public void UnitTestMethod()
{
// Example 1: Loading BibTex file
BibTexDataFile bib_1 = new BibTexDataFile("Resources\\test\\S0306457309000259.bib");
// Example 2: Loading BibTex file
String path = folderResources.findFile("S0306457309000259.bib", SearchOption.AllDirectories);
// initializes bibtex data file object
BibTexDataFile bib = new BibTexDataFile();
// loads .bib or .bibtex file from path specified
bib.Load(path, log);
// converts loaded BibTex entries into DataTable, with all columns discovered in the entries
DataTable dt = bib.ConvertToDataTable();
// saves DataTable to Excel file, without adding Legend spreadsheet
var finalPath = dt.serializeDataTable(Data.enums.reporting.dataTableExportEnum.excel, bib.name, folderResults, notation);
// creates extended version of Excel file, with additional spreadsheet for Legend and other meta information
var reportDataTable_ref = dt.GetReportAndSave(folderResults, notation);
// Example 3: Short way
// High-level method, creates extended version of Excel file, with additional spreadsheet for Legend and other meta information
var reportDataTable = BibTexTools.ExportToExcel(path, notation, log);
// Example 4: Working with BibTexEntryModel
// Creation of BibTex entry from code
BibTexEntryModel entry = new BibTexEntryModel()
{
EntryKey = "SOKOLOVA2009427",
EntryType = "article",
journal = "Information Processing & Management",
title = "A systematic analysis of performance measures for classification tasks",
keywords = "Performance evaluation, Machine Learning, Text classification",
year = 2005,
number = 2,
issn = "0000-0000",
@abstract = "Abs",
doi = "https://doi.org/10.1016/j.ipm.2009.03.002",
url = "http://www.sciencedirect.com/science/article/pii/S0306457309000259"
};
// Creation of data table collection
DataTableTypeExtended <BibTexEntryModel> bibTable = new DataTableTypeExtended <BibTexEntryModel>("RuntimeCreatedBibTex", "BibTex table, created in Run Time");
// creates extended version of Excel file, with additional spreadsheet for Legend and other meta information
var codeDataTable_ref = bibTable.GetReportAndSave(folderResults, notation);
}
public static void MakeReport(classificationReportCollection reportCollection, classificationReportCollectionSettings settings, aceAuthorNotation appInfo, ILogBuilder log, classificationReportStyleDefinition style, classificationReportDataComplexContext context)
{
DataTableTypeExtended <classificationReportExpanded> table = reportCollection.MakeOverviewTable(context, reportCollection.name, reportCollection.description);
table.SetTitle(reportCollection.name);
var statDataTable = table.GetReportAndSave(reportCollection.rootFolder, appInfo);
log.log("Report [" + table.TableName + "] created at " + statDataTable.lastFilePath);
// context.cumulative_tables.Add(table);
var layers = reportCollection.GetSpaceLayers(style);
foreach (var pair in layers)
{
var reportSpace = classificationReportSpace.BuildReportSpace(pair.Value, reportCollection.datasetName, settings.SELECT_REPORT_NAME_PARTS, style, pair.Key);
if (!context.report_spaces.ContainsKey(reportSpace.name))
{
context.report_spaces.Add(reportSpace.name, new List <classificationReportSpace>());
context.comparative_tables.Add(reportSpace.name, new List <DataTable>());
context.comparative_narrow_tables.Add(reportSpace.name, new List <DataTable>());
}
context.report_spaces[reportSpace.name].Add(reportSpace);
System.Data.DataTable comparative_table = reportSpace.ConstructTable("comparative_" + reportCollection.name + "_" + reportSpace.name, reportCollection.description);
context.comparative_tables[reportSpace.name].Add(comparative_table);
comparative_table.AddExtra("Group path: " + reportCollection.rootFolder.path);
comparative_table.GetReportAndSave(reportCollection.rootFolder, appInfo);
System.Data.DataTable comparative_table_small = reportSpace.ConstructTable("comparative_" + reportCollection.name + "_" + reportSpace.name + "_small", reportCollection.description, classificationReportTableMode.onlyBasic);
context.comparative_narrow_tables[reportSpace.name].Add(comparative_table_small);
var styleFS = style.CloneViaXML();
styleFS.valueToUse = classificationReportStyleDefinition.GetFS(); //new reportExpandedDataPair(classificationReportStyleDefinition.VALUE_FS, "Selected Features", "Number of features actually selected");
reportSpace = classificationReportSpace.BuildReportSpace(pair.Value, reportCollection.datasetName, settings.SELECT_REPORT_NAME_PARTS, styleFS, pair.Key);
reportSpace.ConstructTable("featureSelected_" + reportCollection.name + "_" + reportSpace.name, reportCollection.description).GetReportAndSave(reportCollection.rootFolder, appInfo);
}
// return comparative_table;
}
/// <summary>
/// Creates generic DataTable collection, adds 5 rows and generates Excel and CSV file
/// </summary>
public void ExampleOne_DataTableDataAnnotation()
{
// creating typed DataTable collection, holding DataEntryTest class
