseWeightVector into the specified PrintStream.

Methods inherited from class edu.illinois.cs.cogcomp.lbjava.learn.SparseWeightVector

clear, getWeight, getWeight, pairwiseMultiply, readWeightVector, scaledAdd, scaledMultiply, scaledMultiply, setWeight, setWeight, size, toString, toString, toStringJustWeights, toStringJustWeights

Methods inherited from class java.lang.Object

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

Field Detail

averagedWeights

public edu.illinois.cs.cogcomp.core.datastructures.vectors.DVector averagedWeights

Together with SparseWeightVector.weights, this vector provides enough information to reconstruct the average of all weight vectors arrived at during the course of learning.

examples

protected int examples

Counts the total number of training examples this vector has seen.

Constructor Detail

AveragedWeightVector

public AveragedWeightVector()

Simply instantiates the weight vectors.

AveragedWeightVector

public AveragedWeightVector(double[] w)

Simply initializes the weight vectors.

Parameters:

w - An array of weights.

AveragedWeightVector

public AveragedWeightVector(edu.illinois.cs.cogcomp.core.datastructures.vectors.DVector w)

Simply initializes the weight vectors.

Parameters:

w - A vector of weights.

Method Detail

correctExample

public void correctExample()

Increments the examples variable.

getExamples

public int getExamples()

Returns the examples variable.

getAveragedWeight

public double getAveragedWeight(int featureIndex,
                                double defaultW)

Returns the averaged weight of the given feature.

Parameters:

featureIndex - The feature index.

defaultW - The default weight.

Returns:

The weight of the feature.

dot

public double dot(int[] exampleFeatures,
                  double[] exampleValues)

Takes the dot product of this AveragedWeightVector with the argument vector, using the hard coded default weight.

Overrides:

dot in class SparseWeightVector

Parameters:

exampleFeatures - The example's array of feature indices.

exampleValues - The example's array of feature values.

Returns:

The computed dot product.

dot

public double dot(int[] exampleFeatures,
                  double[] exampleValues,
                  double defaultW)

Takes the dot product of this AveragedWeightVector with the argument vector, using the specified default weight when one is not yet present in this vector.

Overrides:

dot in class SparseWeightVector

Parameters:

exampleFeatures - The example's array of feature indices.

exampleValues - The example's array of feature values.

defaultW - The default weight.

Returns:

The computed dot product.

simpleDot

public double simpleDot(int[] exampleFeatures,
                        double[] exampleValues)

Takes the dot product of the regular, non-averaged, Perceptron weight vector with the given vector, using the hard coded default weight.

Parameters:

exampleFeatures - The example's array of feature indices.

exampleValues - The example's array of feature values.

Returns:

The computed dot product.

simpleDot

public double simpleDot(int[] exampleFeatures,
                        double[] exampleValues,
                        double defaultW)

Takes the dot product of the regular, non-averaged, Perceptron weight vector with the given vector, using the specified default weight when a feature is not yet present in this vector.

Parameters:

exampleFeatures - The example's array of feature indices.

exampleValues - The example's array of feature values.

defaultW - An initial weight for new features.

Returns:

The computed dot product.

scaledAdd

public void scaledAdd(int[] exampleFeatures,
                      double[] exampleValues,
                      double factor)

Performs pairwise addition of the feature values in the given vector scaled by the given factor, modifying this weight vector, using the specified default weight when a feature from the given vector is not yet present in this vector. The default weight is used to initialize new feature weights.

Overrides:

scaledAdd in class SparseWeightVector

Parameters:

exampleFeatures - The example's array of feature indices.

exampleValues - The example's array of feature values.

factor - The scaling factor.

scaledAdd

public void scaledAdd(int[] exampleFeatures,
                      double[] exampleValues,
                      double factor,
                      double defaultW)

Performs pairwise addition of the feature values in the given vector scaled by the given factor, modifying this weight vector, using the specified default weight when a feature from the given vector is not yet present in this vector.

Overrides:

scaledAdd in class SparseWeightVector

Parameters:

exampleFeatures - The example's array of feature indices.

exampleValues - The example's array of feature values.

factor - The scaling factor.

defaultW - An initial weight for new features.

updateAveragedWeight

protected void updateAveragedWeight(int featureIndex,
                                    double w)

Adds a new value to the current averaged weight indexed by the supplied feature index.

Parameters:

featureIndex - The feature index.

w - The value to add to the current weight.

write

public void write(PrintStream out)

Outputs the contents of this SparseWeightVector into the specified PrintStream. The string representation starts with a "Begin" annotation, ends with an "End" annotation, and without a Lexicon passed as a parameter, the weights are simply printed in the order of their integer indices.

Overrides:

write in class SparseWeightVector

Parameters:

out - The stream to write to.

write

public void write(PrintStream out,
                  Lexicon lex)

Outputs the contents of this SparseWeightVector into the specified PrintStream. The string representation starts with a "Begin" annotation, ends with an "End" annotation, and lists each feature with its corresponding weight on the same, separate line in between.

Overrides:

write in class SparseWeightVector

Parameters:

out - The stream to write to.

lex - The feature lexicon.

write

public void write(edu.illinois.cs.cogcomp.core.datastructures.vectors.ExceptionlessOutputStream out)

Writes the weight vector's internal representation in binary form.

Overrides:

write in class SparseWeightVector

Parameters:

out - The output stream.

read

public void read(edu.illinois.cs.cogcomp.core.datastructures.vectors.ExceptionlessInputStream in)

Reads the representation of a weight vector with this object's run-time type from the given stream, overwriting the data in this object.

This method is appropriate for reading weight vectors as written by write(ExceptionlessOutputStream).

Overrides:

read in class SparseWeightVector

Parameters:

in - The input stream.

clone

public Object clone()

Returns a copy of this AveragedWeightVector.

Overrides:

clone in class SparseWeightVector

Returns:

A copy of this AveragedWeightVector.

emptyClone

public SparseWeightVector emptyClone()

Returns a new, empty weight vector with the same parameter settings as this one.

Overrides:

emptyClone in class SparseWeightVector

Returns:

An empty weight vector.