/// <summary>
/// Gets the report table on one collection
/// </summary>
/// <returns></returns>
public DataTable GetReportTable(Boolean isTrainingCollection = false, Boolean isSingleCategoryReport = true)
{
DataTable output = this.BuildShema(isSingleCategoryReport, isTrainingCollection);
this.SetAdditionalInfo(output, isSingleCategoryReport, isTrainingCollection);
foreach (var setCase in this)
{
this.BuildRow(setCase, output, isTrainingCollection);
}
ranger = new rangeFinderForDataTable(output, "name");
ranger.AddRangeRows(setClass.name, output, true, imbSCI.Core.math.aggregation.dataPointAggregationType.avg | imbSCI.Core.math.aggregation.dataPointAggregationType.stdev);
return(output);
}
protected void runModel(experimentExecutionContext context, IWebFVExtractor model)
{
imbSCI.Core.screenOutputControl.logToConsoleControl.setAsOutput(context.logger, model.name);
Int32 crashRetries = context.tools.operation.doRebootFVEOnCrashRetryLimit;
aceDictionarySet <IDocumentSetClass, DocumentSetCaseCollection> casesByClasses = new aceDictionarySet <IDocumentSetClass, DocumentSetCaseCollection>();
DSCCReportSet kFoldReport = new DSCCReportSet(model);
var valCol = context.validationCollections[model.name];
List <DocumentSetCaseCollectionSet> modelCaseResults = new List <DocumentSetCaseCollectionSet>();
crashRetries = context.tools.operation.doRebootFVEOnCrashRetryLimit;
while (crashRetries > 0)
{
try
{
experimentNotes modelNotes = new experimentNotes(valCol.folder, "Fold-level experiment settings description notes");
modelNotes.AppendLine("# Notes on Feature Vector Extractor: " + model.name);
var nts = model.DescribeSelf();
nts.ForEach(x => modelNotes.AppendLine(x));
context.logger.log("Executing k-fold cases with model [" + model.name + "]");
valCol.DescribeSampleDistribution(modelNotes);
context.mainReport.valColVsModelVsSampleHash.Add("[" + model.name + "]".toWidthExact(20) + " [sample distribution hash: " + valCol.SampleDistributionHash + "]");
modelNotes.SaveNote();
ParallelOptions ops = new ParallelOptions();
ops.MaxDegreeOfParallelism = context.tools.operation.ParallelThreads;
Parallel.ForEach <kFoldValidationCase>(valCol.GetCases(), ops, valCase =>
{
model.DoFVEAndTraining(valCase, context.tools, context.logger); // <--------------------------------------------------------------------------------------- BUILDING FVE
DocumentSetCaseCollectionSet results = model.DoClassification(valCase, context.tools, context.logger);
if (!results.Any())
{
throw new aceScienceException("DoClassification for [" + model.name + "] returned no results!", null, model, "DoClassification " + model.name + " failed!", context);
}
foreach (var pair in results)
{
DocumentSetCaseCollection cls = pair.Value;
casesByClasses.Add(cls.setClass, cls);
}
valCase.evaluationResults = results;
if (context.tools.DoResultReporting)
{
context.logger.log("producing reports on k-Fold case [" + valCase.name + "]");
DSCCReports r = results.GetReports();
var sumMeans = r.GetAverageTable(context); //.GetReportAndSave(valCase.folder, appManager.AppInfo, "CrossValidation_" + valCase.name);
sumMeans.SetDescription("FVE report, aggregated for all categories - for fold [" + valCase.name + "]");
sumMeans.GetReportAndSave(valCase.folder, appManager.AppInfo, "CrossValidation_" + valCase.name, true, context.tools.operation.doReportsInParalell);
var fveAndCase = r.GetFullValidationTable(context);
