bodhidharma
Class PreferencesPanel

java.lang.Object
  extended by java.awt.Component
      extended by java.awt.Container
          extended by javax.swing.JComponent
              extended by javax.swing.JPanel
                  extended by bodhidharma.PreferencesPanel
All Implemented Interfaces:
java.awt.event.ActionListener, java.awt.image.ImageObserver, java.awt.MenuContainer, java.io.Serializable, java.util.EventListener, javax.accessibility.Accessible

public class PreferencesPanel
extends javax.swing.JPanel
implements java.awt.event.ActionListener

Part of the Bodhidharma automatic music classification project. This is the panel of the GUI that allows users to set preferences.

The Neural Net Preferences button allows the user to change the settings for neural networks. The Genetic Algorithm Preferences button allows the user to change the settings for genetic algorithms.

The Load Preferences, Save Preferences and Save Preferences As buttons allow the user to save the current preference settins.

See the descriptions of the methods below or the on-line help in order to see what each preference does.

The savePreferencesFile method can be called to save the preferences. The other public methods return the values of preferences.

Note that these preferences only affect behaviour at instantiation of objects, and subsequent changes will have no effect on existing objects. Exception are the Classify Into Root Categories, Classify Into Direct Descendants of Parents, Classify Into All Leaf Categories and Classify Using Round Robin Ensembles preferences, which play a roll during classification as well as training.

See Also:
BioKNearestNeighbour, FeedForwardNerualNetwork, ConfigureFileLocationsJFrame, MainJFrame, Serialized Form
Author:
Cory McKay

Nested Class Summary
 
Nested classes/interfaces inherited from class javax.swing.JPanel
javax.swing.JPanel.AccessibleJPanel
 
Nested classes/interfaces inherited from class javax.swing.JComponent
javax.swing.JComponent.AccessibleJComponent
 
Nested classes/interfaces inherited from class java.awt.Container
java.awt.Container.AccessibleAWTContainer
 
Nested classes/interfaces inherited from class java.awt.Component
java.awt.Component.AccessibleAWTComponent, java.awt.Component.BltBufferStrategy, java.awt.Component.FlipBufferStrategy
 
Field Summary
 GeneticAlgorithmJFrame ga_settings
          The basic parameters of new genetic algorithms that are to be created.
 NeuralNetworkJFrame network_settings
          The basic parameters of new neural networks that are to be created.
 MainJFrame parent_window
           
 
Fields inherited from class javax.swing.JComponent
accessibleContext, listenerList, TOOL_TIP_TEXT_KEY, ui, UNDEFINED_CONDITION, WHEN_ANCESTOR_OF_FOCUSED_COMPONENT, WHEN_FOCUSED, WHEN_IN_FOCUSED_WINDOW
 
Fields inherited from class java.awt.Component
BOTTOM_ALIGNMENT, CENTER_ALIGNMENT, LEFT_ALIGNMENT, RIGHT_ALIGNMENT, TOP_ALIGNMENT
 
Fields inherited from interface java.awt.image.ImageObserver
ABORT, ALLBITS, ERROR, FRAMEBITS, HEIGHT, PROPERTIES, SOMEBITS, WIDTH
 
Constructor Summary
PreferencesPanel(MainJFrame parent)
          Basic constructor that configures and instantiates the panel.
 
