[Serializable]
[DataContract]
[Quality(QualityBand.Experimental)]
public class DictionaryWeightFunction<TThis> : WeightFunctions<TSequence, TElement, TElementDistribution, TSequenceManipulator, TAutomaton>.IWeightFunction<TThis>, WeightFunctions<TSequence, TElement, TElementDistribution, TSequenceManipulator, TAutomaton>.IWeightFunction, IEquatable<TThis> where TThis : WeightFunctions<TSequence, TElement, TElementDistribution, TSequenceManipulator, TAutomaton>.DictionaryWeightFunction<TThis>, new()

Type Parameters

Name	Description
TThis	The type of a concrete dictionary weight function class.

Constructors

DictionaryWeightFunction()

Declaration

public DictionaryWeightFunction()

DictionaryWeightFunction(IReadOnlyDictionary<TSequence, Weight>)

Declaration

protected DictionaryWeightFunction(IReadOnlyDictionary<TSequence, Weight> dictionary)

Parameters

Type	Name	Description
IReadOnlyDictionary<TSequence, Weight>	dictionary

Fields

dictionary

Declaration

[DataMember]
protected IReadOnlyDictionary<TSequence, Weight> dictionary

Field Value

Type	Description
IReadOnlyDictionary<TSequence, Weight>

Properties

Dictionary

A dictionary containing the entire support of the current weight function and the corresponding weights.

Declaration

public IReadOnlyDictionary<TSequence, Weight> Dictionary { get; }

Property Value

Type	Description
IReadOnlyDictionary<TSequence, Weight>

ElementDistributionFactory

Declaration

protected static TElementDistribution ElementDistributionFactory { get; }

Property Value

Type	Description
TElementDistribution

IsPointMass

Gets a value indicating whether the current weight function assigns a non-zero weight to exactly one point.

Declaration

public bool IsPointMass { get; }

Property Value

Type	Description
Boolean

Point

Gets the only point to which the current function assigns a non-zero weight.

Declaration

public TSequence Point { get; }

Property Value

Type	Description
TSequence

Exceptions

Type	Condition
InvalidOperationException	Thrown when an attempt is made to get the Point of a non-pointmass weight function.

SequenceManipulator

Declaration

protected static TSequenceManipulator SequenceManipulator { get; }

Property Value

Type	Description
TSequenceManipulator

UsesAutomatonRepresentation

Gets a value indicating whether the current weight function is represented as an automaton internally.

Declaration

public bool UsesAutomatonRepresentation { get; }

Property Value

Type	Description
Boolean

UsesGroups

Checks if the weight function uses groups.

Declaration

public bool UsesGroups { get; }

Property Value

Type	Description
Boolean	true if the weight function uses groups, false otherwise.

Methods

Append(TSequence, Int32)

Creates a weight function f'(st) = f(s), where f(s) is the current weight function and t is the given sequence.

Declaration

public TThis Append(TSequence sequence, int group = 0)

Parameters

Type	Name	Description
TSequence	sequence	The sequence.
Int32	group	The group.

Returns

Type	Description
TThis	The created weight function.

Append(TThis, Int32)

Creates a weight function f'(s) = sum_{tu=s} f(t)g(u), where f(t) is the current weight function and g(u) is the given weight function.

Declaration

public TThis Append(TThis weightFunction, int group = 0)

Parameters

Type	Name	Description
TThis	weightFunction	The weight function to append.
Int32	group	The group.

Returns

Type	Description
TThis	The created weight function.

AsAutomaton()

Returns an automaton representation of the current weight function. If the weight function is normalized, the resulting automaton is stochastic, i.e. the sum of weights of all the outgoing transitions and the ending weight is 1 for every node.

Declaration

public virtual TAutomaton AsAutomaton()

Returns

Type	Description
TAutomaton

EnumeratePaths()

Declaration

public IEnumerable<Tuple<List<TElementDistribution>, double>> EnumeratePaths()

Returns

Type	Description
IEnumerable<Tuple<List<TElementDistribution>, Double>>

EnumerateSupport(Int32)

Enumerates support of this weight function when possible.

Declaration

public IEnumerable<TSequence> EnumerateSupport(int maxCount = 1000000)

Parameters

Type	Name	Description
Int32	maxCount	The maximum support enumeration count.

