public override EvaluationResults EvaluateModelOnData(Converter <Leaf, SufficientStatistics> predMap, Converter <Leaf, SufficientStatistics> targMap)
{
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);
Score nullScore = ModelScorer.MaximizeLikelihood(nullMessageInitializer);
MessageInitializerGaussian altMessageInitializer = MessageInitializerGaussian.GetInstance(
predMap, targMap, (DistributionGaussianConditional)AltDistn, ModelScorer.PhyloTree.LeafCollection);
Score altScore = ModelScorer.MaximizeLikelihood(altMessageInitializer);
EvaluationResults evalResults = EvaluationResultsGaussian.GetInstance(this, nullScore, altScore, predCount, targCount, globalNonMissingCount, ChiSquareDegreesOfFreedom);
return(evalResults);
}
public override EvaluationResults EvaluateModelOnData(Converter <Leaf, SufficientStatistics> predictorMap, Converter <Leaf, SufficientStatistics> targetMap)
{
int[] realFisherCounts = ModelScorer.PhyloTree.FisherCounts(predictorMap, targetMap);
int tt = realFisherCounts[(int)TwoByTwo.ParameterIndex.TT];
int tf = realFisherCounts[(int)TwoByTwo.ParameterIndex.TF];
int ft = realFisherCounts[(int)TwoByTwo.ParameterIndex.FT];
int ff = realFisherCounts[(int)TwoByTwo.ParameterIndex.FF];
int[] fisherCountsPred = new int[] { tt, ft, tf, ff }; //ModelScorer.PhyloTree.FisherCounts(targetMap, predictorMap);
int[] fisherCountsTarg = realFisherCounts;
#if NAIVE_EQUILIBRIUM
//USE THIS FOR BACKWARDS COMPATABILITY
int[] tempCountsPred = ModelScorer.PhyloTree.CountsOfLeaves(predictorMap);
int[] tempCountsTarg = ModelScorer.PhyloTree.CountsOfLeaves(targetMap);
fisherCountsPred = tempCountsPred;
fisherCountsTarg = tempCountsTarg;
#endif
bool predIsInvariant, targIsInvariant;
Score nullScorePred = ComputeSingleVariableScore(targetMap, predictorMap, (DistributionDiscreteSingleVariable)NullDistns[0], fisherCountsPred, out predIsInvariant);
Score nullScoreTarg = ComputeSingleVariableScore(predictorMap, targetMap, (DistributionDiscreteSingleVariable)NullDistns[1], fisherCountsTarg, out targIsInvariant);
List <Score> nullScores = new List <Score>(new Score[] { nullScorePred, nullScoreTarg });
OptimizationParameterList initParams = ((DistributionDiscreteJoint)AltDistn).GenerateInitialParams(nullScorePred.OptimizationParameters, nullScoreTarg.OptimizationParameters);
Score jointScore;
if (predIsInvariant || targIsInvariant) // cannot compute parameters in this case. They come directly from the single variable params
{
double jointLL = nullScorePred.Loglikelihood + nullScoreTarg.Loglikelihood;
jointScore = Score.GetInstance(jointLL, initParams, AltDistn);
}
else
{
MessageInitializerDiscrete altMessageInitializer = MessageInitializerDiscrete.GetInstance(CreateJointMap(predictorMap, targetMap), (DistributionDiscreteJoint)AltDistn, initParams, ModelScorer.PhyloTree.LeafCollection);
jointScore = ModelScorer.MaximizeLikelihood(altMessageInitializer);
}
EvaluationResults evalResults = EvaluationResultsDiscrete.GetInstance(this, nullScores, jointScore, realFisherCounts, ChiSquareDegreesOfFreedom);
return(evalResults);
}
private Score ComputeConditionalVariableScore(
Converter <Leaf, SufficientStatistics> predictorMap,
Converter <Leaf, SufficientStatistics> targetMap,
Score nullScore,
int[] fisherCounts)
{
int tt = fisherCounts[(int)TwoByTwo.ParameterIndex.TT];
int tf = fisherCounts[(int)TwoByTwo.ParameterIndex.TF];
int ft = fisherCounts[(int)TwoByTwo.ParameterIndex.FT];
int sum = SpecialFunctions.Sum(fisherCounts);
Score altScore;
if (tt + ft == sum || tt + ft == 0) // target is always true or false
{
bool isNaN = sum == 0;
OptimizationParameterList altParamList = AltDistn.GetParameters();
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Predictor1].Value = 0;