Method Summary
 void actionPerformed(java.awt.event.ActionEvent event)
          Calls the appropriate methods when the buttons are pressed.
 double getAllLeafRelativeWeighing()
          Returns the relative weighting to be given to the leaf classifier when the results of multiple classifiers are combined.
 double getClassifierVsFeatureGAMultiplier()
          Returns multiplier applied to the number of GA iterations for feature selections and weightings in order to calculate classifier selections and weightings.
 double getHierarchalRelativeWeighing()
          Returns the relative weighting to be given to the hierarchal classifiers when the results of multiple classifiers are combined.
 double getInternalTrainingFraction()
          Returns the fraction of training samples that the user has selected that will actually be used for training when feature selection and weighting are calculated for one-dimensional features.
 int getLinesToSkipWhenReportingTrainingErrors()
          Returns the interval at which training errors are reported.
 double getMaxGATrainingErrorForEarlyEnding()
          Return the maximum acceptable change in error selected by the user for GA feature selection training error rates that will allow training to be stopped early.
 double getMaxNNTrainingErrorForEarlyEnding()
          Return the maximum acceptable error selected by the user for FeedForwardNeuralNetwork training error rates that will allow training to be stopped early.
 int getMinGATrainingIterationsForEarlyEnding()
          Returns the minimum number of consecutive iterations which the user has selected must go by when feature selection training a GA where the error is below the maximum error rate in order for training to stop early.
 double getMinimumAutomaticQualificationScore()
          Returns the minimum score that a category must have to automatically be counted as a first choice during classification.
 double getMinimumScoreToBeSecondChoice()
          Returns the minimum score that a recording must have to qualify as a second choice during classification.
 double getMinimumScoreToQualify()
          Returns the minimum score that a recording must have to qualify as a first choice during classification.
 int getMinNNTrainingIterationsForEarlyEnding()
          Returns the minimum number of consecutive iterations which the user has selected must go by when training a FeedForwardNeuralNetwork where the error is below the maximum error rate in order for training to stop early.
 int getNumberGAIterations()
          Returns the maximum number of generations that should be performed for feature (but not classifier) selections and weightings.
 int getNumberNNIterations()
          Returns the maximum number of generations that should be performed for FeedForwardNeuralNetwork Return a negative value if the use has selected to automatically check if training should be stopped before this number has been reached.
 double getPercentageBelowHighestToBeSecondChoice()
          Returns the percentage below the score of the highest performer at which a category will be classified as a second choice.
 double getPercentageBelowHighestToQualify()
          Returns the percentage below the score of the highest performer at which a category will be classified as a first choice.
 double getRoundRobinDivisor()
          Returns the divisor that is used to divide all round robin scores during classification.
 double getRoundRobinRelativeWeighing()
          Returns the relative weighting to be given to the round classifiers when the results of multiple classifiers are combined.
 double getTimeBetweenProgressBarPolls()
          Returns the time in milliseconds between progress bar polls.
 double getTrainingFraction()
          Returns the fraction of candidate recordings to use for training.
 boolean reportScoresWithWinningCategories()
          Returns whether or not classifier scores for each winning category are reported along with the categories.
 boolean reportSecondaryWinningCategories()
          Returns whether or not classifier scores for secondary choices for winning category are reported along with the winning categories.
 void savePreferencesFile(java.lang.String comments, boolean is_basic_save)
          Saves a preferences_file XML file with the contents specified in the current fields.
 boolean shouldBioKNNsUseFeatureSelection()
          Returns true if the user has selected the option of having BioKNearestNeighbour classifiers perform feature selection.
 boolean shouldBioKNNsUseFeatureWeighting()
          Returns true if the user has selected the option of having BioKNearestNeighbour classifiers perform feature weighting.
 boolean shouldClassifyIntoAllLeafCategories()
          Returns whether or not training/classification should be done where recordings are classified into all leaf categories.
 boolean shouldClassifyIntoDirectDescendantsOfParentCategories()
          Returns whether or not training/classification should be done where recordings are classified into direct descendants of each parent category.
 boolean shouldClassifyIntoRootCategories()
          Returns whether or not training/classification should be done where recordings are classified into the root categories.
 boolean shouldClassifyUsingRoundRobin()
          Returns whether or not round robin ensembles should be trained / used during classification.
 boolean shouldDisplayClassifierSelectionTrainingError()
          Returns whether or not the classification report should include the classifier selection training error for an ensemble of classifiers.
