com.emphysic.myriad.core.data.roi

Class SGDROIFinder

java.lang.Object

com.emphysic.myriad.core.data.roi.SGDROIFinder

All Implemented Interfaces:

MLROIFinder, ROIFinder, ObjectMap, com.esotericsoftware.kryo.KryoSerializable

public class SGDROIFinder
extends java.lang.Object
implements MLROIFinder

SGDROIFinder - machine learning region of interest detection based on the Stochastic Gradient Descent (SGD) algorithm.

Constructor Summary

Constructors

Constructor and Description
SGDROIFinder() Creates a new SGD ROI finder using the Hinge loss function and a regularization set to 1.0E-5.
SGDROIFinder(org.sgdtk.Loss lossFunction, double regularization) Creates a new SGD ROI finder using the specified loss function and regularization.
SGDROIFinder(org.sgdtk.Model mdl) Instantiates a new SGD ROI finder from an existing SGD model.

Method Summary

Modifier and Type	Method and Description
org.sgdtk.Learner	getLearner() Returns the model trainer.
org.sgdtk.Model	getLinearModel() Returns the current SGD model.
int	getNumFeatures() Returns the number of features used to train this model
java.util.Map<java.lang.String,java.lang.Object>	getObjectMap() Creates a map of the important fields for the instance, suitable for serialization.
long	getSerializationVersion() Returns the current version of the serialization format.
int	getVersion() Returns the current class version.
void	initCurrentVersion(java.util.Map<java.lang.String,java.lang.Object> objectMap) Initializes an instance with a current-version object graph.
boolean	isROI(Dataset dataset) Predict whether a sample contains a region of interest
boolean	isROI(double[] data) Predict whether a sample contains a region of interest
void	legacyRead(com.esotericsoftware.kryo.Kryo kryo, com.esotericsoftware.kryo.io.Input input)
void	legacyWrite(com.esotericsoftware.kryo.Kryo kryo, com.esotericsoftware.kryo.io.Output output)
static void	main(java.lang.String[] args)
double	negativeClass() Returns the value of the negative label.
double	positiveClass() Returns the value of the positive label.
double	predict(Dataset dataset) Returns the prediction of the specified sample.
double	predict(double[] data) Returns the prediction of the specified sample.
void	setLearner(org.sgdtk.Learner learner) Sets the model trainer.
void	setLinearModel(org.sgdtk.Model linearModel) Sets the SGD model
void	train(double[][] X, int[] y) Trains the model with another set of samples, creating the model if required.
boolean	validDims(double[] data) Ensure a given sample has correct number of features.

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.emphysic.myriad.core.data.roi.ROIFinder

fromFile

Methods inherited from interface com.emphysic.myriad.core.data.util.ObjectMap

init, initPreviousVersion, initUnknownVersion, load, read, save, write

Constructor Detail

SGDROIFinder

public SGDROIFinder()

Creates a new SGD ROI finder using the Hinge loss function and a regularization set to 1.0E-5.

SGDROIFinder

public SGDROIFinder(org.sgdtk.Loss lossFunction,
                    double regularization)

Creates a new SGD ROI finder using the specified loss function and regularization.

Parameters:

lossFunction - e.g. HingeLoss, LogLoss, SquaredHingeLoss,

regularization - regularization parameter to penalize model complexity

SGDROIFinder

public SGDROIFinder(org.sgdtk.Model mdl)

Instantiates a new SGD ROI finder from an existing SGD model.

Parameters:

mdl - SGD model

Method Detail

train

public void train(double[][] X,
                  int[] y)
           throws java.lang.Exception

Trains the model with another set of samples, creating the model if required.

Specified by:

train in interface MLROIFinder

Parameters:

X - N examples with M features per example

y - N labels for the N examples in X

Throws:

java.lang.Exception - if an error occurs

isROI

public boolean isROI(double[] data)

Predict whether a sample contains a region of interest

Specified by:

isROI in interface ROIFinder

Parameters:

data - raw data to examine

Returns:

true if the sample contains an ROI, false otherwise

isROI

public boolean isROI(Dataset dataset)

Predict whether a sample contains a region of interest

Specified by:

isROI in interface ROIFinder

Parameters:

dataset - raw data to examine

Returns:

true if the sample contains an ROI, false otherwise

getSerializationVersion

public long getSerializationVersion()

Description copied from interface: ObjectMap

Returns the current version of the serialization format. Increments when the serialization format changes, i.e. backwards compatibility is broken.

Specified by:

getSerializationVersion in interface ObjectMap

Returns:

serialization version

getVersion

public int getVersion()

Description copied from interface: ObjectMap

Returns the current class version. Class version increments when the class changes but doesn't necessarily break compatibility with serialization.

Specified by:

getVersion in interface ObjectMap

Returns:

class version

getObjectMap

public java.util.Map<java.lang.String,java.lang.Object> getObjectMap()

Description copied from interface: ObjectMap

Creates a map of the important fields for the instance, suitable for serialization.

Specified by:

getObjectMap in interface ObjectMap

Returns:

"object map" of the instance

initCurrentVersion

public void initCurrentVersion(java.util.Map<java.lang.String,java.lang.Object> objectMap)

Description copied from interface: ObjectMap

Initializes an instance with a current-version object graph.

Specified by:

initCurrentVersion in interface ObjectMap

Parameters:

objectMap - object graph for initialization

predict

public double predict(double[] data)

Returns the prediction of the specified sample.

Specified by:

predict in interface MLROIFinder

Parameters:

data - sample

Returns:

predicted label / value

predict

public double predict(Dataset dataset)

Returns the prediction of the specified sample.

Specified by:

predict in interface MLROIFinder

Parameters:

dataset - sample

Returns:

predicted label / value

validDims

public boolean validDims(double[] data)

Ensure a given sample has correct number of features.

Parameters:

data - sample

Returns:

true if the number of features in the sample = number of features the model was trained on

getLearner

public org.sgdtk.Learner getLearner()

Returns the model trainer.

Returns:

current model trainer

setLearner

public void setLearner(org.sgdtk.Learner learner)

Sets the model trainer.

Parameters:

learner - new model trainer

getLinearModel

public org.sgdtk.Model getLinearModel()

Returns the current SGD model.

Returns:

current model

setLinearModel

public void setLinearModel(org.sgdtk.Model linearModel)

Sets the SGD model

Parameters:

linearModel - new model

getNumFeatures

public int getNumFeatures()

Returns the number of features used to train this model

Returns:

number of features @see #Dataset.getSize()

positiveClass

public double positiveClass()

Returns the value of the positive label.

Specified by:

positiveClass in interface MLROIFinder

Returns:

positive label value

negativeClass

public double negativeClass()

Returns the value of the negative label.

Specified by:

negativeClass in interface MLROIFinder

Returns:

negative label value

legacyWrite

public void legacyWrite(com.esotericsoftware.kryo.Kryo kryo,
                        com.esotericsoftware.kryo.io.Output output)

legacyRead

public void legacyRead(com.esotericsoftware.kryo.Kryo kryo,
                       com.esotericsoftware.kryo.io.Input input)

main

public static void main(java.lang.String[] args)
                 throws java.lang.Exception

Throws:

java.lang.Exception