Returns

Type	Description
IEnumerable<TSequence>	The sequences in the support of this weight function

Exceptions

Type	Condition
AutomatonEnumerationCountException	Thrown if enumeration is too large.

Equals(TThis)

Declaration

public bool Equals(TThis other)

Parameters

Type	Name	Description
TThis	other

Returns

Type	Description
Boolean

Equals(Object)

Declaration

public override bool Equals(object obj)

Parameters

Type	Name	Description
Object	obj

Returns

Type	Description
Boolean

Overrides

Object.Equals(Object)

FillDictionary(IDictionary<TSequence, Weight>, IEnumerable<KeyValuePair<TSequence, Weight>>)

Fills the supplied empty sequence to weight dictionary with values from the given collection. If the supplied collection contains multiple entries for the same sequence, the weights for that sequence are summed.

Declaration

protected static void FillDictionary(IDictionary<TSequence, Weight> dictionaryToFill, IEnumerable<KeyValuePair<TSequence, Weight>> sequenceWeightPairs)

Parameters

Type	Name	Description
IDictionary<TSequence, Weight>	dictionaryToFill	The target empty dictionary.
IEnumerable<KeyValuePair<TSequence, Weight>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

FromDistinctValues(IEnumerable<KeyValuePair<TSequence, Double>>)

Creates a sequence to weight dictionary using the supplied sequenceWeightPairs. If the supplied collection is expected to not contain multiple entries for the same sequence.

Declaration

public static TThis FromDistinctValues(IEnumerable<KeyValuePair<TSequence, double>> sequenceWeightPairs)

Parameters

Type	Name	Description
IEnumerable<KeyValuePair<TSequence, Double>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

Returns

Type	Description
TThis

FromDistinctWeights(IEnumerable<KeyValuePair<TSequence, Weight>>)

Creates a sequence to weight dictionary using the supplied sequenceWeightPairs. If the supplied collection is expected to not contain multiple entries for the same sequence.

Declaration

[Construction(new string[]{"Dictionary"})]
public static TThis FromDistinctWeights(IEnumerable<KeyValuePair<TSequence, Weight>> sequenceWeightPairs)

Parameters

Type	Name	Description
IEnumerable<KeyValuePair<TSequence, Weight>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

Returns

Type	Description
TThis

FromPoint(TSequence)

Creates a sequence to weight dictionary with point being its only key which corresponds to a unit weight.

Declaration

public static TThis FromPoint(TSequence point)

Parameters

Type	Name	Description
TSequence	point	The only sequence contained in the dictionary.

Returns

Type	Description
TThis

FromValues(IEnumerable<KeyValuePair<TSequence, Double>>)

Creates a sequence to weight dictionary using the supplied sequenceWeightPairs. If the supplied collection contains multiple entries for the same sequence, the weights for that sequence are summed.

Declaration

public static TThis FromValues(IEnumerable<KeyValuePair<TSequence, double>> sequenceWeightPairs)

Parameters

Type	Name	Description
IEnumerable<KeyValuePair<TSequence, Double>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

Returns

Type	Description
TThis

FromWeights(IEnumerable<KeyValuePair<TSequence, Weight>>)

Creates a sequence to weight dictionary using the supplied sequenceWeightPairs. If the supplied collection contains multiple entries for the same sequence, the weights for that sequence are summed.

Declaration

public static TThis FromWeights(IEnumerable<KeyValuePair<TSequence, Weight>> sequenceWeightPairs)

Parameters

Type	Name	Description
IEnumerable<KeyValuePair<TSequence, Weight>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

Returns

Type	Description
TThis

GetGroups()

If the current weight function uses groups, returns a dictionary [group index] -> group. Otherwise, returns an empty dictionary.

Declaration

public Dictionary<int, TThis> GetGroups()

Returns

Type	Description
Dictionary<Int32, TThis>	A possibly empty dictionary [group index] -> group.

GetHashCode()

Declaration

public override int GetHashCode()

Returns

Type	Description
Int32

Overrides

Object.GetHashCode()

GetLogNormalizer()

Computes the logarithm of the normalizer (sum of values of the weight function on all sequences).