fveAndCase.SetDescription("Per-category aggregate statistics, for each classifier, within fold [" + valCase.name + "], used for macro-averaging");
fveAndCase.GetReportAndSave(valCase.folder, appManager.AppInfo, "CrossValidation_extrainfo_" + valCase.name, true, context.tools.operation.doReportsInParalell);
var fullCaseReport = results.GetReportOnAllCases();
fullCaseReport.GetReportAndSave(valCase.folder, appManager.AppInfo, "FullReport_" + valCase.name, true, context.tools.operation.doReportsInParalell);
kFoldReport.Add(valCase, r);
}
context.logger.log("k-Fold case [" + valCase.name + "] completed");
context.notes.log("- - Experiment sequence for [" + valCase.name + "] fold completed");
if (context.tools.operation.doSaveKnowledgeForClasses)
{
valCase.knowledgeLibrary.SaveKnowledgeInstancesForClasses(valCase, context.logger);
}
});
foreach (var fold in valCol.GetCases()) // Parallel.ForEach<kFoldValidationCase>(valCol.GetCases(), ops, valCase =>
{
modelCaseResults.Add(fold.evaluationResults);
}
crashRetries = 0;
}
catch (Exception ex)
{
crashRetries--;
context.errorNotes.LogException("FVE Model crashed -- retries left [" + crashRetries + "] --- ", ex, model.name);
context.logger.log(":::: REPEATING the model [" + model.name + "] ::: CRASHED [" + ex.Message + "] ::: RETRIES [" + crashRetries + "]");
imbACE.Services.terminal.aceTerminalInput.doBeepViaConsole(1200, 1000, 1);
imbACE.Services.terminal.aceTerminalInput.doBeepViaConsole(2400, 1000, 1);
imbSCI.Core.screenOutputControl.logToConsoleControl.setAsOutput(context.logger, "RETRIES[" + crashRetries + "]");
}
}
imbSCI.Core.screenOutputControl.logToConsoleControl.setAsOutput(context.logger, "Reporting");
valCol.knowledgeLibrary.SaveCaseKnowledgeInstances(context.logger);
// DocumentSetCaseCollection second = null;
if (modelCaseResults.Any())
{
featureExtractionMetrics modelMetrics = new featureExtractionMetrics(model.name, "All");
DataTableTypeExtended <featureExtractionMetrics> modelVsCategoryMetrics = new DataTableTypeExtended <featureExtractionMetrics>(model.name, "Model metrics per category");
// <-------------------------------------- CATEGORIES REPORT ----------------------------------------------
DataTable allTable = modelCaseResults.First()[0].GetReportTable(false, false).GetClonedShema <DataTable>();; //valCol.GetCases().First().evaluationResults[0].GetReportTable(false, false);
rangeFinderForDataTable ranger = new rangeFinderForDataTable(allTable, "name");
ranger.columnsToSignIn.Add("Case");
foreach (KeyValuePair <IDocumentSetClass, aceConcurrentBag <DocumentSetCaseCollection> > pair in casesByClasses)
{
DocumentSetCaseCollection first = null;
DataTable repTable = null;
ranger.prepareForNextAggregationBlock(allTable, "name");
foreach (DocumentSetCaseCollection cn in pair.Value)
{
foreach (var cni in cn)
{
if (cni != null)
{
cn.BuildRow(cni, allTable, false);
}
}
}
ranger.AddRangeRows(pair.Key.name, allTable, true, imbSCI.Core.math.aggregation.dataPointAggregationType.avg | imbSCI.Core.math.aggregation.dataPointAggregationType.stdev);
var categoryMetrics = new featureExtractionMetrics(model.name, pair.Key.name);
categoryMetrics.SetValues(ranger);
modelVsCategoryMetrics.AddRow(categoryMetrics);
modelMetrics.AddValues(categoryMetrics);
categoryMetrics.saveObjectToXML(valCol.folder.pathFor(model.name + "_" + categoryMetrics.Name + ".xml", imbSCI.Data.enums.getWritableFileMode.overwrite, "FV and Category sample metrics, serialized object"));
//context.notes.log("- - Creating report for category [" + pair.Key.name + "] completed");
