Class SubstringOp

Provides outgoing messages for Substring(String, Int32, Int32), given random arguments to the function.

Inheritance

Object

SubstringOp

Inherited Members

Object.Equals(Object)

Object.Equals(Object, Object)

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Object.ReferenceEquals(Object, Object)

Object.ToString()

Namespace: Microsoft.ML.Probabilistic.Factors

Assembly: Microsoft.ML.Probabilistic.dll

Syntax

[FactorMethod(typeof(Factor), "Substring", new Type[]{})]
[Quality(QualityBand.Experimental)]
public static class SubstringOp

Methods

LogAverageFactor(StringDistribution, StringDistribution, Int32, Int32)

Evidence message for EP.

Declaration

public static double LogAverageFactor(StringDistribution str, StringDistribution sub, int start, int length)

Parameters

Type	Name	Description
StringDistribution	str	Incoming message from str.
StringDistribution	sub	Incoming message from sub.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
Double	Logarithm of the factor's average value across the given argument distributions.

Remarks

The formula for the result is log(sum_(str,sub) p(str,sub) factor(sub,str,start,length)).

LogEvidenceRatio(StringDistribution, StringDistribution, Int32, Int32)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(StringDistribution str, StringDistribution sub, int start, int length)

Parameters

Type	Name	Description
StringDistribution	str	Incoming message from str.
StringDistribution	sub	Incoming message from sub.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
Double	Logarithm of the factor's contribution the EP model evidence.

Remarks

The formula for the result is log(sum_(str,sub) p(str,sub) factor(sub,str,start,length) / sum_sub p(sub) messageTo(sub)). Adding up these values across all factors and variables gives the log-evidence estimate for EP.

LogEvidenceRatio(StringDistribution, String, Int32, Int32)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(StringDistribution str, string sub, int start, int length)

Parameters

Type	Name	Description
StringDistribution	str	Incoming message from str.
String	sub	Constant value for sub.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
Double	Logarithm of the factor's contribution the EP model evidence.

Remarks

The formula for the result is log(sum_(str) p(str) factor(sub,str,start,length)). Adding up these values across all factors and variables gives the log-evidence estimate for EP.

StrAverageConditional(StringDistribution, Int32, Int32)

EP message to str.

Declaration

public static StringDistribution StrAverageConditional(StringDistribution sub, int start, int length)

Parameters

Type	Name	Description
StringDistribution	sub	Incoming message from sub.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
StringDistribution	The outgoing EP message to the str argument.

Remarks

The outgoing message is a distribution matching the moments of str as the random arguments are varied. The formula is proj[p(str) sum_(sub) p(sub) factor(sub,str,start,length)]/p(str).

StrAverageConditional(String, Int32, Int32)

EP message to str.

Declaration

public static StringDistribution StrAverageConditional(string sub, int start, int length)

Parameters

Type	Name	Description
String	sub	Constant value for sub.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
StringDistribution	The outgoing EP message to the str argument.

Remarks

The outgoing message is the factor viewed as a function of str conditioned on the given values.

SubAverageConditional(StringDistribution, Int32, Int32)

EP message to sub.

Declaration

public static StringDistribution SubAverageConditional(StringDistribution str, int start, int length)

Parameters

Type	Name	Description
StringDistribution	str	Incoming message from str.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
StringDistribution	The outgoing EP message to the sub argument.

Remarks

The outgoing message is a distribution matching the moments of sub as the random arguments are varied. The formula is proj[p(sub) sum_(str) p(str) factor(sub,str,start,length)]/p(sub).

SubAverageConditional(StringDistribution, Int32, Int32, Int32)

Declaration

public static StringDistribution SubAverageConditional(StringDistribution str, int start, int minLength, int maxLength)

Parameters

Type	Name	Description
StringDistribution	str
Int32	start
Int32	minLength
Int32	maxLength

Returns

Type	Description
StringDistribution

SubAverageConditional(String, Int32, Int32)

EP message to sub.

Declaration

public static StringDistribution SubAverageConditional(string str, int start, int length)

Parameters

Type	Name	Description
String	str	Constant value for str.
Int32	start	Constant value for start.
Int32	length	Constant value for length.

Returns

Type	Description
StringDistribution	The outgoing EP message to the sub argument.

Remarks

The outgoing message is the factor viewed as a function of sub conditioned on the given values.