KohonenSettings

All Superinterfaces:

java.lang.Cloneable, MiningAlgorithmSettings, MiningAlgorithmSettingsWithTransformation, PersistentObject, Verifiable

All Known Subinterfaces:

KohonenClassificationSettings, KohonenClusteringSettings
```
public interface KohonenSettings
extends MiningAlgorithmSettingsWithTransformation, Verifiable
```
Base settings for Kohonen algorithm.

Method Summary

Methods
Modifier and Type	Method and Description
`double`	`getBeginLearningRate()` Gets begining learning rate.
`int`	`getBeginNeighbourhoodRate()` Gets begining neighbourhood rate.
`CellType`	`getCellsType()` Gets cells (neighbourhood) type.
`ClusteringDistanceFunction`	`getDistanceFunction()` Gets distance function between two vectors.
`double`	`getEndLearningRate()` Gets ending learning rate.
`int`	`getEndNeighbourhoodRate()` Gets ending neighbourhood rate.
`int`	`getHeight()` Gets map height.
`int`	`getMaxNumberOfIterations()` Returns the maximum number of iterations to be used in training the network.
`double`	`getMinErrorTolerance()` Returns the minimum acceptable error in modeling the training data.
`ModificationFunction`	`getModificationFunction()` Gets neighbours modification function.
`double`	`getNoiseVariance()` Gets noise variance.
`SearchType`	`getSearchType()` Gets winner searching type.
`long`	`getSeed()` Gets value of seed.
`double`	`getValidationErrorTolerance()` Returns the factor of acceptable validation error according to current minimal validation error in modeling the training data.
`int`	`getValidationWindow()` Gets size of validation window, i.e. number of iterations between error on validation set is calculated.
`int`	`getWidth()` Gets map width.
`boolean`	`isBatchLearning()` Specify if batch learning is on.
`boolean`	`isDataRandomization()` Specify if data are randomized.
`boolean`	`isTorus()` Specify if map is closed into torus.
`void`	`setBatchLearning(boolean batch)` Sets flag if learning process should be batched.
`void`	`setBeginLearningRate(double beginLearningRate)` Sets begining learning rate.
`void`	`setBeginNeighbourhoodRate(int beginNeighbourhoodRate)` Sets begining neighbourhood rate.
`void`	`setCellsType(CellType cellsType)` Sets cel (neighbourhood) type.
`void`	`setDataRandomization(boolean random)` Sets flag if data should be randomized.
`void`	`setDistanceFunction(ClusteringDistanceFunction distanceFunction)` Sets distance function between two vectors.
`void`	`setEndLearningRate(double endLearningRate)` Sets ending learning rate.
`void`	`setEndNeighbourhoodRate(int endNeighbourhoodRate)` Sets ending neighbourhood rate.
`void`	`setHeight(int height)` Sets map height.
`void`	`setMaxNumberOfIterations(int maxIterations)` Sets the maximum number of iterations to be used in training the network.
`void`	`setMinErrorTolerance(double errorTolerance)` Sets the minimum acceptable error in modeling the training data.
`void`	`setModificationFunction(ModificationFunction modificationFunction)` Sets neighbours modification function.
`void`	`setNoiseVariance(double noiseVariance)` Sets noise variance.
`void`	`setSearchType(SearchType searchType)` Sets winner searching type.
`void`	`setSeed(long seed)` Sets value of seed.
`void`	`setTorus(boolean torus)` Sets torus.
`void`	`setValidationErrorTolerance(double valErrorTolerance)` Sets the factor of acceptable validation error according to current minimal validation error in modeling the training data.
`void`	`setValidationWindow(int w)` Sets a new size of validation window.
`void`	`setWidth(int width)` Sets map width.

Methods inherited from interface biz.sc.mm.dm.base.MiningAlgorithmSettingsWithTransformation
getTransformationSettings, isAutomaticDataTransformations, setAutomaticDataTransformations

Methods inherited from interface biz.sc.mm.dm.base.MiningAlgorithmSettings
clone

Methods inherited from interface biz.sc.mm.dm.PersistentObject
getDescription, getName, getObjectIdentifier, getProperties, isEditable, setDescription, setEditable, setName, setObjectIdentifier

Methods inherited from interface biz.sc.mm.dm.base.Verifiable
verify

- Method Detail
  - getCellsType
```
CellType getCellsType()
```
    Gets cells (neighbourhood) type.
    