Declaration

public double GetLogNormalizer()

Returns

Type	Description
Double	The logarithm of the normalizer.

Remarks

Returns PositiveInfinity if the sum diverges.

GetLogNormalizerOfProduct(TThis)

Computes the logarithm of the normalizer (sum of values of the weight function on all sequences) of the product of the current and the given weight functions.

Declaration

protected virtual double GetLogNormalizerOfProduct(TThis weightFunction)

Parameters

Type	Name	Description
TThis	weightFunction	The given weight function.

Returns

Type	Description
Double	The logarithm of the normalizer.

GetLogNormalizerOfSquare()

Computes the logarithm of the normalizer (sum of values of the weight function on all sequences) of the square of the current weight function.

Declaration

protected double GetLogNormalizerOfSquare()

Returns

Type	Description
Double	The logarithm of the normalizer.

GetLogSimilarity(TThis)

Gets a value indicating how close this weight function is to a given one in terms of weights they assign to sequences.

Declaration

protected double GetLogSimilarity(TThis that)

Parameters

Type	Name	Description
TThis	that	The other weight function.

Returns

Type	Description
Double	The logarithm of a non-negative value, which is close to zero if the two automata assign similar values to all sequences.

GetLogValue(TSequence)

Computes the logarithm of the value of the weight function on a given sequence.

Declaration

public double GetLogValue(TSequence sequence)

Parameters

Type	Name	Description
TSequence	sequence	The sequence to compute the value on.

Returns

Type	Description
Double	The logarithm of the value.

HasGroup(Int32)

Determines whether this weight function has the specified group (if applicable).

Declaration

public bool HasGroup(int group)

Parameters

Type	Name	Description
Int32	group	The specified group.

Returns

Type	Description
Boolean	True if it the weight function has this group, false otherwise.

IsZero()

Checks whether the current weight function is zero on all sequences.

Declaration

public bool IsZero()

Returns

Type	Description
Boolean	true if the current weight function is zero on all sequences, false otherwise.

MaxDiff(TThis)

Gets a value indicating how close this weight function is to a given one in terms of weights they assign to sequences.

Declaration

public double MaxDiff(TThis that)

Parameters

Type	Name	Description
TThis	that	The other weight function.

Returns

Type	Description
Double	A non-negative value, which is close to zero if the two weight functions assign similar values to all sequences.

NormalizeStructure()

Returns the weight function converted to the normalized form e.g. using special case structures for point masses and functions with small support.

Declaration

public TThis NormalizeStructure()

Returns

Type	Description
TThis

Product(TThis)

Computes the product of the current weight function and a given one.

Declaration

public virtual TThis Product(TThis weightFunction)

Parameters

Type	Name	Description
TThis	weightFunction	The weight function to compute the product with.

Returns

Type	Description
TThis	The computed product.

Repeat(Int32, Int32, Int32)

Creates a weight function g(s) = sum_{k=Kmin}^{Kmax} sum_{t1 t2 ... tk = s} f(t1)f(t2)...f(tk), where f(t) is the current weight function, and Kmin and Kmax are the minimum and the maximum number of factors in a sum term.

Declaration

public TThis Repeat(int minTimes, int maxTimes, int expectedResultSupportSize)

Parameters

Type	Name	Description
Int32	minTimes	The minimum number of factors in a sum term. Defaults to 1.
Int32	maxTimes	The maximum number of factors in a sum term.
Int32	expectedResultSupportSize	Predicted size of the support of the resulting weight function. Does not have to be correct, but when it is, the performance is slightly improved.

Returns

Type	Description
TThis	The created weight function.

Repeat(Int32, Nullable<Int32>)

Declaration

public TThis Repeat(int minTimes = 1, int? maxTimes = null)

Parameters

Type	Name	Description
Int32	minTimes	The minimum number of factors in a sum term. Defaults to 1.
Nullable<Int32>	maxTimes	An optional maximum number of factors in a sum term.

Returns

Type	Description
TThis	The created weight function.

ScaleLog(Double)

Scales the weight function and returns the result.

Declaration

public TThis ScaleLog(double logScale)

Parameters

Type	Name	Description
Double	logScale	The logarithm of the scale.

Returns

Type	Description
TThis	The scaled weight function.