 boolean shouldDisplayClassifierSettings()
          Returns whether or not classifier settings should be included in classification reports.
 boolean shouldDisplayClassifiersSelected()
          Returns whether or not the selection/weighting report should include the classifiers selected for an ensemble of classifiers.
 boolean shouldDisplayClassifiersWeightings()
          Returns whether or not the selection/weighting report should include the classifier weightings for an ensemble of classifiers.
 boolean shouldDisplayClassifierWeightingTrainingError()
          Returns whether or not the classification report should include the classifier weighting training error for an ensemble of classifiers.
 boolean shouldDisplayCombinedClassificationResultsForEachRecording()
          Returns whether or not the classification report should include the combined classification results (i.e.
 boolean shouldDisplayCombinedClassificationScoresForEachRecording()
          Returns whether or not the classification report should include the combined classification scores for each category of each recording by an ensemble of classifiers.
 boolean shouldDisplayConfusionMatrix()
          Returns whether or not the classification report should include a confusion matrix.
 boolean shouldDisplayFeatureSelectionWeightingTrainingError()
          Returns whether or not the classification report should include the one-dimensional feature selection or weighting training error for an ensemble of classifiers.
 boolean shouldDisplayIndividualClassifierResultsForEachRecording()
          Returns whether or not the classification report should include separately, for each classifier, the classification results (i.e.
 boolean shouldDisplayIndividualClassifierScoresForEachRecording()
          Returns whether or not the classification report should include, separately for each classifier, the classification scores for each category of each recording by an ensemble of classifiers.
 boolean shouldDisplayListOfElligibleCategories()
          Returns whether or not the classification report should include a list of elligible categories into which recordings can be classified by an ensemble of classifiers.
 boolean shouldDisplayModelResultsAlongWithResults()
          Returns whether or not the classification reports of resulting categories should also include the correct classifications, if available.
 boolean shouldDisplayModelResultsForEeachRecordingInSeparateTable()
          Returns whether or not the classification report should include, as a separate table, a list of the elligible classsification categories for an ensemble of classifiers, along with their code numbers.
 boolean shouldDisplayMultiDimClassifierTrainingError()
          Returns whether or not the classification report should include the training error for the multi-dimensional classifiers in an ensemble of classifiers.
 boolean shouldDisplayOneDimensionalFeaturesSelected()
          Returns whether or not the selection/weighting report should include the one-dimensional features selected for an ensemble of classifiers.
 boolean shouldDisplayOneDimensionalFeatureWeightings()
          Returns whether or not the selection/weighting report should include the one-dimensional feature weightings for an ensemble of classifiers.
 boolean shouldDisplayRootCategorySuccessRates()
          Returns whether or not to display root category success rates.
 boolean shouldDisplaySuccessRatesForClassifiers()
          Returns whether or not the classification report should include the successful classification statistics for the combined and individual classifiers for an ensemble of classifiers.
 boolean shouldDisplayTrainingRecordingNames()
          Returns whether or not the training report should include the names and model leaf categories of the recordings used to train it.
 boolean shouldDisplayTrainingTimesInRawSeconds()
          Returns whether or not training times should be reported as raw seconds.
 boolean shouldOnlyPickOneWinnerForCombinedClassification()
          Returns whether or not only one winning category is permitted per recorcing.
 boolean shouldOnlyUseBestForRoundRobin()
          Returns whether or not all but the highest round robin score should be set to 0.
 boolean shouldSelectClassifiersInEachEnsemble()
          Returns true if the user has selected the option of having classifier selection automatically applied to classifiers in each NN_BioKNN_Ensemble.
 boolean shouldUseFeaturesMarkedAsSelectionCandidates()
          Returns true if the user has selected the option of using features marked as Selection Candidates in the FeaturesPanel for feature selection and returns false if the user has instead selected the option of using the featues marked as having Overide Status in the FeaturesPanel for feature selection.
 boolean shouldUseMultiDimensionalFeaturesInTraining()
          Returns true if the user has selected the option of using multi-dimensional features (and therefore FeedForwardNetworks classifiers) in training.
 boolean shouldUseOneDimensionalFeaturesInTraining()
          Returns true if the user has selected the option of using one-dimensional features (and therefore BioKNearestNeighbour classifiers in training.
 boolean shouldWeightClassifiersInEachEnsemble()
          Returns true if the user has selected the option of having classifier weightings automatically calculated internally in each NN_BioKNN_Ensemble.
 
