public static DataTableTypeExtended <classificationReportExpanded> MakeOverviewTable(this classificationReportCollection reportCollection, classificationReportDataComplexContext context, String name = "", String description = "")
{
DataTableTypeExtended <classificationReportExpanded> table = new DataTableTypeExtended <classificationReportExpanded>("overview_" + reportCollection.name, "Aggregate report for experiments ran [" + DateTime.Now.ToShortDateString() + "]");
if (name != "")
{
table.SetAdditionalInfoEntry("Group name", name);
}
if (description != "")
{
table.SetAdditionalInfoEntry("Group desc", description);
}
table.SetDescription(reportCollection.description);
table.SetAdditionalInfoEntry("Path", reportCollection.rootPath, "Path of the collection");
table.SetAdditionalInfoEntry("Subcollections", reportCollection.Children.Count, "Number of sub collections");
foreach (var rep in reportCollection)
{
table.AddRow(rep);
}
context.overview_tables.Add(table);
return(table);
//table.GetReportAndSave(folder, imbACE.Core.appManager.AppInfo);
}
/// <summary>
/// Gets the data table.
/// </summary>
/// <param name="_name">The name.</param>
/// <param name="_description">The description.</param>
/// <returns></returns>
public DataTable GetDataTable(String _name, String _description)
{
DataTableTypeExtended <HtmlTagCounterResult> output = new DataTableTypeExtended <HtmlTagCounterResult>(_name, _description);
var results = GetResultList();
results.ForEach(x => output.AddRow(x));
output.SetAdditionalInfoEntry("Unknown dist. tags", DistinctUnknownTags.Count, "Number of distinct unknown tags");
output.SetAdditionalInfoEntry("Distinct tags", DistinctTags.Count, "Number of known distinct tags");
output.SetAdditionalInfoEntry("Unknown tags", UnknownTags.Count(), "Number of unknown distinct tags");
output.AddExtra("Distinct tags found: [" + DistinctTags.toCsvInLine() + "]");
output.AddExtra("Unknown tags found: [" + UnknownTags.toCsvInLine() + "]");
return(output);
}
/// <summary>
/// Gets the data table, with all actions
/// </summary>
/// <returns></returns>
public DataTable GetDataTable()
{
DataTableTypeExtended <cloudMatrixReductionReportEntry> output = new DataTableTypeExtended <cloudMatrixReductionReportEntry>(name, "Actions done by cloud matrix [" + name + "]");
rangeFinderForDataTable ranger = new rangeFinderForDataTable(output, nameof(cloudMatrixReductionReportEntry.Hash));
foreach (var entry in entries)
{
output.AddRow(entry);
}
output.SetAdditionalInfoEntry(nameof(TotalReduction).imbTitleCamelOperation(true), TotalReduction);
output.SetAdditionalInfoEntry(nameof(CFFunctionReduction).imbTitleCamelOperation(true), CFFunctionReduction);
output.SetAdditionalInfoEntry(nameof(LPFilterReduction).imbTitleCamelOperation(true), LPFilterReduction);
output.SetAdditionalInfoEntry(nameof(LPFRemovals).imbTitleCamelOperation(true), LPFRemovals);
output.SetAdditionalInfoEntry(nameof(MWRemovals).imbTitleCamelOperation(true), MWRemovals);
return(output);
}
public DataTable GetDataTable(String name)
{
DataTableTypeExtended <ContentMetrics> output = new DataTableTypeExtended <ContentMetrics>(name);
foreach (var c in ClassMetrics)
{
output.AddRow(c);
}
output.AddRow(sumMetrics);
output.AddRow(avgMetrics);
output.SetAdditionalInfoEntry("Terms", terms.Count, "Number of distinct terms in the dataset");
output.SetAdditionalInfoEntry("MaxTF", terms.GetMaxFrequency(), "Max. frequency in the corpus");
output.SetAdditionalInfoEntry("SumTF", terms.GetSumFrequency(), "Sum of frequencies in the corpus");
output.SetAdditionalInfoEntry("Stems", DictinctStems.Count(), "Number of distinct stems");
output.SetAdditionalInfoEntry("Tokens", DictinctTokens.Count(), "Number of distinct tokens");
return(output);
}
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);
}
/// <summary>
/// Generates the final reports and read me files
/// </summary>
public void CloseExperiment(ILogBuilder logger, long startOfLog)
{
if (!testSummaries.Any())
{
logger.log("No experiment procedures performes");
return;
}
DataTableTypeExtended <classificationReport> summaryTable = new DataTableTypeExtended <classificationReport>("Test results", "k-fold cross valudation results");
classificationReport sumRow = new classificationReport(runName);
sumRow.Comment = runName + ", " + description;
// classificationEvalMetricSet metric = new classificationEvalMetricSet("Total", truthTable.labels_without_unknown);
foreach (classificationReport s in testSummaries)
{
summaryTable.AddRow(s);
//metric = metric + s;
if (sumRow.Classifier.isNullOrEmpty())
{
sumRow.Classifier = s.Classifier;
}
sumRow.AddValues(s);
}
sumRow.DivideValues(testSummaries.Count);
sumRow.SetReportDataFields(crossValidation, this);
summaryTable.SetDescription(description);
summaryTable.SetAdditionalInfoEntry("RunName", runName);
summaryTable.SetAdditionalInfoEntry("Description", description);
summaryTable.SetAdditionalInfoEntry("Averaging", averagingMethod.ToString());
summaryTable.AddRow(sumRow);
summaryTable.GetReportAndSave(notes.folder, signature);
finalReport = sumRow;
//sumRow.ReportToLog(logger);
sumRow.ReportToLog(notes);
objectSerialization.saveObjectToXML(sumRow, notes.folder.pathFor("results.xml", imbSCI.Data.enums.getWritableFileMode.overwrite, "Experiment results", true));
logger.log("Experiment completed");
notes.SaveNote("note");
String logPrintout = logger.GetContent(startOfLog);
String p = notes.folder.pathFor("log.txt", imbSCI.Data.enums.getWritableFileMode.overwrite, "Log printout during experiment execution");
File.WriteAllText(p, logPrintout);
experimentRootFolder.generateReadmeFiles(signature);
}