public override EvaluationResults EvaluateModelOnDataGivenParams(Converter <Leaf, SufficientStatistics> predMap, Converter <Leaf, SufficientStatistics> targMap, EvaluationResults previousResults)
{
int predCount = ModelScorer.PhyloTree.CountOfNonMissingLeaves(predMap);
int targCount = ModelScorer.PhyloTree.CountOfNonMissingLeaves(targMap);
int globalNonMissingCount = ModelScorer.PhyloTree.CountOfNonMissingLeaves(predMap, targMap);
MessageInitializerGaussian nullMessageInitializer = MessageInitializerGaussian.GetInstance(
predMap, targMap, (DistributionGaussianConditional)NullDistns[0], ModelScorer.PhyloTree.LeafCollection);
double nullLL = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializer, previousResults.NullScores[0].OptimizationParameters);
Score nullScore = Score.GetInstance(nullLL, previousResults.NullScores[0].OptimizationParameters, previousResults.NullScores[0].Distribution);
MessageInitializerGaussian altMessageInitializer = MessageInitializerGaussian.GetInstance(
predMap, targMap, (DistributionGaussianConditional)AltDistn, ModelScorer.PhyloTree.LeafCollection);
double altLL = ModelScorer.ComputeLogLikelihoodModelGivenData(altMessageInitializer, previousResults.AltScore.OptimizationParameters);
Score altScore = Score.GetInstance(altLL, previousResults.AltScore.OptimizationParameters, previousResults.AltScore.Distribution);
EvaluationResults evalResults = EvaluationResultsGaussian.GetInstance(this, nullScore, altScore, predCount, targCount, globalNonMissingCount, ChiSquareDegreesOfFreedom);
return(evalResults);
}
//public static Converter<Leaf, SufficientStatistics> TESTPRED, TESTTARG;
//public static EvaluationResults TESTEVALRESULTS;
public override EvaluationResults EvaluateModelOnDataGivenParams(
Converter <Leaf, SufficientStatistics> predictorMap, Converter <Leaf, SufficientStatistics> targetMap, EvaluationResults previousResults)
{
int[] fisherCounts = ModelScorer.PhyloTree.FisherCounts(predictorMap, targetMap);
int targNullIdx = _includePredictorInScore ? 1 : 0;
OptimizationParameterList nullParamsTarg = previousResults.NullScores[targNullIdx].OptimizationParameters;
MessageInitializerDiscrete nullMessageInitializerTarg = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap,
NullDistn, new int[0], ModelScorer.PhyloTree.LeafCollection);
double nullLLTarg = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializerTarg, nullParamsTarg);
Score nullScoreTarg = Score.GetInstance(nullLLTarg, nullParamsTarg, NullDistn);
OptimizationParameterList altParams = previousResults.AltScore.OptimizationParameters;
MessageInitializerDiscrete altMessageInitializer = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap,
(DistributionDiscreteConditional)AltDistn, new int[0], ModelScorer.PhyloTree.LeafCollection);
double condLL = ModelScorer.ComputeLogLikelihoodModelGivenData(altMessageInitializer, altParams);
Score altScore = Score.GetInstance(condLL, altParams, AltDistn);
List <Score> nullScores = new List <Score>();
if (_includePredictorInScore)
{
OptimizationParameterList nullParamsPred = previousResults.NullScores[0].OptimizationParameters;
MessageInitializerDiscrete nullMessageInitializerPred = MessageInitializerDiscrete.GetInstance(targetMap, predictorMap,
NullDistn, new int[0], ModelScorer.PhyloTree.LeafCollection);
double nullLLPred = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializerPred, nullParamsPred);
Score nullScorePred = Score.GetInstance(nullLLPred, nullParamsPred, NullDistn);
nullScores.Add(nullScorePred);