    Returns:
    cells type
  - setCellsType
```
void setCellsType(CellType cellsType)
```
    Sets cel (neighbourhood) type.
    
    Parameters:
    cellsType - cells type
  - getWidth
```
int getWidth()
```
    Gets map width. Width is a cells count in one collumn.
    
    Returns:
    map width
  - setWidth
```
void setWidth(int width)
```
    Sets map width. Width is a cells count in one collumn.
    
    Parameters:
    width - map width
  - getHeight
```
int getHeight()
```
    Gets map height. Height is a cells count in one row.
    
    Returns:
    map height
  - setHeight
```
void setHeight(int height)
```
    Sets map height. Height is a cells count in one row.
    
    Parameters:
    height - map height
  - isTorus
```
boolean isTorus()
```
    Specify if map is closed into torus.
    
    Returns:
    true if map is closed
  - setTorus
```
void setTorus(boolean torus)
```
    Sets torus. Connects map at both sides if it is true.
    
    Parameters:
    torus - torus flag
  - getMaxNumberOfIterations
```
int getMaxNumberOfIterations()
```
    Returns the maximum number of iterations to be used in training the network.
    
    Returns:
    maximal number of iterations
  - setMaxNumberOfIterations
```
void setMaxNumberOfIterations(int maxIterations)
```
    Sets the maximum number of iterations to be used in training the network.
    
    Parameters:
    maxIterations - maximal number of iterations
  - getMinErrorTolerance
```
double getMinErrorTolerance()
```
    Returns the minimum acceptable error in modeling the training data.
    
    Returns:
    minimal error tolerance
  - setMinErrorTolerance
```
void setMinErrorTolerance(double errorTolerance)
```
    Sets the minimum acceptable error in modeling the training data.
    
    Parameters:
    errorTolerance - minimal error tolerance
  - isDataRandomization
```
boolean isDataRandomization()
```
    Specify if data are randomized.
    
    Returns:
    true if data are randomized
  - setDataRandomization
```
void setDataRandomization(boolean random)
```
    Sets flag if data should be randomized. If it is true, all training patterns will be presented in random sequence at each iteration.
    
    Parameters:
    random - data randomization flag
  - getNoiseVariance
```
double getNoiseVariance()
```
    Gets noise variance. None noise if is lesser than 0.
    
    Returns:
    noise variance
  - setNoiseVariance
```
void setNoiseVariance(double noiseVariance)
```
    Sets noise variance. None noise if variance is lesser than or equal 0.
    
    Parameters:
    noiceVariance - noise variance
  - getBeginLearningRate
```
double getBeginLearningRate()
```
    Gets begining learning rate. This is the value of learning rate at the begin of a learning process.
    
    Returns:
    begining learning rate
  - setBeginLearningRate
```
void setBeginLearningRate(double beginLearningRate)
```
    Sets begining learning rate. This is the value of learning rate at the begin of a learning process. For approporiate learning process this value should be from range (0, 1).
    
    Parameters:
    beginLearningRate - begining learning rate
  - getEndLearningRate
```
double getEndLearningRate()
```
    Gets ending learning rate. This is the value of learning rate at the end of a learning process.
    
    Returns:
    ending learning rate
  - setEndLearningRate
```
void setEndLearningRate(double endLearningRate)
```
    Sets ending learning rate. This is the value of learning rate at the end of a learning process. For approporiate learning process this value should be from range (0, 1).
    
    Parameters:
    endLearningRate - ending learning rate
  - getBeginNeighbourhoodRate
```
int getBeginNeighbourhoodRate()
```
    Gets begining neighbourhood rate. This is the value of neighbourhood rate (size of area from which neurons near the winner should be updated) at the begin of a learning proces.
    
    Returns:
    ending neighbourhood rate
  - setBeginNeighbourhoodRate
```
void setBeginNeighbourhoodRate(int beginNeighbourhoodRate)
```
    Sets begining neighbourhood rate. This is the value of neighbourhood rate (size of area from which neurons near the winner should be updated) at the begin of a learning proces.
    
