/// <summary>
/// Infers parameters for a given cold user.
/// </summary>
/// <param name="userFeatures">The user features.</param>
/// <returns>A distribution over the user parameters.</returns>
public UserParameterDistribution InferUserParameters(SparseFeatureVector userFeatures)
{
UserParameterDistribution result;
if (this.userFeatureParameterPosteriors.FeatureCount == 0)
{
Debug.Assert(
userFeatures.FeatureCount == 0,
"The number of user features passed must be equal to the number of user features learned.");
result = this.userParameterDistributionAverage;
}
else
{
GaussianArray traits;
Gaussian bias;
AlgorithmUtils.AddFeatureContribution(
this.userParameterDistributionAverage,
this.userFeatureParameterPosteriors,
userFeatures,
out traits,
out bias);
result = new UserParameterDistribution(traits, bias, this.userParameterDistributionAverage.Thresholds);
}
return(result);
}
/// <summary>
/// Adds the feature contribution for a given user/item to its traits and bias.
/// </summary>
/// <param name="parameters">The user/item parameters.</param>
/// <param name="featureWeights">The feature weights.</param>
/// <param name="featureValues">The feature values.</param>
/// <param name="adjustedTraits">The resulting traits.</param>
/// <param name="adjustedBias">The resulting bias.</param>
public static void AddFeatureContribution(
EntityParameterDistribution parameters,
FeatureParameterDistribution featureWeights,
SparseFeatureVector featureValues,
out GaussianArray adjustedTraits,
out Gaussian adjustedBias)
{
adjustedTraits = new GaussianArray(
parameters.Traits.Count,
i => DoublePlusOp.SumAverageConditional(
parameters.Traits[i],
ComputeFeatureContribution(featureWeights.TraitWeights[i], featureValues.NonZeroFeatureValues, featureValues.NonZeroFeatureIndices)));
adjustedBias = DoublePlusOp.SumAverageConditional(
parameters.Bias,
ComputeFeatureContribution(featureWeights.BiasWeights, featureValues.NonZeroFeatureValues, featureValues.NonZeroFeatureIndices));
}