//repTable.GetReportAndSave(valCol.folder, appManager.AppInfo, model.name + "_category_" + pair.Key.name);
}
modelMetrics.DivideValues(casesByClasses.Count);
modelMetrics.saveObjectToXML(valCol.folder.pathFor(model.name + "_metrics.xml", imbSCI.Data.enums.getWritableFileMode.overwrite, "Cross-categories macroaveraged metrics of the FVE model [" + model.name + "]"));
modelVsCategoryMetrics.AddRow(modelMetrics);
modelVsCategoryMetrics.GetRowMetaSet().SetStyleForRowsWithValue <String>(DataRowInReportTypeEnum.dataHighlightA, "Name", modelMetrics.Name);
modelVsCategoryMetrics.GetReportAndSave(valCol.folder, appManager.AppInfo, model.name + "_metrics", true, true);
context.mainReport.AddModelMetrics(modelMetrics);
context.notes.log("- Creating report for all categories [" + model.name + "] ");
allTable.GetReportAndSave(valCol.folder, appManager.AppInfo, model.name + "_categories", true, context.tools.operation.doReportsInParalell);
}
kFoldReport.MakeReports(context, valCol.folder);
context.mainReport.AddBestPerformer(kFoldReport.GetTopClassifierReport(), kFoldReport.meanClassifierReport, model);
// <---------------- creation of complete report
context.notes.log("- Experiment sequence with Feature Vector Extractor [" + model.name + "] completed");
context.notes.SaveNote();
// <------------- END OF THE MODEL -------------------------------------------------------------------------------------------------
}
public void MakeReports(experimentExecutionContext context, folderNode folder)
{
meanClassifierReport = new DocumentSetCaseCollectionReport(extractor.name);
aceDictionary2D <IWebPostClassifier, kFoldValidationCase, DocumentSetCaseCollectionReport> tempStructure = new aceDictionary2D <IWebPostClassifier, kFoldValidationCase, DocumentSetCaseCollectionReport>();
DSCCReports firstCase = null;
List <IWebPostClassifier> classifiers = new List <IWebPostClassifier>();
foreach (var kFoldCasePair in this)
{
if (firstCase == null)
{
firstCase = kFoldCasePair.Value;
}
foreach (var pair in kFoldCasePair.Value.avgReports)
{
tempStructure[pair.Key, kFoldCasePair.Key] = pair.Value;
if (!classifiers.Contains(pair.Key))
{
classifiers.Add(pair.Key);
}
}
}
// DataSet dataSet = new DataSet(context.setup.name);
// <---------- CREATING AVERAGE TABLE -----------------------------------------------------
var tpAvgMacro = new DataTableTypeExtended <DocumentSetCaseCollectionReport>(context.setup.name + " summary", "Cross k-fold averages measures, fold-level measures are computed by macro-average method");
var tpAvgMicro = new DataTableTypeExtended <DocumentSetCaseCollectionReport>(context.setup.name + " summary", "Cross k-fold averages measures, fold-level measures are computed by micro-average method");
List <DocumentSetCaseCollectionReport> macroaverages = new List <DocumentSetCaseCollectionReport>();
DataTableTypeExtended <DocumentSetCaseCollectionReport> EMperKFolds = new DataTableTypeExtended <DocumentSetCaseCollectionReport>(extractor.name + "_allReports");
foreach (IWebPostClassifier classifier in classifiers)
{
// < ---- report on each classifier
context.logger.log("-- producing report about [" + classifier.name + "]");
//objectTable<DocumentSetCaseCollectionReport> tp = new objectTable<DocumentSetCaseCollectionReport>(nameof(DocumentSetCaseCollectionReport.Name), classifier + "_sum");
DocumentSetCaseCollectionReport avg = new DocumentSetCaseCollectionReport(classifier.name + " macro-averaging, k-fold avg. ");
