java.lang.Object
- com.bayesserver.learning.parameters.Priors

All Implemented Interfaces:

Cloneable
```
public final class Priors
extends Object
implements Cloneable
```
Contains parameters used to avoid boundary conditions during learning.

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method	Description
`double`	`getContinuous()`	Gets the amount continuous distributions are adjusted during learning.
`double`	`getDiscrete()`	Gets the amount distributions containing discrete variables are adjusted during learning.
`DiscretePriorMethod`	`getDiscretePriorMethod()`	The default discrete prior to use for discrete distributions during parameter learning.
`boolean`	`getIncludeGlobalCovariance()`	When Gaussian distributions are adjusted according to the `getContinuous()` prior, this property determines whether the global covariance should be included in the adjustment, as well as the global variance.
`double`	`getSimpleVariance()`	Used to make a fixed adjustment to all covariance matrices during learning, by increasing each diagonal (variance) entry.
`void`	`setContinuous(double value)`	Sets the amount continuous distributions are adjusted during learning.
`void`	`setDiscrete(double value)`	Sets the amount distributions containing discrete variables are adjusted during learning.
`void`	`setDiscretePriorMethod(DiscretePriorMethod value)`	The default discrete prior to use for discrete distributions during parameter learning.
`void`	`setIncludeGlobalCovariance(boolean value)`	When Gaussian distributions are adjusted according to the `getContinuous()` prior, this property determines whether the global covariance should be included in the adjustment, as well as the global variance.
`void`	`setSimpleVariance(double value)`	Used to make a fixed adjustment to all covariance matrices during learning, by increasing each diagonal (variance) entry.
`String`	`toString()`	Returns a `String` that represents this instance.
`void`	`zeroAll()`	Sets all values to zero.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

- Method Detail
  - toString
```
public String toString()
```
    Returns a String that represents this instance.
    
    Overrides:
    
    toString in class Object
    
    Returns:
    
    A String that represents this instance.
  - zeroAll
```
public void zeroAll()
```
    Sets all values to zero.
  - getSimpleVariance
```
public double getSimpleVariance()
```
    Used to make a fixed adjustment to all covariance matrices during learning, by increasing each diagonal (variance) entry. It is recommended that this property is left at zero. However sometimes it is useful to use this property in order to compare outputs with other libraries.
  - setSimpleVariance
```
public void setSimpleVariance(double value)
```
    Used to make a fixed adjustment to all covariance matrices during learning, by increasing each diagonal (variance) entry. It is recommended that this property is left at zero. However sometimes it is useful to use this property in order to compare outputs with other libraries.
  - getDiscretePriorMethod
```
public DiscretePriorMethod getDiscretePriorMethod()
```
    The default discrete prior to use for discrete distributions during parameter learning. Can be overriden for individual distributions.
  - setDiscretePriorMethod
```
public void setDiscretePriorMethod(DiscretePriorMethod value)
```
    The default discrete prior to use for discrete distributions during parameter learning. Can be overriden for individual distributions.
  - getContinuous
```
public double getContinuous()
```
    Gets the amount continuous distributions are adjusted during learning.
    This value is used to avoid boundary conditions, such as perfect correlations.
    
    The larger the number of cases used during learning, the less impact this value has.
    
    The value defines the number of virtual cases taken from the global statistics (overall data summary statistics), that are included when learning continuous Gaussian distributions. The property getIncludeGlobalCovariance() determines how the adjustments are made.
    
    Setting this value to zero, will disable the adjustments.
  - setContinuous
```
public void setContinuous(double value)
```
    Sets the amount continuous distributions are adjusted during learning.
    This value is used to avoid boundary conditions, such as perfect correlations.
    
    The larger the number of cases used during learning, the less impact this value has.
    
    The value defines the number of virtual cases taken from the global statistics (overall data summary statistics), that are included when learning continuous Gaussian distributions. The property getIncludeGlobalCovariance() determines how the adjustments are made.
    
    Setting this value to zero, will disable the adjustments.
  - getIncludeGlobalCovariance
```
public boolean getIncludeGlobalCovariance()
```
    When Gaussian distributions are adjusted according to the getContinuous() prior, this property determines whether the global covariance should be included in the adjustment, as well as the global variance.
  - setIncludeGlobalCovariance
```
public void setIncludeGlobalCovariance(boolean value)
```
    When Gaussian distributions are adjusted according to the getContinuous() prior, this property determines whether the global covariance should be included in the adjustment, as well as the global variance.
  - getDiscrete
```
public double getDiscrete()
```
    Gets the amount distributions containing discrete variables are adjusted during learning.
    This value is used to avoid boundary conditions.
    
    The larger the number of cases used during learning, the less impact this value has.
    
    The value defines the number of virtual cases taken from the global statistics (overall data summary statistics), that are included when learning distributions with discrete variables.
    
    Setting this value to zero, will disable the adjustments.
  - setDiscrete
```
public void setDiscrete(double value)
```
    Sets the amount distributions containing discrete variables are adjusted during learning.
    This value is used to avoid boundary conditions.
    
    The larger the number of cases used during learning, the less impact this value has.
    
    The value defines the number of virtual cases taken from the global statistics (overall data summary statistics), that are included when learning distributions with discrete variables.
    
    Setting this value to zero, will disable the adjustments.

Class Priors

Method Summary

Methods inherited from class java.lang.Object

Method Detail

toString

zeroAll

getSimpleVariance

setSimpleVariance

getDiscretePriorMethod

setDiscretePriorMethod

getContinuous

setContinuous

getIncludeGlobalCovariance

setIncludeGlobalCovariance

getDiscrete

setDiscrete