// conditional model altScore doesn't include predLL. If we're here, we want to add it to make it comparable to joint or reverseConditional
altScore = Score.GetInstance(altScore.Loglikelihood + nullScorePred.Loglikelihood, altScore.OptimizationParameters, altScore.Distribution);
}
nullScores.Add(nullScoreTarg);
EvaluationResults evalResults = EvaluationResultsDiscrete.GetInstance(this, nullScores, altScore, fisherCounts, ChiSquareDegreesOfFreedom);
return(evalResults);
}
public override EvaluationResults EvaluateModelOnDataGivenParams(Converter <Leaf, SufficientStatistics> predictorMap, Converter <Leaf, SufficientStatistics> targetMap, EvaluationResults previousResults)
{
int[] fisherCounts = ModelScorer.PhyloTree.FisherCounts(predictorMap, targetMap);
OptimizationParameterList nullParamsTarg = previousResults.NullScores[1].OptimizationParameters;
MessageInitializerDiscrete nullMessageInitializerTarg = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, (DistributionDiscreteSingleVariable)NullDistns[0], fisherCounts, ModelScorer.PhyloTree.LeafCollection);
double nullLLTarg = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializerTarg, nullParamsTarg);
Score nullScoreTarg = Score.GetInstance(nullLLTarg, nullParamsTarg, previousResults.NullScores[1].Distribution);
OptimizationParameterList nullParamsPred = previousResults.NullScores[0].OptimizationParameters;
MessageInitializerDiscrete nullMessageInitializerPred = MessageInitializerDiscrete.GetInstance(targetMap, predictorMap, (DistributionDiscreteSingleVariable)NullDistns[1], fisherCounts, ModelScorer.PhyloTree.LeafCollection);
double nullLLPred = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializerPred, nullParamsPred);
Score nullScorePred = Score.GetInstance(nullLLPred, nullParamsPred, previousResults.NullScores[0].Distribution);
List <Score> nullScores = new List <Score>(new Score[] { nullScorePred, nullScoreTarg });
OptimizationParameterList altParams = previousResults.AltScore.OptimizationParameters;
double altLL;
if (((DistributionDiscreteJoint)AltDistn).ParametersCannotBeEvaluated(altParams))
{
// we'll get here only if one of the variables is always (or never) true. In this case, the variables must be independent.
altLL = nullLLTarg + nullLLPred;
}
else
{
MessageInitializerDiscrete altMessageInitializer = MessageInitializerDiscrete.GetInstance(CreateJointMap(predictorMap, targetMap), (DistributionDiscreteJoint)AltDistn, fisherCounts, ModelScorer.PhyloTree.LeafCollection);
altLL = ModelScorer.ComputeLogLikelihoodModelGivenData(altMessageInitializer, altParams);
}
Score altScore = Score.GetInstance(altLL, altParams, previousResults.AltScore.Distribution);
EvaluationResults evalResults = EvaluationResultsDiscrete.GetInstance(this, nullScores, altScore, fisherCounts, ChiSquareDegreesOfFreedom);
return(evalResults);
}
public override EvaluationResults EvaluateModelOnData(Converter <Leaf, SufficientStatistics> predictorMap, Converter <Leaf, SufficientStatistics> targetMap)
{
EvaluationResults evalResults;
int[] fisherCounts = ModelScorer.PhyloTree.FisherCounts(predictorMap, targetMap);
int[] realFisherCounts = fisherCounts; // for compatability when NAIVE_EQUILIBRIUM is set
#if NAIVE_EQUILIBRIUM
//USE THIS FOR BACKWARDS COMPATABILITY
int[] tempCounts = ModelScorer.PhyloTree.CountsOfLeaves(targetMap);
fisherCounts = tempCounts;
#endif
//MessageInitializerDiscrete nullMessageInitializer = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, NullDistn, fisherCounts, ModelScorer.PhyloTree.LeafCollection);
//if (TryShortCutFromCounts(realFisherCounts, nullMessageInitializer, out evalResults))
//{
