void KKJob::ProcessStatusStr (const KKStr& statusStr)
{
log.Level (30) << "KKJob::ProcessStatusStr[" << statusStr << "]" << endl;
KKStr fieldName;
KKStr fieldValue;
VectorKKStr fields = statusStr.Split ('\t');
kkuint32 fieldNum = 0;
while (fieldNum < fields.size ())
{
fieldName = fields[fieldNum];
fieldNum++;
if (fieldNum < fields.size ())
{
fieldValue = fields[fieldNum];
fieldNum++;
}
else
{
fieldValue = "";
}
fieldName.Upper ();
fieldValue.TrimLeft ("\n\r\t ");
fieldValue.TrimRight ("\n\r\t ");
if (fieldName.CompareIgnoreCase ("JOBID") == 0)
jobId = atoi (fieldValue.Str ());
else if (fieldName.CompareIgnoreCase ("PARENTID") == 0)
parentId = atoi (fieldValue.Str ());
else if (fieldName.CompareIgnoreCase ("STATUS") == 0)
status = JobStatusFromStr (fieldValue);
else if (fieldName.CompareIgnoreCase ("NumProcessors") == 0)
numProcessors = fieldValue.ToInt ();
else if (fieldName.CompareIgnoreCase ("NumPorcessesAllowed") == 0)
numPorcessesAllowed = fieldValue.ToInt ();
else if (fieldName.CompareIgnoreCase ("Prerequisites") == 0)
PrerequisitesFromStr (fieldValue);
else
{
ProcessStatusField (fieldName, fieldValue);
}
}
} /* ProcessStatusStr */
void DataBaseServer::ParseParameterStr (const KKStr& parameterStr)
{
VectorKKStr parameterPairs = parameterStr.Split ("\t");
VectorKKStr::iterator idx;
for (idx = parameterPairs.begin (); idx != parameterPairs.end (); idx++)
{
VectorKKStr fields = (*idx).Split (":="); // Split by either ':' or '='
if (fields.size () < 2)
{
// Should be two fields; line must be malformed.
continue;
}
KKStr parameterName = fields[0].ToUpper ();
if ((parameterName == "EMBEDDED") || (parameterName == "EMB") || (parameterName == "E")) embedded = fields[1].ToBool ();
else if ((parameterName == "MYSQLDATADIR") || (parameterName == "MYSQL") || (parameterName == "MDD")) mySqlDataDir = fields[1];
else if ((parameterName == "DESCRIPTION") || (parameterName == "DESC") || (parameterName == "D")) description = fields[1];
else if ((parameterName == "HOSTNAME") || (parameterName == "HOST") || (parameterName == "H")) hostName = fields[1];
else if ((parameterName == "USERNAME") || (parameterName == "USER") || (parameterName == "U")) userName = fields[1];
else if ((parameterName == "PASSWORD") || (parameterName == "PW") || (parameterName == "P")) passWord = fields[1];
else if ((parameterName == "PORTNUM") || (parameterName == "PN")) portNum = fields[1].ToUint32 ();
else if ((parameterName == "DATABASENAME") || (parameterName == "DATABASE") || (parameterName == "DB")) dataBaseName = fields[1];
}
if (description.EqualIgnoreCase ("Embedded"))
embedded = true;
} /* ParseParameterStr */
void InstrumentDataPitchAndRoll::ProcessData (const KKStr& txt)
{
VectorKKStr fields = txt.Split (" \t\n\r");
if (fields.size () < 4)
return;
float pitch = -999.99f;
float roll = -999.99f;
KKStr fieldName = "";
KKStr fieldValue = "";
kkuint32 fieldNum = 0;
while (fieldNum < fields.size ())
{
fieldName = fields[fieldNum];
fieldName.Upper ();
fieldNum++;
if (fieldNum < fields.size ())
{
fieldValue = fields[fieldNum];
fieldNum++;
}
else
{
fieldValue = "";
}
if (fieldName == "R")
{
roll = fieldValue.ToFloat ();
}
else if (fieldName == "P")
{
pitch = fieldValue.ToFloat ();
}
}
manager->PitchAndRollData (curTextLineStartScanLine, pitch, roll);
} /* ProcessData */
void KKJob::PrerequisitesFromStr (const KKStr& s)
{
prerequisites.clear ();
if (s.CompareIgnoreCase ("None") != 0)
{
VectorKKStr fields = s.Split (',');
for (kkuint32 x = 0; x < fields.size (); ++x)
{
kkint32 p = fields[x].ToInt ();
prerequisites.push_back (p);
}
}
} /* PrerequisitesFromStr */
void InstrumentDataBatteryMeter::ProcessBatteryData (const KKStr& txt)
{
// We will be expecting 5 fields;
// <Current battery> <\t> <Bat 0 Voltage> <\t> .... <\t> <Bat-3 Voltage>
VectorKKStr fields = txt.Split (',');
if (fields.size () < (1 + numOfBatteries))
return;
// activeBattery is '1' based that is batteries '1' - '4'; so
// batteryLevels[0] = battery level for battery 1.