Methods inherited from class javax.swing.JPanel
getAccessibleContext, getUI, getUIClassID, paramString, setUI, updateUI
 
Methods inherited from class javax.swing.JComponent
addAncestorListener, addNotify, addVetoableChangeListener, computeVisibleRect, contains, createToolTip, disable, enable, firePropertyChange, firePropertyChange, firePropertyChange, fireVetoableChange, getActionForKeyStroke, getActionMap, getAlignmentX, getAlignmentY, getAncestorListeners, getAutoscrolls, getBorder, getBounds, getClientProperty, getComponentGraphics, getComponentPopupMenu, getConditionForKeyStroke, getDebugGraphicsOptions, getDefaultLocale, getFontMetrics, getGraphics, getHeight, getInheritsPopupMenu, getInputMap, getInputMap, getInputVerifier, getInsets, getInsets, getListeners, getLocation, getMaximumSize, getMinimumSize, getNextFocusableComponent, getPopupLocation, getPreferredSize, getRegisteredKeyStrokes, getRootPane, getSize, getToolTipLocation, getToolTipText, getToolTipText, getTopLevelAncestor, getTransferHandler, getVerifyInputWhenFocusTarget, getVetoableChangeListeners, getVisibleRect, getWidth, getX, getY, grabFocus, isDoubleBuffered, isLightweightComponent, isManagingFocus, isOpaque, isOptimizedDrawingEnabled, isPaintingTile, isRequestFocusEnabled, isValidateRoot, paint, paintBorder, paintChildren, paintComponent, paintImmediately, paintImmediately, print, printAll, printBorder, printChildren, printComponent, processComponentKeyEvent, processKeyBinding, processKeyEvent, processMouseEvent, processMouseMotionEvent, putClientProperty, registerKeyboardAction, registerKeyboardAction, removeAncestorListener, removeNotify, removeVetoableChangeListener, repaint, repaint, requestDefaultFocus, requestFocus, requestFocus, requestFocusInWindow, requestFocusInWindow, resetKeyboardActions, reshape, revalidate, scrollRectToVisible, setActionMap, setAlignmentX, setAlignmentY, setAutoscrolls, setBackground, setBorder, setComponentPopupMenu, setDebugGraphicsOptions, setDefaultLocale, setDoubleBuffered, setEnabled, setFocusTraversalKeys, setFont, setForeground, setInheritsPopupMenu, setInputMap, setInputVerifier, setMaximumSize, setMinimumSize, setNextFocusableComponent, setOpaque, setPreferredSize, setRequestFocusEnabled, setToolTipText, setTransferHandler, setUI, setVerifyInputWhenFocusTarget, setVisible, unregisterKeyboardAction, update
 
Methods inherited from class java.awt.Container
add, add, add, add, add, addContainerListener, addImpl, addPropertyChangeListener, addPropertyChangeListener, applyComponentOrientation, areFocusTraversalKeysSet, countComponents, deliverEvent, doLayout, findComponentAt, findComponentAt, getComponent, getComponentAt, getComponentAt, getComponentCount, getComponents, getComponentZOrder, getContainerListeners, getFocusTraversalKeys, getFocusTraversalPolicy, getLayout, getMousePosition, insets, invalidate, isAncestorOf, isFocusCycleRoot, isFocusCycleRoot, isFocusTraversalPolicyProvider, isFocusTraversalPolicySet, layout, list, list, locate, minimumSize, paintComponents, preferredSize, printComponents, processContainerEvent, processEvent, remove, remove, removeAll, removeContainerListener, setComponentZOrder, setFocusCycleRoot, setFocusTraversalPolicy, setFocusTraversalPolicyProvider, setLayout, transferFocusBackward, transferFocusDownCycle, validate, validateTree
 