    Parameters:
    beginNeighbourhoodRate - begining neighbourhood rate
  - getEndNeighbourhoodRate
```
int getEndNeighbourhoodRate()
```
    Gets ending neighbourhood rate. This is the value of neighbourhood rate (size of area from which neurons near the winner should be updated) at the end of a learning proces.
    
    Returns:
    ending neighbourhood rate
  - setEndNeighbourhoodRate
```
void setEndNeighbourhoodRate(int endNeighbourhoodRate)
```
    Sets ending neighbourhood rate. This is the value of neighbourhood rate (size of area from which neurons near the winner should be updated) at the end of a learning proces.
    
    Parameters:
    endNeighbourhoodRate - ending neighbourhood rate
  - getSearchType
```
SearchType getSearchType()
```
    Gets winner searching type.
    
    Returns:
    searching type
  - setSearchType
```
void setSearchType(SearchType searchType)
```
    Sets winner searching type.
    
    Parameters:
    searchType - searching type
  - getDistanceFunction
```
ClusteringDistanceFunction getDistanceFunction()
```
    Gets distance function between two vectors.
    
    Returns:
    distance function
  - setDistanceFunction
```
void setDistanceFunction(ClusteringDistanceFunction distanceFunction)
```
    Sets distance function between two vectors.
    
    Parameters:
    distanceFunction - distance function
  - getModificationFunction
```
ModificationFunction getModificationFunction()
```
    Gets neighbours modification function.
    
    Returns:
    modification function
  - setModificationFunction
```
void setModificationFunction(ModificationFunction modificationFunction)
```
    Sets neighbours modification function.
    
    Parameters:
    modificationFunction - modification function
  - isBatchLearning
```
boolean isBatchLearning()
```
    Specify if batch learning is on. If batch mode is on, neurons are updated once in the iteration after presentation all of learning patterns.
    
    Returns:
    true if batch learning is on
  - setBatchLearning
```
void setBatchLearning(boolean batch)
```
    Sets flag if learning process should be batched.
    
    Parameters:
    batch - batch learning flag
  - getValidationWindow
```
int getValidationWindow()
```
    Gets size of validation window, i.e. number of iterations between error on validation set is calculated.
    
    Returns:
    size of validation window
  - setValidationWindow
```
void setValidationWindow(int w)
```
    Sets a new size of validation window.
    
    Parameters:
    w - size of validation window
  - getValidationErrorTolerance
```
double getValidationErrorTolerance()
```
    Returns the factor of acceptable validation error according to current minimal validation error in modeling the training data.
    
    Returns:
    validation error tolerance related to minimum error on validation set
  - setValidationErrorTolerance
```
void setValidationErrorTolerance(double valErrorTolerance)
```
    Sets the factor of acceptable validation error according to current minimal validation error in modeling the training data.
    
    Parameters:
    valErrorTolerance - validation error tolerance related to minimum error on validation set
  - getSeed
```
long getSeed()
```
    Gets value of seed. Seed = 0 means random value.
    
    Returns:
    value of seed
  - setSeed
```
void setSeed(long seed)
```
    Sets value of seed. If seed is 0, value of seed will be taken randomicaly.
    
    Parameters:
    seed - value of seed

Interface KohonenSettings

Method Summary

Methods inherited from interface biz.sc.mm.dm.base.MiningAlgorithmSettingsWithTransformation

Methods inherited from interface biz.sc.mm.dm.base.MiningAlgorithmSettings

Methods inherited from interface biz.sc.mm.dm.PersistentObject

Methods inherited from interface biz.sc.mm.dm.base.Verifiable

Method Detail

getCellsType

setCellsType

getWidth

setWidth

getHeight

setHeight

isTorus

setTorus

getMaxNumberOfIterations

setMaxNumberOfIterations

getMinErrorTolerance

setMinErrorTolerance

isDataRandomization

setDataRandomization

getNoiseVariance

setNoiseVariance

getBeginLearningRate

setBeginLearningRate

getEndLearningRate

setEndLearningRate

getBeginNeighbourhoodRate

setBeginNeighbourhoodRate

getEndNeighbourhoodRate

setEndNeighbourhoodRate

getSearchType

setSearchType

getDistanceFunction

setDistanceFunction

getModificationFunction

setModificationFunction

isBatchLearning

setBatchLearning

getValidationWindow

setValidationWindow

getValidationErrorTolerance

setValidationErrorTolerance

getSeed

setSeed