// return evalResults;
//}
//Score nullScore = ModelScorer.MaximizeLikelihood(nullMessageInitializer);
bool isInvariant;
Score nullScoreTarg = ComputeSingleVariableScore(predictorMap, targetMap, NullDistn, fisherCounts, out isInvariant);
Score altScore = ComputeConditionalVariableScore(predictorMap, targetMap, nullScoreTarg, fisherCounts);
//(realFisherCounts, nullScoreTarg, out evalResults))
//{
// return evalResults;
//}
//MessageInitializerDiscrete altMessageInitializer = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, (DistributionDiscreteConditional)AltDistn, nullScore.OptimizationParameters, ModelScorer.PhyloTree.LeafCollection);
//Score condScore = ModelScorer.MaximizeLikelihood(altMessageInitializer);
List <Score> nullScores = new List <Score>();
if (_includePredictorInScore)
{
int[] predFisherCounts = new int[] { realFisherCounts[0], realFisherCounts[2], realFisherCounts[1], realFisherCounts[3] };
Score predNullScore = ComputeSingleVariableScore(targetMap, predictorMap, NullDistn, predFisherCounts, out isInvariant);
nullScores.Add(predNullScore);
// conditional model altScore doesn't include predLL. If we're here, we want to add it to make it comparable to joint or reverseConditional
altScore = Score.GetInstance(altScore.Loglikelihood + predNullScore.Loglikelihood, altScore.OptimizationParameters, altScore.Distribution);
}
nullScores.Add(nullScoreTarg);
evalResults = EvaluationResultsDiscrete.GetInstance(this, nullScores, altScore, realFisherCounts, ChiSquareDegreesOfFreedom);
#if DEBUG
MessageInitializerDiscrete nullMessageInitializer = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, NullDistn, fisherCounts, ModelScorer.PhyloTree.LeafCollection);
MessageInitializerDiscrete altMessageInitializer = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, (DistributionDiscreteConditional)AltDistn, nullScoreTarg.OptimizationParameters, ModelScorer.PhyloTree.LeafCollection);
double nullLL = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializer, nullScoreTarg.OptimizationParameters);
double altLL = ModelScorer.ComputeLogLikelihoodModelGivenData(altMessageInitializer, altScore.OptimizationParameters);
if (_includePredictorInScore)
{
int[] predFisherCounts = new int[] { realFisherCounts[0], realFisherCounts[2], realFisherCounts[1], realFisherCounts[3] };
MessageInitializerDiscrete nullMessageInitializerPred = MessageInitializerDiscrete.GetInstance(targetMap, predictorMap, NullDistn, predFisherCounts, ModelScorer.PhyloTree.LeafCollection);
double nullLLPred = ModelScorer.ComputeLogLikelihoodModelGivenData(nullMessageInitializerPred, nullScores[0].OptimizationParameters);
altLL += nullLLPred;
}
EvaluationResults evalResults2 = EvaluateModelOnDataGivenParams(predictorMap, targetMap, evalResults);
double eps = 1E-10;
Debug.Assert(ComplexNumber.ApproxEqual(nullLL, nullScoreTarg.Loglikelihood, eps));
Debug.Assert(ComplexNumber.ApproxEqual(altLL, altScore.Loglikelihood, eps));
Debug.Assert(ComplexNumber.ApproxEqual(evalResults.NullLL, evalResults2.NullLL, eps) && ComplexNumber.ApproxEqual(evalResults.AltLL, evalResults2.AltLL, eps), "In ModelEvaluatorCond, results of maximizing LL and computing LL from same params are not the same.");
#endif
return(evalResults);
}
public void ScoreTree(
ModelScorer modelScorer,
PhyloTree phyloTree,
string predictorSparseFileName,
string targetSparseFileName,
string predictorVariableName,
string targetVariableName,
double[] nullModelArgs,
double[] altModelArgs)
{
//Dictionary<string, Dictionary<string, SufficientStatistics>> predictorVariableToCaseIdToRealNonMissingValue = LoadSparseFileInMemory(predictorSparseFileName);