Methods inherited from class java.awt.Component
action, add, addComponentListener, addFocusListener, addHierarchyBoundsListener, addHierarchyListener, addInputMethodListener, addKeyListener, addMouseListener, addMouseMotionListener, addMouseWheelListener, bounds, checkImage, checkImage, coalesceEvents, contains, createImage, createImage, createVolatileImage, createVolatileImage, disableEvents, dispatchEvent, enable, enableEvents, enableInputMethods, firePropertyChange, firePropertyChange, firePropertyChange, firePropertyChange, firePropertyChange, firePropertyChange, getBackground, getBounds, getColorModel, getComponentListeners, getComponentOrientation, getCursor, getDropTarget, getFocusCycleRootAncestor, getFocusListeners, getFocusTraversalKeysEnabled, getFont, getForeground, getGraphicsConfiguration, getHierarchyBoundsListeners, getHierarchyListeners, getIgnoreRepaint, getInputContext, getInputMethodListeners, getInputMethodRequests, getKeyListeners, getLocale, getLocation, getLocationOnScreen, getMouseListeners, getMouseMotionListeners, getMousePosition, getMouseWheelListeners, getName, getParent, getPeer, getPropertyChangeListeners, getPropertyChangeListeners, getSize, getToolkit, getTreeLock, gotFocus, handleEvent, hasFocus, hide, imageUpdate, inside, isBackgroundSet, isCursorSet, isDisplayable, isEnabled, isFocusable, isFocusOwner, isFocusTraversable, isFontSet, isForegroundSet, isLightweight, isMaximumSizeSet, isMinimumSizeSet, isPreferredSizeSet, isShowing, isValid, isVisible, keyDown, keyUp, list, list, list, location, lostFocus, mouseDown, mouseDrag, mouseEnter, mouseExit, mouseMove, mouseUp, move, nextFocus, paintAll, postEvent, prepareImage, prepareImage, processComponentEvent, processFocusEvent, processHierarchyBoundsEvent, processHierarchyEvent, processInputMethodEvent, processMouseWheelEvent, remove, removeComponentListener, removeFocusListener, removeHierarchyBoundsListener, removeHierarchyListener, removeInputMethodListener, removeKeyListener, removeMouseListener, removeMouseMotionListener, removeMouseWheelListener, removePropertyChangeListener, removePropertyChangeListener, repaint, repaint, repaint, resize, resize, setBounds, setBounds, setComponentOrientation, setCursor, setDropTarget, setFocusable, setFocusTraversalKeysEnabled, setIgnoreRepaint, setLocale, setLocation, setLocation, setName, setSize, setSize, show, show, size, toString, transferFocus, transferFocusUpCycle
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Field Detail

network_settings

public NeuralNetworkJFrame network_settings
The basic parameters of new neural networks that are to be created.


ga_settings

public GeneticAlgorithmJFrame ga_settings
The basic parameters of new genetic algorithms that are to be created.


parent_window

public MainJFrame parent_window
Constructor Detail

PreferencesPanel

public PreferencesPanel(MainJFrame parent)
Basic constructor that configures and instantiates the panel.

Parameters:
parent - Name of the MainJFrame window that holds this panel.
See Also:
ConfigureFileLocationsJFrame, MainJFrame
Method Detail

actionPerformed

public void actionPerformed(java.awt.event.ActionEvent event)
Calls the appropriate methods when the buttons are pressed.

Specified by:
actionPerformed in interface java.awt.event.ActionListener
Parameters:
event - The event that is to be reacted to.

savePreferencesFile

public void savePreferencesFile(java.lang.String comments,
                                boolean is_basic_save)
Saves a preferences_file XML file with the contents specified in the current fields.

If the is_basic_save parameter is true, then the file is saved at the path specified in the ConfigureFileLocationsJFrame object's preferences_path field (automatically overwriting any existing files with the same path). If the is_basic_save parameter is false, then the file is saved at a location chosen by the user with a JFileChooser dialog box.

Parameters:
comments - Any comments to be saved inside the comments element of the XML file.
is_basic_save - Whether this is a save (true) or save as (false) operation.
See Also:
ConfigureFileLocationsJFrame

getTrainingFraction

public double getTrainingFraction()
                           throws java.lang.Exception
Returns the fraction of candidate recordings to use for training.