kkint32 activeBattery = fields[0].ToInt ();
if ((activeBattery < 1) || ((kkuint32)activeBattery > numOfBatteries))
return;
kkuint32 x;
for (x = 0; x < numOfBatteries; x++)
batteryLevels[x] = fields[x + 1].ToFloat ();
manager->BatteryData (curTextLineStartScanLine, activeBattery, batteryLevels);
} /* ProcessBatteryData */
void ImportGPSDataGPGGA (const KKStr& fileName)
{
RunLog log;
DataBasePtr dbConn = new DataBase (log);
ifstream i (fileName.Str ());
if (!i.is_open ())
{
log.Level (-1) << endl << endl
<< "ImpotrtGPSData Could not open file[" << fileName << "]" << endl
<< endl;
return;
}
log.Level (10) << endl << endl << endl << endl << endl
<< "ImpotrtGPSData FileName[" << fileName << "]" << endl << endl
<< endl;
char buff[20480];
bool firstPass = true;
int lastMinute = 0;
int linesRead = 0;
KKStr ln (256);
DateTime lastDateTime;
while (i.getline (buff, sizeof (buff)))
{
linesRead++;
ln = buff;
ln.TrimLeft ();
if (!ln.LocateStr ("GPGGA"))
continue;
VectorKKStr fields = ln.Parse (",");
if (fields.size () < 8)
continue;
if (!fields[2].EqualIgnoreCase ("$GPGGA"))
continue;
/*
0 1 2 3 4 5 6 7 8
06/01/2010, 23:59:59.818, $GPGGA, 235958, 2840.927, N, 08828.458, W, 2, 09,22.10,0,M,,,14,0000*12
06/02/2010, 00:00:10.818, $GPGGA, 000009, 2840.931, N, 08828.482, W, 1, 09,0.89,0,M,,,,*2D
06/02/2010, 00:00:21.802, $GPGGA, 000020, 2840.929, N, 08828.505, W, 1, 09,0.89,0,M,,,,*21
06/02/2010, 00:00:31.818, $GPGGA, 000030, 2840.924, N, 08828.526, W, 1, 09,0.89,0,M,,,,*2C
06/02/2010, 00:00:42.818, $GPGGA, 000041, 2840.917, N, 08828.547, W, 1, 09,0.89,0,M,,,,*2D
06/02/2010, 00:00:53.802, $GPGGA, 000052, 2840.906, N, 08828.568, W, 1, 09,1.00,0,M,,,,*22
06/02/2010, 00:01:03.802, $GPGGA, 000102, 2840.895, N, 08828.585, W, 1, 09,0.89,0,M,,,,*2E
06/02/2010, 00:01:13.818, $GPGGA, 000112, 2840.883, N, 08828.600, W, 1, 09,0.89,0,M,,,,*26
*/
KKStr dateStr = fields[0];
KKStr timeStr = fields[1];
KKStr latStr = fields[4];
KKStr logStr = fields[6];
auto x = latStr.LocateCharacter ('.');
if (!x)
continue;
KKStr latMinStr = latStr.SubStrPart (x - 2);
KKStr latDegStr = latStr.SubStrSeg (0, x - 2);
double latitude = latDegStr.ToDouble () + latMinStr.ToDouble () / 60.0;
if (fields[5].EqualIgnoreCase ("S"))
latitude = 0.0 - latitude;
x = logStr.LocateCharacter ('.');
if (!x)
continue;
KKStr logMinStr = logStr.SubStrPart (x - 2);
KKStr logDegStr = logStr.SubStrSeg (0, x - 2);
