public static UniversalWorkList GetInstance(
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > predictorNameAndCaseIdToNonMissingValueEnumeration,
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > targetNameAndCaseIdToNonMissingValueEnumeration,
//Dictionary<string, Dictionary<string, SufficientStatistics>> predictorVariableToCaseIdToRealNonMissingValue,
NullDataCollection nullDataCollection,
RangeCollection nullIndexRange,
KeepTest <Dictionary <string, string> > keepTest
)
{
//SpecialFunctions.CheckCondition(-1 <= nullIndexStart && nullIndexStart <= nullIndexLast);
bool enumeratePairs = keepTest is KeepPredictorTargetPairs;
if (keepTest is KeepCollection <Dictionary <string, string> > )
{
foreach (KeepTest <Dictionary <string, string> > keepTestInCollection in ((KeepCollection <Dictionary <string, string> >)keepTest).KeepTestCollection)
{
if (keepTestInCollection is KeepPredictorTargetPairs)
{
enumeratePairs = true;
}
}
}
UniversalWorkList aUniversalWorkList;
if (enumeratePairs)
{
aUniversalWorkList = UniversalWorkListPredTargPairs.GetInstance(
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration,
nullDataCollection,
nullIndexRange,
keepTest
);
}
else
{
aUniversalWorkList = new UniversalWorkList(
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration,
nullDataCollection,
nullIndexRange,
keepTest
);
}
// aUniversalWorkList._predictorNameAndCaseIdToNonMissingValueEnumeration = predictorNameAndCaseIdToNonMissingValueEnumeration;
// aUniversalWorkList._targetNameAndCaseIdToNonMissingValueEnumeration = targetNameAndCaseIdToNonMissingValueEnumeration;
//// aUniversalWorkList._targetVariables = targetVariables;
//// aUniversalWorkList._predictorVariableToCaseIdToNonMissingValue = predictorVariableToCaseIdToRealNonMissingValue;
// aUniversalWorkList._keepTest = keepTest;
// aUniversalWorkList._nullDataCollection = nullDataCollection;
// aUniversalWorkList._nullIndexRange = nullIndexRange;
return(aUniversalWorkList);
}
protected NullDataCollection CreateNullDataGenerator(
string nullDataGeneratorName,
ModelScorer modelScorer,
PhyloTree phyloTree,
RangeCollection nullIndexRangeCollection,
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > predictorNameAndCaseIdToNonMissingValueEnumeration,
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > targetNameAndCaseIdToNonMissingValueEnumeration)
{
return(NullDataCollection.GetInstance(
NullDataGenerator.GetInstance(nullDataGeneratorName, modelScorer, phyloTree, this),
nullIndexRangeCollection,
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration));
}
protected UniversalWorkList(
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > predictorNameAndCaseIdToNonMissingValueEnumeration,
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > targetNameAndCaseIdToNonMissingValueEnumeration,
NullDataCollection nullDataCollection,
RangeCollection nullIndexRange,
KeepTest <Dictionary <string, string> > keepTest
)
{
_predictorNameAndCaseIdToNonMissingValueEnumeration = predictorNameAndCaseIdToNonMissingValueEnumeration;
_targetNameAndCaseIdToNonMissingValueEnumeration = targetNameAndCaseIdToNonMissingValueEnumeration;
_keepTest = keepTest;
_nullDataCollection = nullDataCollection;
_nullIndexRange = nullIndexRange;
//Console.WriteLine("In UniversalWorkList constructor.");
}
protected UniversalWorkListPredTargPairs(
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > predictorNameAndCaseIdToNonMissingValueEnumeration,
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > targetNameAndCaseIdToNonMissingValueEnumeration,
NullDataCollection nullDataCollection,
RangeCollection nullIndexRange,
KeepTest <Dictionary <string, string> > keepTest
)
:
base(
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration,
nullDataCollection, nullIndexRange,
keepTest
)
{
//Console.WriteLine("In UniversalWorkListPredTargPairs constructor.");
}
new public static UniversalWorkList GetInstance(
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > predictorNameAndCaseIdToNonMissingValueEnumeration,
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > > targetNameAndCaseIdToNonMissingValueEnumeration,
//Dictionary<string, Dictionary<string, SufficientStatistics>> predictorVariableToCaseIdToRealNonMissingValue,
NullDataCollection nullDataCollection,
RangeCollection nullIndexRange,
KeepTest <Dictionary <string, string> > keepTest
)
{
//SpecialFunctions.CheckCondition(-1 <= nullIndexStart && nullIndexStart <= nullIndexLast);
