Class StringCharConcatOp
Provides outgoing messages for Concat(String, Char), given random arguments to the function.
Inherited Members
Namespace: Microsoft.ML.Probabilistic.Factors
Assembly: Microsoft.ML.Probabilistic.dll
Syntax
[FactorMethod(typeof(Factor), "Concat", new Type[]{typeof(string), typeof(char)})]
[Quality(QualityBand.Experimental)]
public static class StringCharConcatOp
Methods
ChAverageConditional(StringDistribution, StringDistribution)
EP message to ch
.
Declaration
public static DiscreteChar ChAverageConditional(StringDistribution concat, StringDistribution str)
Parameters
Type | Name | Description |
---|---|---|
StringDistribution | concat | Incoming message from |
StringDistribution | str | Incoming message from |
Returns
Type | Description |
---|---|
DiscreteChar | The outgoing EP message to the |
Remarks
The outgoing message is a distribution matching the moments of ch
as the random arguments are varied. The formula is proj[p(ch) sum_(concat,str) p(concat,str) factor(concat,str,ch)]/p(ch)
.
ConcatAverageConditional(StringDistribution, DiscreteChar)
EP message to concat
.
Declaration
public static StringDistribution ConcatAverageConditional(StringDistribution str, DiscreteChar ch)
Parameters
Type | Name | Description |
---|---|---|
StringDistribution | str | Incoming message from |
DiscreteChar | ch | Incoming message from |
Returns
Type | Description |
---|---|
StringDistribution | The outgoing EP message to the |
Remarks
The outgoing message is a distribution matching the moments of concat
as the random arguments are varied. The formula is proj[p(concat) sum_(str,ch) p(str,ch) factor(concat,str,ch)]/p(concat)
.
LogAverageFactor(StringDistribution, StringDistribution, DiscreteChar)
Evidence message for EP.
Declaration
public static double LogAverageFactor(StringDistribution concat, StringDistribution str, DiscreteChar ch)
Parameters
Type | Name | Description |
---|---|---|
StringDistribution | concat | Incoming message from |
StringDistribution | str | Incoming message from |
DiscreteChar | ch | Incoming message from |
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_(concat,str,ch) p(concat,str,ch) factor(concat,str,ch))
.
LogEvidenceRatio(StringDistribution, StringDistribution, DiscreteChar)
Evidence message for EP.
Declaration
public static double LogEvidenceRatio(StringDistribution concat, StringDistribution str, DiscreteChar ch)
Parameters
Type | Name | Description |
---|---|---|
StringDistribution | concat | Incoming message from |
StringDistribution | str | Incoming message from |
DiscreteChar | ch | Incoming message from |
Returns
Type | Description |
---|---|
Double | Logarithm of the factor's contribution the EP model evidence. |
Remarks
The formula for the result is log(sum_(concat,str,ch) p(concat,str,ch) factor(concat,str,ch) / sum_concat p(concat) messageTo(concat))
. Adding up these values across all factors and variables gives the log-evidence estimate for EP.
LogEvidenceRatio(String, StringDistribution, DiscreteChar)
Evidence message for EP.
Declaration
public static double LogEvidenceRatio(string concat, StringDistribution str, DiscreteChar ch)
Parameters
Type | Name | Description |
---|---|---|
String | concat | Constant value for |
StringDistribution | str | Incoming message from |
DiscreteChar | ch | Incoming message from |
Returns
Type | Description |
---|---|
Double | Logarithm of the factor's contribution the EP model evidence. |
Remarks
The formula for the result is log(sum_(str,ch) p(str,ch) factor(concat,str,ch))
. Adding up these values across all factors and variables gives the log-evidence estimate for EP.
StrAverageConditional(StringDistribution, DiscreteChar)
EP message to str
.
Declaration
public static StringDistribution StrAverageConditional(StringDistribution concat, DiscreteChar ch)
Parameters
Type | Name | Description |
---|---|---|
StringDistribution | concat | Incoming message from |
DiscreteChar | ch | Incoming message from |
Returns
Type | Description |
---|---|
StringDistribution | The outgoing EP message to the |
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_(concat,ch) p(concat,ch) factor(concat,str,ch)]/p(str)
.