double longitude = logDegStr.ToDouble () + logMinStr.ToDouble () / 60.0;
if (fields[7].EqualIgnoreCase ("W"))
longitude = 0.0 - longitude;
DateType gmtDate (dateStr);
TimeType gmtTime (timeStr);
DateTime gmtDateTime (gmtDate, gmtTime);
DateTime localTime = gmtDateTime;
localTime.HoursAdd (-4);
DateTime startDT = localTime;
DateTime endDT = localTime;
if (firstPass)
{
firstPass = false;
startDT.SecondsAdd (-180);
}
else
{
DateTime deltaDT = localTime - lastDateTime;
long deltaSecs = (long)deltaDT.Seconds ();
startDT.SecondsAdd (-(deltaSecs / 2));
}
endDT.SecondsAdd (30);
if (gmtTime.Minute () != lastMinute)
{
lastMinute = gmtTime.Minute ();
log.Level (10) << "LinesRead[" << linesRead << "] File[" << osGetRootName (fileName) << "] GMT Time[" << gmtDate.MMM_DD_YYYY () << " - " << gmtTime.HH_MM_SS () << "]" << endl;
}
if ((endDT.Month () < 6) && (endDT.Day () < 28))
{
}
else
{
dbConn->InstrumentDataUpdateLatitudeAndLongitude (startDT, endDT, latitude, longitude);
}
lastDateTime = localTime;
}
i.close ();
delete dbConn;
dbConn = NULL;
} /* ImportGPSDataGPGGA */
void KKJobManager::ProcessJobXmlBlockOfText (const KKStr& startStr,
istream& i
)
{
if ((startStr.SubStrPart (0, 4) != "<KKJob ") || (startStr.LastChar () != '>'))
{
log.Level (-1) << endl
<< "KKJobManager::ProcessJobXmlBlockOfText ***ERROR*** StartStr[" << startStr << "] is not a KKJob String." << endl
<< endl;
return;
}
KKStr s = startStr.SubStrPart (5);
s.TrimLeft ();
s.ChopLastChar ();
KKStr jobTypeStr = "";
kkint32 jobId = -1;
VectorKKStr parameters = s.Split (',');
for (kkuint32 x = 0; x < parameters.size (); ++x)
{
KKStr parameterStr = parameters[x];
parameterStr.TrimLeft ();
parameterStr.TrimRight ();
KKStr fieldName = parameterStr.ExtractToken2 ("=");
fieldName.TrimLeft (); fieldName.TrimRight ();
KKStr fieldValue = parameterStr.ExtractToken2 ("=");
fieldValue.TrimLeft (); fieldValue.TrimRight ();
if (fieldName.CompareIgnoreCase ("JobType") == 0)
jobTypeStr = fieldValue;
else if (fieldName.CompareIgnoreCase ("JobId") == 0)
jobId = fieldValue.ToInt ();
}
if (jobTypeStr.Empty () || (jobId < 0))
{
log.Level (-1) << endl
<< "KKJobManager::ProcessJobXmlBlockOfText ***ERROR*** StartStr[" << startStr << "]." << endl
<< " JobType and/or JobId were not provided." << endl
<< endl;
return;
}
KKJobPtr j = jobs->LookUpByJobId (jobId);
if (j == NULL)
{
// We do not have this job in memory yet. We will have to create it now.