Throws:
java.lang.Exception

shouldUseFeaturesMarkedAsSelectionCandidates

public boolean shouldUseFeaturesMarkedAsSelectionCandidates()
Returns true if the user has selected the option of using features marked as Selection Candidates in the FeaturesPanel for feature selection and returns false if the user has instead selected the option of using the featues marked as having Overide Status in the FeaturesPanel for feature selection.


shouldUseOneDimensionalFeaturesInTraining

public boolean shouldUseOneDimensionalFeaturesInTraining()
Returns true if the user has selected the option of using one-dimensional features (and therefore BioKNearestNeighbour classifiers in training.


shouldUseMultiDimensionalFeaturesInTraining

public boolean shouldUseMultiDimensionalFeaturesInTraining()
Returns true if the user has selected the option of using multi-dimensional features (and therefore FeedForwardNetworks classifiers) in training.


shouldBioKNNsUseFeatureSelection

public boolean shouldBioKNNsUseFeatureSelection()
Returns true if the user has selected the option of having BioKNearestNeighbour classifiers perform feature selection.


shouldBioKNNsUseFeatureWeighting

public boolean shouldBioKNNsUseFeatureWeighting()
Returns true if the user has selected the option of having BioKNearestNeighbour classifiers perform feature weighting.


shouldSelectClassifiersInEachEnsemble

public boolean shouldSelectClassifiersInEachEnsemble()
Returns true if the user has selected the option of having classifier selection automatically applied to classifiers in each NN_BioKNN_Ensemble.


shouldWeightClassifiersInEachEnsemble

public boolean shouldWeightClassifiersInEachEnsemble()
Returns true if the user has selected the option of having classifier weightings automatically calculated internally in each NN_BioKNN_Ensemble.


getInternalTrainingFraction

public double getInternalTrainingFraction()
                                   throws java.lang.Exception
Returns the fraction of training samples that the user has selected that will actually be used for training when feature selection and weighting are calculated for one-dimensional features. The remainder are used for testing. This value must be between 0 and 1, and an exception is thrown if it is not.

Throws:
java.lang.Exception

shouldClassifyIntoAllLeafCategories

public boolean shouldClassifyIntoAllLeafCategories()
Returns whether or not training/classification should be done where recordings are classified into all leaf categories.


shouldClassifyIntoRootCategories

public boolean shouldClassifyIntoRootCategories()
Returns whether or not training/classification should be done where recordings are classified into the root categories.


shouldClassifyIntoDirectDescendantsOfParentCategories

public boolean shouldClassifyIntoDirectDescendantsOfParentCategories()
Returns whether or not training/classification should be done where recordings are classified into direct descendants of each parent category.


shouldClassifyUsingRoundRobin

public boolean shouldClassifyUsingRoundRobin()
Returns whether or not round robin ensembles should be trained / used during classification.


getAllLeafRelativeWeighing

public double getAllLeafRelativeWeighing()
                                  throws java.lang.Exception
Returns the relative weighting to be given to the leaf classifier when the results of multiple classifiers are combined. This weighting is relative to the Hierarchal and Round Robin weightings. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getHierarchalRelativeWeighing

public double getHierarchalRelativeWeighing()
                                     throws java.lang.Exception
Returns the relative weighting to be given to the hierarchal classifiers when the results of multiple classifiers are combined. This weighting is relative to the Leaf and Round Robin weightings. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

shouldOnlyUseBestForRoundRobin

public boolean shouldOnlyUseBestForRoundRobin()
Returns whether or not all but the highest round robin score should be set to 0.


getRoundRobinDivisor

public double getRoundRobinDivisor()
                            throws java.lang.Exception
Returns the divisor that is used to divide all round robin scores during classification.

Throws:
java.lang.Exception

getRoundRobinRelativeWeighing

public double getRoundRobinRelativeWeighing()
                                     throws java.lang.Exception
Returns the relative weighting to be given to the round classifiers when the results of multiple classifiers are combined. This weighting is relative to the Leaf and Hierarchal weightings. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getNumberGAIterations

public int getNumberGAIterations()
                          throws java.lang.Exception
Returns the maximum number of generations that should be performed for feature (but not classifier) selections and weightings. Returns a negative value if the use has selected to automatically check if training should be stopped before this number has been reached.

