internal static KeepTest <Dictionary <string, string> > GetInstance(bool keepIt)
{
if (keepIt)
{
return(AlwaysKeep <Dictionary <string, string> > .GetInstance());
}
KeepEndOfGag aKeepEndOfGag = new KeepEndOfGag();
aKeepEndOfGag.KeepIt = keepIt;
return(aKeepEndOfGag);
}
internal static KeepTest <Dictionary <string, string> > GetInstance(int k1)
{
if (k1 == 0)
{
return(AlwaysKeep <Dictionary <string, string> > .GetInstance());
}
K1 aK1 = new K1();
aK1.k1 = k1;
return(aK1);
}
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));
}
}
}
static void Main(string[] argsx)
{
try
{
List <string> argumentCollection = new List <string>(argsx);
bool auditRowIndexValues = true;
string noAuditFlag = "-NoAudit";
if (argumentCollection.Contains(noAuditFlag))
{
argumentCollection.Remove(noAuditFlag);
auditRowIndexValues = false;
}
double maxPValue = 1.0; // Ignore pValues greater than this
string maxPValueFlag = "-MaxPValue";
int maxPValuePosition = argumentCollection.IndexOf(maxPValueFlag);
if (maxPValuePosition >= 0)
{
argumentCollection.RemoveAt(maxPValuePosition);
SpecialFunctions.CheckCondition(maxPValuePosition < argumentCollection.Count, "pValue expected after -MaxPValue");
maxPValue = double.Parse(argumentCollection[maxPValuePosition]);
argumentCollection.RemoveAt(maxPValuePosition);
}
KeepTest <Dictionary <string, string> > keepTest; // Ignore pValues greater than this
string keepTestFlag = "-KeepTest";
int keepTestPosition = argumentCollection.IndexOf(keepTestFlag);
if (keepTestPosition >= 0)
{
argumentCollection.RemoveAt(keepTestPosition);
SpecialFunctions.CheckCondition(keepTestPosition < argumentCollection.Count, "KeepTest expected after -MaxPValue");
keepTest = KeepTest <Dictionary <string, string> > .GetInstance(null, argumentCollection[keepTestPosition]);
argumentCollection.RemoveAt(keepTestPosition);
}
else
{
keepTest = new AlwaysKeep <Dictionary <string, string> >();
}
SpecialFunctions.CheckCondition(argumentCollection.Count > 1, "Expect 2 or more parameters");
string outputFileName = argumentCollection[argumentCollection.Count - 1];
argumentCollection.RemoveAt(argumentCollection.Count - 1);
Tabulate.CreateTabulateReport(argumentCollection, outputFileName, keepTest, maxPValue, auditRowIndexValues);
}
catch (Exception e)
{
Console.WriteLine("");
Console.WriteLine(e.Message);
if (e.InnerException != null)
{
Console.WriteLine(e.InnerException.Message);
}
Console.WriteLine(@"
Usage:
Tabulate {-NoAudit} {-MaxPValue maxPValue} {-KeepTest keeptest} broadInputFileNamePattern1 {broadInputFileNamePattern2 ...} outputFileName
Each broadInputFileNamePattern1 is of the form
narrowInputFileNamePattern1{+narrowInputFileNamePattern2...}
Each broadInputFileNamePattern must cover the same range of nullIndexes (including -1, the real index).
Each narrowInputFileNamePattern within a broadInputFileNamePattern must cover a disjoint
set of nullIndexes.
For example
Tabulate -MaxPValue .05 raw\GagEscape0606*-1-19*.txt raw\GagReversion0606*-1-9*.txt+raw\GagReversion0606*10-19*.txt AllGag.qValue.txt
Notice that broad pattern
raw\GagEscape0606*-1-19*.txt
has one narrow pattern and covers nullIndex's -1 to 19
While broad pattern
raw\GagReversion0606*-1-9*.txt+raw\GagReversion0606*10-19*.txt
has two narrow patterns:
raw\GagReversion0606*-1-9*.txt, which covers nullIndexes -1 to 9
raw\GagReversion0606*10-19*.txt which covers nullIndexes 10 to 19
By default, ""Tabulate"" will audit the ""rowIndex"" and ""rowCount"" values
in the input to remove duplicates and check that all rows are present.
Use ""-NoAudit"" when this is not desired.
Use ""-MaxPValue maxPValue"", where maxPValue is a double, to ignore rows with obviously bad rows
");
throw;
}
}