DataTableTypeExtended<DataEntryTest> dataTableTypeExtended = new DataTableTypeExtended<DataEntryTest>(nameof(DataEntryTest), nameof(ExampleOne_DataTableDataAnnotation));
// adding five rows
dataTableTypeExtended.AddRow(new DataEntryTest());
dataTableTypeExtended.AddRow(new DataEntryTest());
dataTableTypeExtended.AddRow(new DataEntryTest());
dataTableTypeExtended.AddRow(new DataEntryTest());
dataTableTypeExtended.AddRow(new DataEntryTest());
// Generating and exporting report into Excel file
DataTableForStatistics report = dataTableTypeExtended.GetReportAndSave(folderResults);
}
/// <summary>Creation of BibTex entry from code, and generation of Excel table</summary>
/** <example><para>Creation of BibTex entry from code, and generation of Excel table</para>
* <code>
* // --- We create the entry and write its source code to the disk
*
* // Creation of BibTex entry from code
* BibTexEntryModel entry = new BibTexEntryModel()
* {
* EntryKey = "SOKOLOVA2009427",
* EntryType = "article",
* journal = "Information Processing & Management",
* title = "A systematic analysis of performance measures for classification tasks",
* keywords = "Performance evaluation, Machine Learning, Text classification",
* year = 2005,
* number = 2,
* issn = "0000-0000",
* @abstract = "Abs",
* doi = "https://doi.org/10.1016/j.ipm.2009.03.002",
* url = "http://www.sciencedirect.com/science/article/pii/S0306457309000259",
* author = "Marina Sokolova and Guy Lapalme"
* };
*
* // New instance of TextProcessor object, this one you would share with other parts of your code.
* BibTexSourceProcessor processor = new BibTexSourceProcessor();
*
* // Generating BibTex code
* String code = entry.GetSource(processor.latex, log);
*
* // Making path
* String path = folderResults.pathFor(nameof(Example4_UsingObjectModel) + ".txt");
*
* File.WriteAllText(path, code);
*
* // --- Now we export it to the Excel file
*
* // Creation of data table collection
* DataTableTypeExtended<BibTexEntryModel> bibTable = new DataTableTypeExtended<BibTexEntryModel>("RuntimeCreatedBibTex", "BibTex table, created in Run Time");
* bibTable.AddRow(entry);
*
* // creates extended version of Excel file, with additional spreadsheet for Legend and other meta information
* var codeDataTable_ref = bibTable.GetReportAndSave(folderResults, notation, nameof(Example4_UsingObjectModel));
*/
public void Example4_UsingObjectModel()
{
// --- We create the entry and write its source code to the disk
// Creation of BibTex entry from code
BibTexEntryModel entry = new BibTexEntryModel()
{
EntryKey = "SOKOLOVA2009427",
EntryType = "article",
journal = "Information Processing & Management",
title = "A systematic analysis of performance measures for classification tasks",
keywords = "Performance evaluation, Machine Learning, Text classification",
year = 2005,
number = 2,
issn = "0000-0000",
@abstract = "Abs",
doi = "https://doi.org/10.1016/j.ipm.2009.03.002",
url = "http://www.sciencedirect.com/science/article/pii/S0306457309000259",
author = "Marina Sokolova and Guy Lapalme"
};
// New instance of TextProcessor object, this one you would share with other parts of your code.
BibTexSourceProcessor processor = new BibTexSourceProcessor();
// Generating BibTex code
String code = entry.GetSource(processor.latex, log);
// Making path
String path = folderResults.pathFor(nameof(Example4_UsingObjectModel) + ".txt");
File.WriteAllText(path, code);
// --- Now we export it to the Excel file
// Creation of data table collection
DataTableTypeExtended <BibTexEntryModel> bibTable = new DataTableTypeExtended <BibTexEntryModel>("RuntimeCreatedBibTex", "BibTex table, created in Run Time");
bibTable.AddRow(entry);
// creates extended version of Excel file, with additional spreadsheet for Legend and other meta information
var codeDataTable_ref = bibTable.GetReportAndSave(folderResults, notation, nameof(Example4_UsingObjectModel));
}
public void Publish(folderNode folder, Boolean exportXML = true, Boolean exportDescribe = true, Boolean exportDatatable = true)
{
if (exportXML)
{
String xml = objectSerialization.ObjectToXML(this);
String x_path = folder.pathFor(name + "_report.xml", imbSCI.Data.enums.getWritableFileMode.overwrite, "Serialized dtructural report of a dataset");
File.WriteAllText(x_path, xml);
}
if (exportDescribe)
{
builderForText builderForText = new builderForText();
String t_path = folder.pathFor(name + "_report.txt", imbSCI.Data.enums.getWritableFileMode.overwrite, "Summary of structural report of a dataset");
Describe(builderForText);
File.WriteAllText(t_path, builderForText.GetContent());
}
if (exportDatatable)
{
DataTableTypeExtended <DatasetStructureReport> dt_reports = new DataTableTypeExtended <DatasetStructureReport>(name, "Dataset structure stats");
dt_reports.AddRow(this);
foreach (var ch in Children)
{
dt_reports.AddRow(ch);
}
dt_reports.GetReportAndSave(folder, null, name + "_report");
}
}
/// <summary>
/// Publishes the table blocks.