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Predictor2].Value = 0;
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Lambda].Value = isNaN ? double.NaN : 0;
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Equilibrium].Value = (double)(tt + ft) / sum;
altScore = Score.GetInstance(isNaN ? double.NaN : 0, altParamList, AltDistn);
}
else if (tt + tf == 0 || tt + tf == sum) // predictor is always true or false
{
OptimizationParameterList nullParamList = nullScore.OptimizationParameters;
OptimizationParameterList altParamList = AltDistn.GetParameters();
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Predictor1].Value = nullParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Predictor1].Value;
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Predictor2].Value = nullParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Predictor2].Value;
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Lambda].Value = nullParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Lambda].Value;
altParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Equilibrium].Value = nullParamList[(int)DistributionDiscreteSingleVariable.ParameterIndex.Equilibrium].Value;
altScore = Score.GetInstance(nullScore.Loglikelihood, altParamList, AltDistn);
}
else // compute ML using ModelScorer
{
MessageInitializerDiscrete altMessageInitializer = MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, (DistributionDiscreteConditional)AltDistn, nullScore.OptimizationParameters, ModelScorer.PhyloTree.LeafCollection);
altScore = ModelScorer.MaximizeLikelihood(altMessageInitializer);
}
return(altScore);
}
public override Dictionary <string, SufficientStatistics> GenerateRandomMapping(Dictionary <string, SufficientStatistics> realCaseIdToNonMissingValue, ref Random random)
{
//!!!!put check in to make sure ISufficientSTatistics is reall BooleanStatistics
Converter <Leaf, SufficientStatistics> leafToDistnClassFunction = PhyloDDriver.CreateSufficientStatisticsMap(realCaseIdToNonMissingValue);
PhyloTree tree = _modelScorer.PhyloTree;
MessageInitializer messageInitializer = MessageInitializerDiscrete.GetInstance(leafToDistnClassFunction, _discreteDistribution, new int[] { 1, 1 }, tree.LeafCollection);
Score score = _modelScorer.MaximizeLikelihood(messageInitializer);
double percentNonMissing = (double)tree.CountOfNonMissingLeaves(realCaseIdToNonMissingValue) /
(double)SpecialFunctions.Count(tree.LeafCollection);
double equilibrium = score.OptimizationParameters[(int)DistributionDiscreteConditional.ParameterIndex.Equilibrium].Value;
double lambda = score.OptimizationParameters[(int)DistributionDiscreteConditional.ParameterIndex.Lambda].Value;
Dictionary <string, BooleanStatistics> randomCaseIdToNonMissingValue = tree.EvolveBinaryTree(equilibrium, lambda, 1 - percentNonMissing, ref random);
Dictionary <string, SufficientStatistics> converted;
SpecialFunctions.ConvertDictionaryToBaseClasses(randomCaseIdToNonMissingValue, out converted);
return(converted);
}
protected Score ComputeSingleVariableScore(
Converter <Leaf, SufficientStatistics> predictorMap,
Converter <Leaf, SufficientStatistics> targetMap,
DistributionDiscreteSingleVariable nullDistn,
int[] fisherCounts,
out bool variableIsInvariant)
{
MessageInitializerDiscrete nullMessageInitializer =
MessageInitializerDiscrete.GetInstance(predictorMap, targetMap, nullDistn, fisherCounts, ModelScorer.PhyloTree.LeafCollection);
double p = (double)TwoByTwo.GetRightSum(fisherCounts) / SpecialFunctions.Sum(fisherCounts);
Score nullScore;
if (TryGetSingleVariableScoreFromCounts(nullMessageInitializer, p, out nullScore))
{
variableIsInvariant = true;
}
else
{
variableIsInvariant = false;
nullScore = ModelScorer.MaximizeLikelihood(nullMessageInitializer);
}
return(nullScore);
}