protected override double ComputeLLR(ModelScorer modelScorer, PhyloTree phyloTree, StringBuilder stringBuilder, double targetMarginal, double predictorMarginal,
Converter <Leaf, SufficientStatistics> predictorDistributionClassFunction, Converter <Leaf, SufficientStatistics> targetDistributionClassFunction)
{
Converter <Leaf, SufficientStatistics> LeafToJointDistributionClass =
CreateAlternativeSufficientStatisticsMap(predictorDistributionClassFunction, targetDistributionClassFunction);
double logLikelihoodIndependentModel, logLikelihoodJointModel;
Score scoreIndTarget, scoreIndPredictor, scoreJoint;
MessageInitializer messageInitializer;
// first score the target.
NullModelDistribution.EmpiricalEquilibrium = targetMarginal;
messageInitializer = modelScorer.CreateMessageInitializer(predictorDistributionClassFunction, targetDistributionClassFunction, NullModelDistribution);
scoreIndTarget = modelScorer.ScoreModel(messageInitializer, false);
NullModelDistribution.EmpiricalEquilibrium = predictorMarginal;
messageInitializer = modelScorer.CreateMessageInitializer(targetDistributionClassFunction, predictorDistributionClassFunction, NullModelDistribution);
scoreIndPredictor = modelScorer.ScoreModel(messageInitializer, false);
DistributionDiscreteJointBinary jointDistn = (DistributionDiscreteJointBinary)AlternativeModelDistribution;
jointDistn.SetInitialParams(scoreIndPredictor.OptimizationParameters, scoreIndTarget.OptimizationParameters);
messageInitializer = modelScorer.CreateMessageInitializer(null, LeafToJointDistributionClass, jointDistn);
scoreJoint = modelScorer.ScoreModel(messageInitializer, false);
logLikelihoodIndependentModel = scoreIndTarget.Loglikelihood + scoreIndPredictor.Loglikelihood;
logLikelihoodJointModel = scoreJoint.Loglikelihood;
stringBuilder.Append(SpecialFunctions.CreateTabString(scoreIndPredictor.ToString(NullModelDistribution), scoreIndTarget.ToString(NullModelDistribution),
logLikelihoodIndependentModel, scoreJoint.ToString(jointDistn), ""));
double diff = logLikelihoodJointModel - logLikelihoodIndependentModel;
return(diff);
}
protected override double ComputeLLR(ModelScorer modelScorer, PhyloTree phyloTree, StringBuilder stringBuilder, double targetMarginal, double predictorMarginal,
Converter <Leaf, SufficientStatistics> predictorDistributionClassFunction, Converter <Leaf, SufficientStatistics> targetDistributionClassFunction)
{
NullModelDistribution.EmpiricalEquilibrium = targetMarginal;
NullModelDistribution.InitialParamVals = null;
MessageInitializer messageInitializer = modelScorer.CreateMessageInitializer(predictorDistributionClassFunction, targetDistributionClassFunction, NullModelDistribution);
List <double> logLikelihoodList = new List <double>();
foreach (bool useParameter in new bool[] { false, true })
{
Score score = modelScorer.ScoreModel(messageInitializer, useParameter);
stringBuilder.Append(SpecialFunctions.CreateTabString(score.ToString(useParameter ? AlternativeModelDistribution : NullModelDistribution), ""));
logLikelihoodList.Add(score.Loglikelihood);
AltModelDistribution.InitialParamVals = score.OptimizationParameters;
Debug.WriteLine(SpecialFunctions.CreateTabString("AltModelDistribution.InitialParamVals = score.OptimizationParameters", score.OptimizationParameters));
}
double diff = logLikelihoodList[1] - logLikelihoodList[0];
return(diff);
}
protected override string CreateReportLine(
ModelScorer modelScorer,
PhyloTree phyloTree,
RowData rowAndTargetData,
UniversalWorkList workList,
int rowIndex, int workListCount, int workIndex)
{
//!!!there is very similar code in ModelTesterDiscrete.cs
Dictionary <string, string> row = rowAndTargetData.Row;
string predictorVariable = row[PhyloTree.PredictorVariableColumnName];
string targetVariable = row[PhyloTree.TargetVariableColumnName]; // e.g. A@182 (amino acid "A" at position 182)
int nullIndex = int.Parse(row[PhyloTree.NullIndexColumnName]);
//Dictionary<string, bool> caseIdToNonNullPredictorValue = workList.NullIndexToPredictorToCaseIdToNonMissingValue[nullIndex][predictorVariable];
Dictionary <string, SufficientStatistics> caseIdToNonNullPredictorValue = rowAndTargetData.PredictorData; //workList.GetCaseIdToNonMissingValueForNullIndexAndPredictorVariable(nullIndex, predictorVariable);
Dictionary <string, SufficientStatistics> caseIdToNonMissingTargetValue = rowAndTargetData.TargetData;
Converter <Leaf, SufficientStatistics> targetDistributionMap = CreateSufficientStatisticsMap(caseIdToNonMissingTargetValue);
Converter <Leaf, SufficientStatistics> predictorDistributionClassFunction = CreateSufficientStatisticsMap(caseIdToNonNullPredictorValue);
int[] predictorCounts = phyloTree.CountsOfLeaves(predictorDistributionClassFunction);
int predictorFalseNameCount = predictorCounts[(int)DistributionDiscreteBinary.DistributionClass.False];
int predictorTrueNameCount = predictorCounts[(int)DistributionDiscreteBinary.DistributionClass.True];
int targetNonMissingCount = phyloTree.CountOfNonMissingLeaves(caseIdToNonMissingTargetValue);
int globalNonMissingCount = phyloTree.GlobalNonMissingCount(predictorDistributionClassFunction, targetDistributionMap);
StringBuilder stringBuilder = new StringBuilder(
SpecialFunctions.CreateTabString(
this, rowIndex, workListCount, workIndex, nullIndex, predictorVariable,
predictorFalseNameCount,
predictorTrueNameCount,
predictorTrueNameCount + predictorFalseNameCount,
targetVariable,
targetNonMissingCount,
globalNonMissingCount,
""));
bool ignoreRow = false;
foreach (int count in predictorCounts)
{
if (count == 0)
{
ignoreRow = true;
}
}
if (ignoreRow)
{
CompleteRowWithNaN(stringBuilder);
}
else
{
List <double> logLikelihoodList = new List <double>();
MessageInitializer messageInitializer =
modelScorer.CreateMessageInitializer(predictorDistributionClassFunction, targetDistributionMap, NullModelDistribution);
NullModelDistribution.InitialParamVals = null;
foreach (bool useParameter in new bool[] { false, true })
{
Score score = modelScorer.ScoreModel(messageInitializer, useParameter);
stringBuilder.Append(SpecialFunctions.CreateTabString(score, ""));
Debug.Write(SpecialFunctions.CreateTabString(score, ""));
logLikelihoodList.Add(score.Loglikelihood);
AltModelDistribution.InitialParamVals = score.OptimizationParameters;
}
double diff = logLikelihoodList[1] - logLikelihoodList[0];
double pValue = SpecialFunctions.LogLikelihoodRatioTest(Math.Max(diff, 0), ChiSquareDegreesOfFreedom);
stringBuilder.Append(SpecialFunctions.CreateTabString(diff, pValue));
Debug.WriteLine(SpecialFunctions.CreateTabString(diff, pValue));
}
return(stringBuilder.ToString());
}