KKStr emptyStatusStr = "JobId\t" + StrFormatInt (jobId, "ZZZZ0");
j = KKJob::CallAppropriateConstructor (this, jobTypeStr, emptyStatusStr);
}
j->CompletedJobDataRead (i);
} /* ProcessJobXmlBlockOfText */
void RandomSplitJobManager::GenerateFinalResultsReport ()
{
KKStr reportFileName = osGetRootName (ManagerName ()) + "_Results.html;";
ofstream f (reportFileName.Str ());
f << "Run Time Parameters" << endl
<< "Run Time" << "\t" << osGetLocalDateTime () << endl
<< "configFileName" << "\t" << configFileName << endl
<< "DataFileName" << "\t" << dataFileName << endl
<< "Format" << "\t" << format->DriverName () << endl
<< "DataIndexFileName" << "\t" << dataIndexFileName << endl
<< "NumFolds" << "\t" << numFolds << endl
<< "NumSplits" << "\t" << numSplits << endl
<< "splitFraction" << "\t" << splitFraction << endl
<< endl;
KKJobList::const_iterator idx;
ConfusionMatrix2 avgResults (*(this->MLClasses ()));
KKB::uint x = 0;
for (idx = Jobs ()->begin (); idx != Jobs ()->end (); idx++)
{
RandomSplitJobPtr j = dynamic_cast<RandomSplitJobPtr> (*idx);
if (j->RandomSplitsResults () != NULL)
{
f << endl
<< "Random Split[" << j->SplitNum () << "]" << endl;
j->RandomSplitsResults ()->PrintConfusionMatrixTabDelimited (f);
f << endl << endl;
j->PrintClassCounts (f);
f << endl << endl;
avgResults.AddIn (*(j->RandomSplitsResults ()), log);
x++;
}
}
f << endl << "Mean Average of all random Splits." << endl;
avgResults.FactorCounts (1.0 / (double)x);
avgResults.PrintConfusionMatrixTabDelimited (f);
f << endl
<< endl
<< endl
<< endl
<< "Class Counts" << endl
<< endl;
kkuint32 numClasses = (kkuint32)mlClasses->size ();
VectorFloat classAccs;
VectorDouble knownCounts;
VectorDouble predCounts;
VectorDouble adjCounts;
VectorDouble adjCountsStdError;
VectorDouble predDelta;
VectorDouble adjDelta;
KKStr l1, l2, l3;
mlClasses->ExtractThreeTitleLines (l1, l2, l3);
VectorKKStr knownCountLines;
VectorKKStr predCountLines;
VectorKKStr adjCountLines;
VectorKKStr deltaPredCountLines;
VectorKKStr deltaAdjCountLines;
VectorKKStr accLines;
ConfusionMatrix2 totalCM (*MLClasses ());
int totalCmCount = 0;
// Known Counts
for (idx = Jobs ()->begin (); idx != Jobs ()->end (); idx++)
{
RandomSplitJobPtr j = dynamic_cast<RandomSplitJobPtr> (*idx);
if (j->RandomSplitsResults () != NULL)
{
KKStr splitNumStr = StrFormatInt (j->SplitNum (), "ZZZ0");
j->GetClassCounts (classAccs, knownCounts, predCounts, adjCounts, adjCountsStdError, predDelta, adjDelta);
totalCM.AddIn (*(j->RandomSplitsResults ()), log);
totalCmCount++;
KKStr accLine = "Acc By Class\t" + splitNumStr;
KKStr knownLine = "Known\t" + splitNumStr;
KKStr predLine = "Predicted\t" + splitNumStr;
KKStr adjLine = "Adjusted\t" + splitNumStr;
KKStr deltaPredLine = "Delta Pred\t" + splitNumStr;
KKStr deltaAdjLine = "Delta Adj\t" + splitNumStr;
double totalAcc = 0.0;
double totalDeltaPred = 0.0;
double totalDeltaAdj = 0.0;
for (x = 0; x < numClasses; x++)
{
accLine << "\t" << StrFormatDouble (classAccs [x], "zz0.00") << "%";
knownLine << "\t" << StrFormatDouble (knownCounts [x], "-Z,ZZZ,ZZ0.0");
predLine << "\t" << StrFormatDouble (predCounts [x], "-Z,ZZZ,ZZ0.0");
adjLine << "\t" << StrFormatDouble (adjCounts [x], "-Z,ZZZ,ZZ0.0");
deltaPredLine << "\t" << StrFormatDouble (predDelta [x], "-Z,ZZZ,ZZ0.0");
deltaAdjLine << "\t" << StrFormatDouble (adjDelta [x], "-Z,ZZZ,ZZ0.0");
totalAcc += classAccs [x];
totalDeltaPred += fabs (predDelta[x]);