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > predictorNameAndCaseIdToNonMissingValueEnumeration = LoadSparseFileEnumeration(predictorSparseFileName);
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > targetNameAndCaseIdToNonMissingValueEnumeration = LoadSparseFileEnumeration(targetSparseFileName);
RangeCollection nullIndexRangeCollection = RangeCollection.GetInstance(-1, -1);
NullDataCollection nullDataGenerator =
CreateNullDataGenerator("PredictorPermutation", modelScorer, phyloTree, nullIndexRangeCollection,
predictorNameAndCaseIdToNonMissingValueEnumeration, targetNameAndCaseIdToNonMissingValueEnumeration);
UniversalWorkList workList = UniversalWorkList.GetInstance(
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration,
//targetNameAndCaseIdToNonMissingValueEnumeration,
nullDataGenerator, nullIndexRangeCollection, AlwaysKeep <Dictionary <string, string> > .GetInstance());
foreach (RowData rowAndTargetData in workList.List())
{
if (rowAndTargetData.Row[PhyloTree.PredictorVariableColumnName] == predictorVariableName &&
rowAndTargetData.Row[PhyloTree.TargetVariableColumnName] == targetVariableName)
{
Dictionary <string, SufficientStatistics> caseIdToNonNullPredictorValue = rowAndTargetData.PredictorData;//workList.GetCaseIdToNonMissingValueForNullIndexAndPredictorVariable(-1, predictorVariableName);
Dictionary <string, SufficientStatistics> caseIdToNonMissingTargetValue = rowAndTargetData.TargetData;
Converter <Leaf, SufficientStatistics> targetDistributionMap = CreateSufficientStatisticsMap(caseIdToNonMissingTargetValue);
Converter <Leaf, SufficientStatistics> predictorDistributionClassFunction = CreateSufficientStatisticsMap(caseIdToNonNullPredictorValue);
Converter <Leaf, SufficientStatistics> altDistributionMap = CreateAlternativeSufficientStatisticsMap(predictorDistributionClassFunction, targetDistributionMap);
double logLikelihood;
Score scoreIndTarget, scoreIndPredictor, scoreAlt;
MessageInitializer messageInitializer;
OptimizationParameterList nullParams = NullModelDistribution.GetParameters(nullModelArgs);
OptimizationParameterList altParams = AltModelDistribution.GetParameters(altModelArgs);
Console.WriteLine(SpecialFunctions.CreateTabString("Variable", nullParams.ToStringHeader(), "LogL"));
messageInitializer = modelScorer.CreateMessageInitializer(predictorDistributionClassFunction, targetDistributionMap, NullModelDistribution);
logLikelihood = modelScorer.ComputeLogLikelihoodModelGivenData(messageInitializer, nullParams);
scoreIndTarget = Score.GetInstance(logLikelihood, nullParams);
Console.WriteLine("Target\t" + scoreIndTarget);
messageInitializer = modelScorer.CreateMessageInitializer(targetDistributionMap, predictorDistributionClassFunction, NullModelDistribution);
logLikelihood = modelScorer.ComputeLogLikelihoodModelGivenData(messageInitializer, nullParams);
modelScorer.ComputeLogLikelihoodModelGivenData(messageInitializer, nullParams);
scoreIndPredictor = Score.GetInstance(logLikelihood, nullParams);
Console.WriteLine("Predictor\t" + scoreIndPredictor);
Console.WriteLine("\n" + SpecialFunctions.CreateTabString("Variable", altParams.ToStringHeader(), "LogL"));
messageInitializer = modelScorer.CreateMessageInitializer(null, altDistributionMap, AltModelDistribution);
logLikelihood = modelScorer.ComputeLogLikelihoodModelGivenData(messageInitializer, altParams);
scoreAlt = Score.GetInstance(logLikelihood, altParams);
Console.WriteLine(SpecialFunctions.CreateTabString(AltModelDistribution, scoreAlt));
}
}
}