Throws:
java.lang.Exception

getClassifierVsFeatureGAMultiplier

public double getClassifierVsFeatureGAMultiplier()
                                          throws java.lang.Exception
Returns multiplier applied to the number of GA iterations for feature selections and weightings in order to calculate classifier selections and weightings. Also applied to the population.

Throws:
java.lang.Exception

getMaxGATrainingErrorForEarlyEnding

public double getMaxGATrainingErrorForEarlyEnding()
                                           throws java.lang.Exception
Return the maximum acceptable change in error selected by the user for GA feature selection training error rates that will allow training to be stopped early. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getMinGATrainingIterationsForEarlyEnding

public int getMinGATrainingIterationsForEarlyEnding()
                                             throws java.lang.Exception
Returns the minimum number of consecutive iterations which the user has selected must go by when feature selection training a GA where the error is below the maximum error rate in order for training to stop early. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getNumberNNIterations

public int getNumberNNIterations()
Returns the maximum number of generations that should be performed for FeedForwardNeuralNetwork Return a negative value if the use has selected to automatically check if training should be stopped before this number has been reached.


getMaxNNTrainingErrorForEarlyEnding

public double getMaxNNTrainingErrorForEarlyEnding()
                                           throws java.lang.Exception
Return the maximum acceptable error selected by the user for FeedForwardNeuralNetwork training error rates that will allow training to be stopped early. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getMinNNTrainingIterationsForEarlyEnding

public int getMinNNTrainingIterationsForEarlyEnding()
                                             throws java.lang.Exception
Returns the minimum number of consecutive iterations which the user has selected must go by when training a FeedForwardNeuralNetwork where the error is below the maximum error rate in order for training to stop early. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getLinesToSkipWhenReportingTrainingErrors

public int getLinesToSkipWhenReportingTrainingErrors()
                                              throws java.lang.Exception
Returns the interval at which training errors are reported. Throws an exception if a negative value is entered.

Throws:
java.lang.Exception

getMinimumAutomaticQualificationScore

public double getMinimumAutomaticQualificationScore()
                                             throws java.lang.Exception
Returns the minimum score that a category must have to automatically be counted as a first choice during classification.

Throws:
java.lang.Exception

getMinimumScoreToQualify

public double getMinimumScoreToQualify()
                                throws java.lang.Exception
Returns the minimum score that a recording must have to qualify as a first choice during classification.

Throws:
java.lang.Exception

getPercentageBelowHighestToQualify

public double getPercentageBelowHighestToQualify()
                                          throws java.lang.Exception
Returns the percentage below the score of the highest performer at which a category will be classified as a first choice.

Throws:
java.lang.Exception

getMinimumScoreToBeSecondChoice

public double getMinimumScoreToBeSecondChoice()
                                       throws java.lang.Exception
Returns the minimum score that a recording must have to qualify as a second choice during classification.

Throws:
java.lang.Exception

getPercentageBelowHighestToBeSecondChoice

public double getPercentageBelowHighestToBeSecondChoice()
                                                 throws java.lang.Exception
Returns the percentage below the score of the highest performer at which a category will be classified as a second choice.

Throws:
java.lang.Exception

shouldOnlyPickOneWinnerForCombinedClassification

public boolean shouldOnlyPickOneWinnerForCombinedClassification()
Returns whether or not only one winning category is permitted per recorcing.


getTimeBetweenProgressBarPolls

public double getTimeBetweenProgressBarPolls()
Returns the time in milliseconds between progress bar polls. Defaults to ten seconds if a negative value is entered.


shouldDisplayTrainingTimesInRawSeconds

public boolean shouldDisplayTrainingTimesInRawSeconds()
Returns whether or not training times should be reported as raw seconds.


shouldDisplayClassifierSettings

public boolean shouldDisplayClassifierSettings()
Returns whether or not classifier settings should be included in classification reports.


reportScoresWithWinningCategories

public boolean reportScoresWithWinningCategories()
Returns whether or not classifier scores for each winning category are reported along with the categories.


reportSecondaryWinningCategories

public boolean reportSecondaryWinningCategories()
Returns whether or not classifier scores for secondary choices for winning category are reported along with the winning categories.