totalDeltaAdj += fabs (adjDelta[x]);
}
accLine << "\t" << StrFormatDouble ((totalAcc / (double)classAccs.size ()), "ZZ0.00") << "%";
deltaPredLine << "\t" << StrFormatDouble ((totalDeltaPred / (double)predDelta.size ()), "ZZ0.00");
deltaAdjLine << "\t" << StrFormatDouble ((totalDeltaAdj / (double)adjDelta.size ()), "ZZ0.00");
accLines.push_back (accLine);
knownCountLines.push_back (knownLine);
predCountLines.push_back (predLine);
adjCountLines.push_back (adjLine);
deltaPredCountLines.push_back (deltaPredLine);
deltaAdjCountLines.push_back (deltaAdjLine);
}
}
double factor = 0.0;
if (totalCmCount > 0)
factor = 1.0 / (double)totalCmCount;
totalCM.FactorCounts (factor);
f << endl << endl
<< "Average Confusion Matrix" << endl
<< endl;
totalCM.PrintConfusionMatrixTabDelimited (f);
f << "" << "\t" << "" << "\t" << l1 << endl
<< "" << "\t" << "Split" << "\t" << l2 << endl
<< "Description" << "\t" << "Num" << "\t" << l3 << endl;
f << endl << endl;
for (x = 0; x < knownCountLines.size (); x++)
f << knownCountLines[x] << endl;
f << endl << endl;
for (x = 0; x < predCountLines.size (); x++)
f << predCountLines[x] << endl;
f << endl << endl;
for (x = 0; x < adjCountLines.size (); x++)
f << adjCountLines[x] << endl;
f << endl << endl;
for (x = 0; x < deltaPredCountLines.size (); x++)
f << deltaPredCountLines[x] << endl;
f << endl << endl;
for (x = 0; x < deltaAdjCountLines.size (); x++)
f << deltaAdjCountLines[x] << endl;
f << endl << endl;
for (x = 0; x < knownCountLines.size (); x++)
f << accLines[x] << endl;
VectorFloat avgAccuracies = totalCM.AccuracyByClass ();
f << "Avg-Accuracies";
for (x = 0; x < avgAccuracies.size (); x++)
f << "\t" << StrFormatDouble (avgAccuracies[x], "zz0.00") << "%";
f << "\t" << StrFormatDouble (totalCM.Accuracy (), "zz0.00") << "%";
f << endl;
f << endl << endl;
f.close ();
} /* GenerateFinalResultsReport */
void CmdLineExpander::BuildCmdLineParameters (const VectorKKStr& argv)
{
kkuint32 x = 0;
while (x < argv.size ())
{
KKStr s = argv[x];
x++;
KKStr sUpper = s.ToUpper();
if ((sUpper == "-L") || (sUpper == "-LOGFILE"))
{
if (x < argv.size ())
{
if (argv[x][(kkint16)0] != '-')
{
logFileName = argv[x];
if (!logFileName.Empty ())
log.AttachFile (logFileName);
x++;
}
}
if (logFileName.Empty ())
{
log.Level (-1) << std::endl << std::endl;
log.Level (-1) << applicationName << " - Invalid Log File Parameter (-L)." << endl;
log.Level (-1) << " Name of log file required." << endl;
log.Level (-1) << endl;
parmsGood = false;
}
}
else if (sUpper == "-CMDFILE")
{
KKStr cmdFileName = "";
if (x < argv.size ())
{
if (argv[x][(kkint16)0] != '-')
{
cmdFileName = argv[x];
x++;
}
}
if (cmdFileName.Empty ())
{
log.Level (-1) << endl << endl << endl
<< applicationName << " " << "BuildCmdLineParameters *** ERROR ***" << endl << endl
<< "-CMDFILE option did not define a file name." << endl
<< endl;
parmsGood = false;
}
else
{
if (FileInStack (cmdFileName, cmdFileStack))
{
log.Level (-1) << endl << endl << endl
<< applicationName << " BuildCmdLineParameters *** ERROR ***" << endl
<< endl
<< "-CMDFILE [" << cmdFileName << "] is being called recursively." << endl
<< endl;
parmsGood = false;
}
else
{
bool validFile = true;
cmdFileStack.push_back (cmdFileName);
VectorKKStr cmdFileParameters;
ExtractParametersFromFile (cmdFileName, cmdFileParameters, validFile);
BuildCmdLineParameters (cmdFileParameters);
cmdFileStack.pop_back ();
if (!validFile)