DocumentSetCaseCollectionReport rep_eval = new DocumentSetCaseCollectionReport(classifier.name + " micro-averaging, k-fold avg.");
rep_eval.Classifier = classifier.name;
classificationEvalMetricSet metrics = new classificationEvalMetricSet();
classificationEval eval = new classificationEval();
//eval = metrics[classifier.name];
Int32 c = 0;
foreach (KeyValuePair <kFoldValidationCase, DSCCReports> kFoldCasePair in this)
{
DocumentSetCaseCollectionReport rep = kFoldCasePair.Value.avgReports[classifier];
kFoldValidationCase vCase = kFoldCasePair.Key;
classificationEvalMetricSet met = rep.GetSetMetrics();
if (met != null)
{
foreach (IDocumentSetClass cl in context.classes.GetClasses())
{
eval = eval + met[cl.name];
}
}
rep.Name = classifier.name + "_" + vCase.name;
avg.AddValues(rep);
EMperKFolds.AddRow(rep);
c++;
}
rep_eval.AddValues(metrics, classificationMetricComputation.microAveraging);
avg.Classifier = classifier.name;
avg.DivideValues(c);
// <<< detecting the best performed classifier in all evaluation folds
if (avg.F1measure > highestF1Value)
{
highestF1Value = avg.F1measure;
topClassifierReport = avg;
}
meanClassifierReport.AddValues(avg);
// -----------------
EMperKFolds.AddRow(avg);
tpAvgMacro.AddRow(avg);
macroaverages.Add(avg);
if (DOMAKE_MICROaverage)
{
tpAvgMicro.AddRow(rep_eval);
}
// tp.Add(rep_eval);
if (context.tools.operation.DoMakeReportForEachClassifier)
{
DataTable cTable = EMperKFolds;
cTable.SetTitle($"{classifier.name} report");
cTable.SetDescription("Summary " + context.setup.validationSetup.k + "-fold validation report for [" + classifier.name + "]");
cTable.SetAdditionalInfoEntry("FV Extractor", extractor.name);
cTable.SetAdditionalInfoEntry("Classifier", classifier.name);
cTable.SetAdditionalInfoEntry("Class name", classifier.GetType().Name);
cTable.SetAdditionalInfoEntry("Correct", rep_eval.Correct);
cTable.SetAdditionalInfoEntry("Wrong", rep_eval.Wrong);
//cTable.SetAdditionalInfoEntry("Precision", rep_eval.Precision);
//cTable.SetAdditionalInfoEntry("Recall", rep_eval.Recall);
//cTable.SetAdditionalInfoEntry("F1", rep_eval.F1measure);
cTable.SetAdditionalInfoEntry("True Positives", metrics[classifier.name].truePositives);
cTable.SetAdditionalInfoEntry("False Negatives", metrics[classifier.name].falseNegatives);
cTable.SetAdditionalInfoEntry("False Positives", metrics[classifier.name].falsePositives);
cTable.AddExtra("Classifier: " + classifier.name + " [" + classifier.GetType().Name + "]");
var info = classifier.DescribeSelf();
info.ForEach(x => cTable.AddExtra(x));
cTable.AddExtra("-----------------------------------------------------------------------");
cTable.AddExtra("Precision, Recall and F1 measures expressed in this table are computed by macroaveraging shema");
// output.CopyRowsFrom(cTable);
cTable.GetReportAndSave(folder, appManager.AppInfo, extractor.name + "_classifier_" + classifier.name);
// dataSet.AddTable(cTable);
}
}
rangeFinderForDataTable rangerMacro = new rangeFinderForDataTable(tpAvgMacro, "Name");
meanClassifierReport.DivideValues(classifiers.Count);
if (macroaverages.Count > 0)
{
Double maxF1 = macroaverages.Max(x => x.F1measure);
Double minF1 = macroaverages.Min(x => x.F1measure);
List <String> minCaseNames = macroaverages.Where(x => x.F1measure == minF1).Select(x => x.Name).ToList();
List <String> maxCaseNames = macroaverages.Where(x => x.F1measure == maxF1).Select(x => x.Name).ToList();