shouldDisplaySuccessRatesForClassifiers

public boolean shouldDisplaySuccessRatesForClassifiers()
Returns whether or not the classification report should include the successful classification statistics for the combined and individual classifiers for an ensemble of classifiers.


shouldDisplayConfusionMatrix

public boolean shouldDisplayConfusionMatrix()
Returns whether or not the classification report should include a confusion matrix.


shouldDisplayRootCategorySuccessRates

public boolean shouldDisplayRootCategorySuccessRates()
Returns whether or not to display root category success rates.


shouldDisplayListOfElligibleCategories

public boolean shouldDisplayListOfElligibleCategories()
Returns whether or not the classification report should include a list of elligible categories into which recordings can be classified by an ensemble of classifiers.


shouldDisplayCombinedClassificationResultsForEachRecording

public boolean shouldDisplayCombinedClassificationResultsForEachRecording()
Returns whether or not the classification report should include the combined classification results (i.e. name of resulting categories) for each recording by an ensemble of classifiers.


shouldDisplayIndividualClassifierResultsForEachRecording

public boolean shouldDisplayIndividualClassifierResultsForEachRecording()
Returns whether or not the classification report should include separately, for each classifier, the classification results (i.e. name of resulting categories) for each recording by an ensemble of classifiers.


shouldDisplayModelResultsAlongWithResults

public boolean shouldDisplayModelResultsAlongWithResults()
Returns whether or not the classification reports of resulting categories should also include the correct classifications, if available.


shouldDisplayCombinedClassificationScoresForEachRecording

public boolean shouldDisplayCombinedClassificationScoresForEachRecording()
Returns whether or not the classification report should include the combined classification scores for each category of each recording by an ensemble of classifiers.


shouldDisplayIndividualClassifierScoresForEachRecording

public boolean shouldDisplayIndividualClassifierScoresForEachRecording()
Returns whether or not the classification report should include, separately for each classifier, the classification scores for each category of each recording by an ensemble of classifiers.


shouldDisplayModelResultsForEeachRecordingInSeparateTable

public boolean shouldDisplayModelResultsForEeachRecordingInSeparateTable()
Returns whether or not the classification report should include, as a separate table, a list of the elligible classsification categories for an ensemble of classifiers, along with their code numbers.


shouldDisplayTrainingRecordingNames

public boolean shouldDisplayTrainingRecordingNames()
Returns whether or not the training report should include the names and model leaf categories of the recordings used to train it.


shouldDisplayFeatureSelectionWeightingTrainingError

public boolean shouldDisplayFeatureSelectionWeightingTrainingError()
Returns whether or not the classification report should include the one-dimensional feature selection or weighting training error for an ensemble of classifiers.


shouldDisplayMultiDimClassifierTrainingError

public boolean shouldDisplayMultiDimClassifierTrainingError()
Returns whether or not the classification report should include the training error for the multi-dimensional classifiers in an ensemble of classifiers.


shouldDisplayClassifierSelectionTrainingError

public boolean shouldDisplayClassifierSelectionTrainingError()
Returns whether or not the classification report should include the classifier selection training error for an ensemble of classifiers.


shouldDisplayClassifierWeightingTrainingError

public boolean shouldDisplayClassifierWeightingTrainingError()
Returns whether or not the classification report should include the classifier weighting training error for an ensemble of classifiers.


shouldDisplayOneDimensionalFeaturesSelected

public boolean shouldDisplayOneDimensionalFeaturesSelected()
Returns whether or not the selection/weighting report should include the one-dimensional features selected for an ensemble of classifiers.


shouldDisplayOneDimensionalFeatureWeightings

public boolean shouldDisplayOneDimensionalFeatureWeightings()
Returns whether or not the selection/weighting report should include the one-dimensional feature weightings for an ensemble of classifiers.


shouldDisplayClassifiersSelected

public boolean shouldDisplayClassifiersSelected()
Returns whether or not the selection/weighting report should include the classifiers selected for an ensemble of classifiers.


shouldDisplayClassifiersWeightings

public boolean shouldDisplayClassifiersWeightings()
Returns whether or not the selection/weighting report should include the classifier weightings for an ensemble of classifiers.