parmsGood = false;
}
}
}
else
{
expandedParameters.push_back (s);
}
}
} /* BuildCmdLineParameters */
void OurNeighbors::RandomReport (ImageFeaturesList& images)
{
double allClassesMeanNNDAnyClass = 0.0f;
double allClassesMeanStdDevAnyClass = 0.0f;
ClassSummaryList classSummaries (log);
MLClassList::iterator classIdx;
VectorKKStr zScoreSummaryLines;
for (classIdx = mlClasses->begin (); classIdx != mlClasses->end (); classIdx++)
{
MLClassPtr mlClass = *classIdx;
if (fromPlankton && (fromPlankton != mlClass))
continue;
double randomMeanNND = 0.0f;
double randomStdDevNND = 0.0f;
double realDataU2Stat = 0.0f;
double sampleMeanNND = 0.0f;
double sampleStdDevNND = 0.0f;
double sampleMaxDist = 0.0f;
double sampleMinDist = 0.0f;
ImageFeaturesListPtr imagesInClass = images.ExtractExamplesForAGivenClass (mlClass);
if (imagesInClass->QueueSize () > 0)
{
// We are going to make a list of images that has duplicate instances of 'ImageFeatures' objects
// This way when we Randomize the locations of each 'sfCentroidRow' and 'sfCentroidCol' we do not
// imapct on the original data.
ImageFeaturesListPtr imagesToRandomize = new ImageFeaturesList (*imagesInClass,
true // 'true means we want to own the data so new instances will be created.
);
LLoydsEntryListPtr lloydsEntries = DeriveAllLLoydsBins (*imagesToRandomize);
{
// We will now get mean and stdDev of nnd for this class
NeighborList neighbors (*imagesToRandomize, log);
neighbors.FindNearestNeighbors (neighborType, mlClass);
neighbors.CalcStatistics (sampleMeanNND, sampleStdDevNND, sampleMaxDist, sampleMinDist);
}
KKStr randomReportFileName;
if (reportFileName.Empty ())
randomReportFileName = "RandomDistanceReport";
else
randomReportFileName = osRemoveExtension (reportFileName) + "_Random";
randomReportFileName << "_" << mlClass->Name () << ".txt";
ofstream randomReport (randomReportFileName.Str ());
randomReport << "Random Distribution Report" << endl
<< endl;
randomReport << "Source Directory [" << sourceRootDirPath << "]" << endl;
randomReport << "Class [" << mlClass->Name () << "]" << endl;
RandomNND randomizeLocations (lastScanLine,
*imagesToRandomize,
numOfIterations,
numOfBuckets,
bucketSize,
randomReport,
log
);
randomizeLocations.GenerateReport ();
randomMeanNND = randomizeLocations.NND_Mean ();
randomStdDevNND = randomizeLocations.NND_StdDev ();
realDataU2Stat = randomizeLocations.RealDataU2Stat ();
//double sampleMeanNND = 0.0f;
//double sampleStdDevNND = 0.0f;
double z_Score = Z_Score (sampleMeanNND, randomMeanNND, randomStdDevNND, imagesToRandomize->QueueSize ());
randomReport << endl << endl << endl
<< "Z-Score" << endl
<< "=======" << endl
<< endl
<< "SampleMeanNND " << "\t" << sampleMeanNND << endl
<< "SampleStdDevNND " << "\t" << sampleStdDevNND << endl
<< "RandomMeanNND " << "\t" << randomMeanNND << endl
<< "RandomStdDevNND " << "\t" << randomStdDevNND << endl
<< "------- Z-Score " << "\t" << z_Score << endl
<< endl;
KKStr zScoreSummaryLine = mlClass->Name () + "\t" +
StrFormatDouble (sampleMeanNND, "###,##0.00") + "\t" +
StrFormatDouble (sampleStdDevNND, "###,##0.00") + "\t" +
StrFormatDouble (randomMeanNND, "###,##0.00") + "\t" +
StrFormatDouble (randomStdDevNND, "###,##0.00") + "\t" +
StrFormatDouble (z_Score, "###,##0.000");
zScoreSummaryLines.push_back (zScoreSummaryLine);
// The new instance on 'ClassSummary' that is aboiut to be created will take ownership
// of lloydsBins.