/// </summary>
/// <param name="folder">The folder.</param>
/// <param name="blockSize">Size of the block.</param>
/// <param name="blockCount">The block count.</param>
/// <returns></returns>
public DataTableTypeExtended <FeatureCWPFrequencies> PublishTableBlocks(folderNode folder, Int32 blockSize = 500, Int32 blockCount = 10)
{
if (!this.Any())
{
return(null);
}
foreach (var pair in this)
{
pair.Value.Compute();
}
Int32 b = 0;
for (int i = 0; i < blockCount; i++)
{
var p = this.First();
String dt_n = name + "_" + i.ToString();
DataTableTypeExtended <FeatureCWPFrequencies> cwpMetrics = new DataTableTypeExtended <FeatureCWPFrequencies>(dt_n, "Collected metrics");
// DataTableTypeExtended<FeatureCWPFrequencies> cwpFrequencies = new DataTableTypeExtended<FeatureCWPFrequencies>(dt_n + "_freq", "frequency metrics");
// p.Value.SetDataTable(datatable);
// DataColumn nm = datatable.Columns.Add("Name");
Int32 c = 0;
foreach (var pair in this)
{
if (c > (i * blockSize) && c < (i + 1) * blockSize)
{
cwpMetrics.AddRow(pair.Value);
// cwpFrequencies.AddRow(term_finders.)
}
c++;
}
if (cwpMetrics.Rows.Count > 0)
{
DataTableConverterASCII dataTableConverterASCII = new DataTableConverterASCII();
dataTableConverterASCII.ConvertToFile(cwpMetrics, folder, dt_n);
DataTableForStatistics report = cwpMetrics.GetReportAndSave(folder, null, dt_n);
}
}
DataTableTypeExtended <FeatureCWPFrequencies> output = new DataTableTypeExtended <FeatureCWPFrequencies>();
foreach (var p in this)
{
output.AddRow(p.Value);
}
output.Save(folder, null, "stats_frequencies");
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 -------------------------------------------------------------------------------------------------
}
/// <summary>
/// Prepares for parallel execution.
/// </summary>
/// <param name="tools">The tools.</param>
/// <param name="_context">The context.</param>
public webProjectKnowledgeSet PrepareForParallelExecution(classifierTools tools, experimentExecutionContext _context)
{
if (caseKnowledgeSet == null)
{
caseKnowledgeSet = new webProjectKnowledgeSet();
}
if (items.Any())
{
experimentContext.notes.log("Mining Context was ready already.");
return(caseKnowledgeSet);
}
DateTime startTime = DateTime.Now;
experimentContext = _context;
List <webCaseKnowledge> cases = new List <webCaseKnowledge>();
folderNode classReportFolder = experimentContext.folder.Add("General", "General and diagnostic reports", "The folder contains general (outside k-folds) reports on analysied industries (categories), web sites and other diagnostic data");
// <---------------------------------------------------------------------------------------------------------------- [ performing pipeline ]
experimentContext.notes.log("Executing the Mining Context decomposition with the pipeline model");
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
var pipelineContext = GetContextForPipeline(tools, classSet);
sitesByCategory.Add(classSet, new List <pipelineTaskMCSiteSubject>());
if (!pipelineContext.exitByType.ContainsKey(typeof(pipelineTaskMCSiteSubject)))
{
throw new aceGeneralException("Pipeline context output contains no web site subjects! Check the pipeline Site Task constructor.", null, pipelineContext, "Pipeline broken");
}
var sitesForContext = pipelineContext.exitByType[typeof(pipelineTaskMCSiteSubject)]; // <----- preparing
foreach (var site in sitesForContext)
{
tokenBySite.Add(site as pipelineTaskMCSiteSubject, new ConcurrentBag <pipelineTaskSubjectContentToken>());
sitesByCategory[classSet].Add(site as pipelineTaskMCSiteSubject);
webCaseKnowledge webCase = new webCaseKnowledge(site as pipelineTaskMCSiteSubject, classSet);
caseKnowledgeSet.Add(webCase);
cases.Add(webCase);
}
semanticFVExtractorKnowledge kn = new semanticFVExtractorKnowledge();
kn.name = classSet.name + "_general";
kn.relatedItemPureName = classSet.name;
kn.type = WebFVExtractorKnowledgeType.aboutCompleteCategory;