UniversalWorkList aUniversalWorkList = new UniversalWorkListPredTargPairs(
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration,
nullDataCollection,
nullIndexRange,
keepTest
);
return(aUniversalWorkList);
}
public void Run(
ModelScorer modelScorer,
PhyloTree phyloTree,
string predictorSparseFileName,
string targetSparseFileName,
string leafDistributionName,
string nullDataGeneratorName,
KeepTest <Dictionary <string, string> > keepTest,
RangeCollection skipRowIndexRangeCollectionOrNull,
string shortName,
string outputDirectoryName,
RangeCollection pieceIndexRangeCollection, int pieceCount,
RangeCollection nullIndexRangeCollection,
string optimizerName)
{
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
Directory.CreateDirectory(outputDirectoryName);
string outputFileName = string.Format(@"{0}\{1}.{2}.{3}.{4}.{5}.{6}{7}.txt",
outputDirectoryName, shortName,
leafDistributionName, nullDataGeneratorName,
nullIndexRangeCollection,
pieceCount,
pieceIndexRangeCollection,
skipRowIndexRangeCollectionOrNull == null ? "" : ".Skip" + skipRowIndexRangeCollectionOrNull.Count().ToString()
);
#region from PhyloTree refactor
//Dictionary<string, Dictionary<string, bool>> predictorVariableToCaseIdToRealNonMissingValue = LoadSparseFileInMemory<bool>(predictorSparseFileName);
//IEnumerable<Pair<string, Dictionary<string, T>>> targetNameAndCaseIdToNonMissingValueEnumeration = LoadSparseFileEnumeration<T>(targetSparseFileName);
//NullDataCollection nullDataGenerator =
// NullDataCollection.GetInstance(this, modelTester, nullIndexRangeCollection, predictorVariableToCaseIdToRealNonMissingValue);
//UniversalWorkList<T> workList = UniversalWorkList<T>.GetInstance(
// predictorVariableToCaseIdToRealNonMissingValue,
// targetNameAndCaseIdToNonMissingValueEnumeration,
// nullDataGenerator, nullIndexRangeCollection, keepTest);
#endregion
bool speedOverMemory = true;
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > >
predictorNameAndCaseIdToNonMissingValueEnumeration = CreateNameAndCaseIdToNonMissingValueEnumeration(predictorSparseFileName, speedOverMemory);
IEnumerable <Pair <string, Dictionary <string, SufficientStatistics> > >
targetNameAndCaseIdToNonMissingValueEnumeration = CreateNameAndCaseIdToNonMissingValueEnumeration(targetSparseFileName, speedOverMemory);
NullDataCollection nullDataGenerator =
CreateNullDataGenerator(nullDataGeneratorName, modelScorer, phyloTree, nullIndexRangeCollection,
predictorNameAndCaseIdToNonMissingValueEnumeration, targetNameAndCaseIdToNonMissingValueEnumeration);
UniversalWorkList workList = UniversalWorkList.GetInstance(
predictorNameAndCaseIdToNonMissingValueEnumeration,
targetNameAndCaseIdToNonMissingValueEnumeration,
nullDataGenerator, nullIndexRangeCollection, keepTest);
int workListCount = SpecialFunctions.Count(workList.List());
int effectiveWorkListCount;
if (skipRowIndexRangeCollectionOrNull == null)
{
effectiveWorkListCount = workListCount;
}
else
{
effectiveWorkListCount = 0;
for (int iRowIndex = 0; iRowIndex < workListCount; iRowIndex++)
{
if (!skipRowIndexRangeCollectionOrNull.Contains(iRowIndex))
{
effectiveWorkListCount++;
}
}
}
Console.WriteLine("{0} Total rows. Skipping {1} of them.", workListCount, workListCount - effectiveWorkListCount);
using (TextWriter textWriter = File.CreateText(outputFileName))
{
textWriter.WriteLine(Header);
int rowIndex = -1;
int effectiveRowIndex = -1;
foreach (RowData rowAndTargetData in workList.List())
{
//!!!make all these parameters and the calculation a class
++rowIndex;
Debug.Assert(rowIndex < workListCount); // real assert
if (skipRowIndexRangeCollectionOrNull == null || !skipRowIndexRangeCollectionOrNull.Contains(rowIndex))
{
++effectiveRowIndex;
int workIndex = ExtractWorkIndex(effectiveRowIndex, pieceCount, effectiveWorkListCount);
if (pieceIndexRangeCollection.Contains(workIndex))
{
Debug.WriteLine("WorkItemIndex " + rowIndex.ToString());
string reportLine;
try
{
reportLine =
CreateReportLine(modelScorer, phyloTree, rowAndTargetData, workList, rowIndex, workListCount, workIndex);
}
catch (OutOfMemoryException)
{
Console.WriteLine("OUT OF MEMORY!! Clearing cache and trying to recover where we left off.");
modelScorer.ClearCache();
reportLine =
CreateReportLine(modelScorer, phyloTree, rowAndTargetData, workList, rowIndex, workListCount, workIndex);
}
textWriter.WriteLine(reportLine);
textWriter.Flush();
}
}
}
}
stopwatch.Stop();
Console.WriteLine("Running time: " + stopwatch.Elapsed);
}
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));
}
}
}