var style = EMperKFolds.GetRowMetaSet().SetStyleForRowsWithValue <String>(DataRowInReportTypeEnum.dataHighlightA, nameof(DocumentSetCaseCollectionReport.Name), maxCaseNames);
EMperKFolds.GetRowMetaSet().AddUnit(style);
// style = tpAvgMacro.GetRowMetaSet().SetStyleForRowsWithValue<String>(DataRowInReportTypeEnum.dataHighlightC, nameof(DocumentSetCaseCollectionReport.Name), minCaseNames);
tpAvgMacro.SetAdditionalInfoEntry("FV Extractor", extractor.name);
if (DOMAKE_MICROaverage)
{
tpAvgMicro.SetAdditionalInfoEntry("FV Extractor", extractor.name);
}
List <String> averageNames = macroaverages.Select(x => x.Name).ToList();
var avg_style = EMperKFolds.GetRowMetaSet().SetStyleForRowsWithValue <String>(DataRowInReportTypeEnum.dataHighlightC, nameof(DocumentSetCaseCollectionReport.Name), averageNames);
foreach (var x in averageNames)
{
avg_style.AddMatch(x);
}
}
// ::: ------------------------------------------------------------------------------------------------- ::: --------------------------------------------------------------------- ::: //
tpAvgMacro.SetTitle($"{extractor.name} - macroaverage report");
if (DOMAKE_MICROaverage)
{
tpAvgMicro.SetTitle($"{extractor.name} - microaverage report");
}
tpAvgMacro.AddExtra("Complete report on " + context.setup.validationSetup.k + "-fold validation FVE [" + extractor.name + "]");
tpAvgMacro.AddExtra("Fold-level P, R and F1 measures are computed by macroaveraging method, values here are cross k-fold means.");
if (DOMAKE_MICROaverage)
{
tpAvgMicro.AddExtra("Complete " + context.setup.validationSetup.k + "-fold validation report for FVE [" + extractor.name + "]");
}
if (DOMAKE_MICROaverage)
{
tpAvgMicro.AddExtra("Fold-level P, R and F1 measures are computed by microaveraging method, values here are cross k-fold means.");
}
context.AddExperimentInfo(tpAvgMacro);
if (DOMAKE_MICROaverage)
{
context.AddExperimentInfo(tpAvgMicro);
}
tpAvgMacro.AddExtra(extractor.description);
if (extractor is semanticFVExtractor)
{
semanticFVExtractor semExtractor = (semanticFVExtractor)extractor;
semExtractor.termTableConstructor.DescribeSelf().ForEach(x => tpAvgMacro.AddExtra(x));
semExtractor.CloudConstructor.DescribeSelf().ForEach(x => tpAvgMacro.AddExtra(x));
semExtractor.termTableConstructor.DescribeSelf().ForEach(x => tpAvgMicro.AddExtra(x));
semExtractor.CloudConstructor.DescribeSelf().ForEach(x => tpAvgMicro.AddExtra(x));
}
context.logger.log("-- producing summary reports on [" + extractor.name + "]");
rangerMacro.AddRangeRows("Macroaverage ", tpAvgMacro, true,
imbSCI.Core.math.aggregation.dataPointAggregationType.min | imbSCI.Core.math.aggregation.dataPointAggregationType.max
| imbSCI.Core.math.aggregation.dataPointAggregationType.avg
| imbSCI.Core.math.aggregation.dataPointAggregationType.stdev);
tpAvgMacro.GetReportAndSave(folder, appManager.AppInfo, extractor.name + "_macroaverage_report", true, true);
EMperKFolds.AddExtra("The table shows average measures for each fold --- rows marked with colored background show averages for all folds, per classifier.");
EMperKFolds.GetReportAndSave(folder, appManager.AppInfo, extractor.name + "_allFolds", true, true);
if (DOMAKE_MICROaverage)
{
tpAvgMicro.GetReportAndSave(folder, appManager.AppInfo, extractor.name + "_microaverage_report", true, true);
}
//dataSet.GetReportVersion().serializeDataSet(extractor.name + "_classifiers_MultiSheetSummary", folder, imbSCI.Data.enums.reporting.dataTableExportEnum.excel, appManager.AppInfo);
}