classSummaries.PushOnBack (new ClassSummary (mlClass, lloydsEntries, (float)realDataU2Stat, (float)z_Score));
delete imagesToRandomize; imagesToRandomize = NULL;
}
delete imagesInClass; imagesInClass = NULL;
}
if (!fromPlankton)
{
LLoydsEntryListPtr allClassesLLoydsEntries = DeriveAllLLoydsBins (images);
// Create a report for all classes
KKStr randomReportFileName;
if (reportFileName.Empty ())
randomReportFileName = "RandomDistanceReport_All.txt";
else
randomReportFileName = osRemoveExtension (reportFileName) + "_Random_All.txt";
ofstream randomReport (randomReportFileName.Str ());
randomReport << "Source Directory [" << sourceRootDirPath << "]" << endl;
randomReport << "Class [" << "All" << "]" << endl;
{
// Find the mean and stddev of Nearest Neighbor regardless of class.
NeighborList allClassesNeighbors (images, log);
allClassesNeighbors.FindNearestNeighbors (NeighborType::AnyPlankton, fromPlankton);
double allClassesMinDistAnyClass = 0.0f;
double allClassesMaxDistAnyClass = 0.0f;
allClassesNeighbors.CalcStatistics (allClassesMeanNNDAnyClass,
allClassesMeanStdDevAnyClass,
allClassesMinDistAnyClass,
allClassesMaxDistAnyClass
);
}
RandomNND randomizeLocations (lastScanLine,
images,
numOfIterations,
numOfBuckets,
bucketSize,
randomReport,
log
);
randomizeLocations.GenerateReport ();
// All classes Z-Score
double allClassesRandomMeanNND = randomizeLocations.NND_Mean ();
double allClassesRandomStdDevNND = randomizeLocations.NND_StdDev ();
double allClassesRealDataU2Stat = randomizeLocations.RealDataU2Stat ();
double z_Score = Z_Score (allClassesMeanNNDAnyClass, allClassesRandomMeanNND, allClassesRandomStdDevNND, images.QueueSize ());
KKStr zScoreSummaryLine = KKStr ("All-Classes") + "\t" +
StrFormatDouble (allClassesMeanNNDAnyClass, "###,##0.00") + "\t" +
StrFormatDouble (allClassesMeanStdDevAnyClass, "###,##0.00") + "\t" +
StrFormatDouble (allClassesRandomMeanNND, "###,##0.00") + "\t" +
StrFormatDouble (allClassesRandomStdDevNND, "###,##0.00") + "\t" +
StrFormatDouble (z_Score, "###,##0.00");
zScoreSummaryLines.push_back (zScoreSummaryLine);
randomReport << endl << endl << endl
<< "Z-Score" << endl
<< "=======" << endl
<< endl
<< "SampleMeanNND " << "\t" << allClassesMeanNNDAnyClass << endl
<< "SampleStdDevNND " << "\t" << allClassesMeanStdDevAnyClass << endl
<< "RandomMeanNND " << "\t" << allClassesRandomMeanNND << endl
<< "RandomStdDevNND " << "\t" << allClassesRandomStdDevNND << endl
<< "------- Z-Score " << "\t" << z_Score << endl
<< endl;
classSummaries.PushOnBack (new ClassSummary (MLClass::CreateNewMLClass (KKStr ("AllClasses")),
allClassesLLoydsEntries,
(float)allClassesRealDataU2Stat,
(float)z_Score
)
);
}
{
// Z-Score Summary Report
KKB::kkuint32 x;
*report << std::endl << std::endl
<< "Z-Score Summary By Class" << std::endl
<< std::endl
<< "ClassName" << "\t" << "SampleMean" << "\t" << "SampleStdDev" << "\t" << "RandomMean" << "\t" << "RandomStdDev" << "\t" << "Z-Score" << std::endl
<< "=========" << "\t" << "==========" << "\t" << "============" << "\t" << "==========" << "\t" << "============" << "\t" << "=======" << std::endl;
for (x = 0; x < zScoreSummaryLines.size (); x++)
*report << zScoreSummaryLines[x] << std::endl;
}
*report << endl << endl << endl;
classSummaries.SummaryReport (*report);
*report << endl << endl << endl;
classSummaries.SpatialOverlapReport (*report);
classSummaries.SaveLLoydsBinsData (lloydsBinsFileName, sourceRootDirPath, lastScanLine, baseLLoydsBinSize);
} /* RandomReport */
void ClassificationBiasMatrix::ReadSimpleConfusionMatrix (istream& sr,
MLClassListPtr fileClasses
)
{
// 'classes' - The class order that the owner of this object is expecting.
