private static bool ProcessRow(RangeCollection skipRowIndexRangeCollectionOrNull, RangeCollection pieceIndexRangeCollection, int rowIndex, int workIndex)
{
bool doTheWork = true;
if (skipRowIndexRangeCollectionOrNull != null && skipRowIndexRangeCollectionOrNull.Contains(rowIndex))
{
doTheWork = false;
}
if (!pieceIndexRangeCollection.Contains(workIndex))
{
doTheWork = false;
}
return(doTheWork);
}
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);
}
static public void Test()
{
RangeCollection aRangeCollection = RangeCollection.GetInstance();
aRangeCollection.Add(0);
SpecialFunctions.CheckCondition("0-0" == aRangeCollection.ToString());
aRangeCollection.Add(1);
SpecialFunctions.CheckCondition("0-1" == aRangeCollection.ToString());
aRangeCollection.Add(4);
SpecialFunctions.CheckCondition("0-1,4-4" == aRangeCollection.ToString());
aRangeCollection.Add(5);
SpecialFunctions.CheckCondition("0-1,4-5" == aRangeCollection.ToString());
aRangeCollection.Add(7);
SpecialFunctions.CheckCondition("0-1,4-5,7-7" == aRangeCollection.ToString());
aRangeCollection.Add(2);
SpecialFunctions.CheckCondition("0-2,4-5,7-7" == aRangeCollection.ToString());
aRangeCollection.Add(3);
SpecialFunctions.CheckCondition("0-5,7-7" == aRangeCollection.ToString());
aRangeCollection.Add(6);
SpecialFunctions.CheckCondition("0-7" == aRangeCollection.ToString());
aRangeCollection.Add(-10);
SpecialFunctions.CheckCondition("-10--10,0-7" == aRangeCollection.ToString());
aRangeCollection.Add(-5);
SpecialFunctions.CheckCondition("-10--10,-5--5,0-7" == aRangeCollection.ToString());
aRangeCollection = RangeCollection.Parse("1-5,7-12,13-14");
Console.WriteLine(aRangeCollection);
Console.WriteLine(aRangeCollection.Contains(3));
Console.WriteLine(aRangeCollection.Contains(12));
Console.WriteLine(aRangeCollection.Contains(13));
Console.WriteLine(aRangeCollection.Contains(6));
aRangeCollection = RangeCollection.Parse("-10--5,-1-14");
Console.WriteLine(aRangeCollection);
Console.WriteLine(aRangeCollection.Contains(-12));
Console.WriteLine(aRangeCollection.Contains(-10));
Console.WriteLine(aRangeCollection.Contains(-7));
Console.WriteLine(aRangeCollection.Contains(-5));
Console.WriteLine(aRangeCollection.Contains(-4));
Console.WriteLine(aRangeCollection.Contains(0));
Console.WriteLine(aRangeCollection.Contains(1));
Console.WriteLine(aRangeCollection.Contains(-2));
Console.WriteLine("Count: " + aRangeCollection.Count());
Console.WriteLine("Count -5 to 2: " + aRangeCollection.Count(-5, 2));
RangeCollectionCollection rcc = RangeCollectionCollection.GetInstance(aRangeCollection);
Console.WriteLine(rcc);
Console.WriteLine(rcc.GetContainingRangeCollection(-12));
Console.WriteLine(rcc.GetContainingRangeCollection(-10));
Console.WriteLine(rcc.GetContainingRangeCollection(-5));
Console.WriteLine(rcc.GetContainingRangeCollection(3));
Console.WriteLine(rcc.GetContainingRangeCollection(15));
}