SetDistinctWeights(IEnumerable<KeyValuePair<TSequence, Weight>>)

Replaces the internal sequence to weight dictionary with a new one using the supplied sequenceWeightPairs. If the supplied collection is expected to not contain multiple entries for the same sequence.

Declaration

protected virtual void SetDistinctWeights(IEnumerable<KeyValuePair<TSequence, Weight>> sequenceWeightPairs)

Parameters

Type	Name	Description
IEnumerable<KeyValuePair<TSequence, Weight>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

Remarks

Should only ever be called in factory methods.

SetWeights(IEnumerable<KeyValuePair<TSequence, Weight>>)

Replaces the internal sequence to weight dictionary with a new one using the supplied sequenceWeightPairs. If the supplied collection contains multiple entries for the same sequence, the weights for that sequence are summed.

Declaration

protected virtual void SetWeights(IEnumerable<KeyValuePair<TSequence, Weight>> sequenceWeightPairs)

Parameters

Type	Name	Description
IEnumerable<KeyValuePair<TSequence, Weight>>	sequenceWeightPairs	The collection of pairs of a sequence and the weight on that sequence.

Remarks

Should only ever be called in factory methods.

Sum(TThis)

Computes the sum of the current weight function and a given weight function.

Declaration

public TThis Sum(TThis weightFunction)

Parameters

Type	Name	Description
TThis	weightFunction	The weight function to compute the sum with.

Returns

Type	Description
TThis	The computed sum.

Sum(Double, TThis, Double)

Computes the weighted sum of the current weight function and a given weight function.

Declaration

public TThis Sum(double weight1, TThis weightFunction, double weight2)

Parameters

Type	Name	Description
Double	weight1	The weight of the current weight function.
TThis	weightFunction	The weight function to compute the sum with.
Double	weight2	The weight of the `weightFunction`.

Returns

Type	Description
TThis

SumLog(Double, TThis, Double)

Computes the weighted sum of the current weight function and a given weight function.

Declaration

public TThis SumLog(double logWeight1, TThis weightFunction, double logWeight2)

Parameters

Type	Name	Description
Double	logWeight1	The logarithm of the weight of the current weight function.
TThis	weightFunction	The weight function to compute the sum with.
Double	logWeight2	The logarithm of the weight of the `weightFunction`.

Returns

Type	Description
TThis

ToString()

Declaration

public override string ToString()

Returns

Type	Description
String

Overrides

Object.ToString()

ToString(Action<TElementDistribution, StringBuilder>)

Declaration

public string ToString(Action<TElementDistribution, StringBuilder> appendElement)

Parameters

Type	Name	Description
Action<TElementDistribution, StringBuilder>	appendElement

Returns

Type	Description
String

TryEnumerateSupport(Int32, out IEnumerable<TSequence>)

Tries to enumerate support of this weight function.

Declaration

public bool TryEnumerateSupport(int maxCount, out IEnumerable<TSequence> result)

Parameters

Type	Name	Description
Int32	maxCount	The maximum support enumeration count.
IEnumerable<TSequence>	result	The sequences in the support of this weight function

Returns

Type	Description
Boolean	True if successful, false otherwise

TryNormalizeValues(out TThis, out Double)

Attempts to normalize the weight function so that sum of its values on all possible sequences equals to one (if it is possible) and returns the result in an out parameter. If successful, calls to AsAutomaton() methods of the resulting function produce a stochastic automaton, i.e. an automaton, in which the sum of weights of all the outgoing transitions and the ending weight is 1 for every node.

Declaration

public virtual bool TryNormalizeValues(out TThis normalizedFunction, out double logNormalizer)

Parameters

Type	Name	Description
TThis	normalizedFunction	Result of the normaliztion attempt.
Double	logNormalizer	When the function returns, contains the logarithm of the normalizer.

Returns

Type	Description
Boolean	true if the weight function was successfully normalized, false otherwise.

Implements

WeightFunctions<TSequence, TElement, TElementDistribution, TSequenceManipulator, TAutomaton>.IWeightFunction<TThis>

WeightFunctions<TSequence, TElement, TElementDistribution, TSequenceManipulator, TAutomaton>.IWeightFunction

System.IEquatable<T>