// 'fileClasses' - The order that the classes are stored in the text file.
if ((classes == NULL) || (fileClasses == NULL))
{
KKStr errMsg = "ReadSimpleConfusionMatrix ***ERROR*** The 'Classes' line was never provided.";
runLog.Level (-1) << errMsg << endl;
valid = false;
throw KKException (errMsg);
}
kkint32 classesColIdx = 0;
char buff[10240];
KKStr l;
while (!sr.eof ())
{
sr.getline (buff, sizeof (buff));
l = buff;
l.TrimLeft ();
l.TrimRight ();
if (l.CompareIgnoreCase ("</SimpleConfusionMatrix>") == 0)
break;
KKStr lineName = l.ExtractToken2 ("\t");
if (lineName.CompareIgnoreCase ("DataRow") == 0)
{
if (fileClasses == NULL)
{
KKStr errMsg = "ReadSimpleConfusionMatrix ***ERROR*** 'Classes' was not provided before 'DataRow'.";
runLog.Level (-1) << errMsg << endl;
valid = false;
throw KKException (errMsg);
}
KKStr className = l.ExtractToken2 ("\t");
KKStr data = l.ExtractToken2 ("\t");
MLClassPtr pc = MLClass::CreateNewMLClass (className);
kkint32 classesIdx = classes->PtrToIdx (pc);
kkint32 fileClassesIdx = fileClasses->PtrToIdx (pc);
if (classesIdx < 0)
{
KKStr errMsg = "ReadSimpleConfusionMatrix ***ERROR*** DataRow specifies class[" + className + "] which is not defined by caller";
runLog.Level (-1) << errMsg << endl;
valid = false;
throw KKException (errMsg);
}
if (fileClassesIdx < 0)
{
KKStr errMsg = "ReadSimpleConfusionMatrix ***ERROR*** DataRow specifies class[" + className + "] was not defined in 'Classes' line.";
runLog.Level (-1) << errMsg << endl;
valid = false;
throw KKException (errMsg);
}
kkint32 classesRowIdx = classesIdx;
VectorKKStr dataFields = data.Split (',');
if (dataFields.size () != (kkuint32)numClasses)
{
KKStr errMsg = "ReadSimpleConfusionMatrix ***ERROR*** DataRow Class[" + className + "] number[" + StrFormatInt ((kkint32)dataFields.size (), "ZZZ0") + "] of values provided does not match number of Classes.";
runLog.Level (-1) << errMsg << endl;
valid = false;
throw KKException (errMsg);
}
for (kkint32 c = 0; c < numClasses; c++)
{
pc = fileClasses->IdxToPtr (c);
classesColIdx = classes->PtrToIdx (pc);
VectorKKStr parts = dataFields[c].Split (':');
if (parts.size () > 1)
{
(*counts) [classesRowIdx][classesColIdx] = parts[0].ToDouble ();
(*probabilities)[classesRowIdx][classesColIdx] = parts[1].ToDouble ();
}
}
}
}
} /* ReadSimpleConfusionMatrix */