kn.Deploy(classReportFolder, experimentContext.logger);
knowledgeByClass.TryAdd(classSet, kn);
}
experimentContext.notes.log("Sorting tokens for all sites [in parallel]");
Parallel.ForEach(tokenBySite.Keys, site =>
{
var leafs = site.getAllLeafs();
foreach (var leaf in leafs)
{
pipelineTaskSubjectContentToken token = leaf as pipelineTaskSubjectContentToken;
if (token != null)
{
tokenBySite[site].Add(token);
}
}
});
foreach (var c in cases)
{
c.tokens = tokenBySite[c.MCSiteSubject];
}
experimentContext.notes.log("Building diagnostic TF-IDF master tables for all classes [in parallel]");
Boolean useIntegratedApproach = false;
if (useIntegratedApproach)
{
var valCase = experimentContext.validationCollections[experimentContext.masterExtractor.name].GetDiagnosticCase(experimentContext.classes);
Parallel.ForEach(sitesByCategory, pair =>
{
knowledgeByClass.TryAdd(pair.Key, experimentContext.masterExtractor.DoFVExtractionForClassViaCases(valCase.trainingCases[pair.Key.classID], pair.Key, valCase, experimentContext.tools, experimentContext.logger));
});
}
else
{
Parallel.ForEach(sitesByCategory, pair =>
{
IDocumentSetClass category = pair.Key;
List <pipelineTaskMCSiteSubject> sites = pair.Value;
var lt = BuildLemmaTableForClass(tools, category, sites);
lt.Save();
// lt.SaveAs(classReportFolder.pathFor(lt.info.Name), imbSCI.Data.enums.getWritableFileMode.overwrite);
});
}
experimentContext.notes.log("Saving lexic resource cache subset - for later reuse in case of repeated experiment run");
tools.SaveCache();
if (!useIntegratedApproach)
{
experimentContext.notes.log("Performing chunk construction for all web sites in all categories [in serial]");
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
BuildChunksForClass(tools, classSet);
}
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
experimentContext.masterExtractor.chunkTableConstructor.process(chunksByCategory[classSet], cnt_level.mcPage, knowledgeByClass[classSet].WLChunkTableOfIndustryClass, null, experimentContext.logger, false);
}
}
if (tools.operation.doCreateDiagnosticMatrixAtStart)
{
experimentContext.notes.log("Performing diagnostic analysis on all categories...[doCreateDiagnosticMatrixAtStart=true]");
folderNode matrixReport = classReportFolder.Add("clouds", "More reports on semantic cloud", "Directory contains exported DirectedGraphs, varous matrix derivates, combined cloud and other diagnostic things");
List <lemmaSemanticCloud> clouds = new List <lemmaSemanticCloud>();
List <lemmaSemanticCloud> filteredClouds = new List <lemmaSemanticCloud>();
var converter = lemmaSemanticCloud.GetDGMLConverter();
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
// experimentContext.masterExtractor.chunkTableConstructor.process(chunksByCategory[classSet], cnt_level.mcPage, knowledgeByClass[classSet].WLChunkTableOfIndustryClass, null, experimentContext.logger, false);
var cloud = experimentContext.masterExtractor.CloudConstructor.process(knowledgeByClass[classSet].WLChunkTableOfIndustryClass, knowledgeByClass[classSet].WLTableOfIndustryClass, knowledgeByClass[classSet].semanticCloud, experimentContext.logger, tokenBySite.Keys.ToList(), tools.GetLemmaResource());
knowledgeByClass[classSet].semanticCloud.className = classSet.name;
clouds.Add(cloud);
if (experimentContext.tools.operation.doUseSimpleGraphs)
{
cloud.GetSimpleGraph(true).Save(matrixReport.pathFor("cloud_initial_" + classSet.name, imbSCI.Data.enums.getWritableFileMode.none, "Initial version of full-sample set, diagnostic Semantic Cloud for category [" + classSet.name + "]"));
}
else
{
converter.ConvertToDMGL(cloud).Save(matrixReport.pathFor("cloud_initial_" + classSet.name, imbSCI.Data.enums.getWritableFileMode.none, "Initial version of full-sample set, diagnostic Semantic Cloud for category [" + classSet.name + "]"));
}
knowledgeByClass[classSet].semanticCloudFiltered = knowledgeByClass[classSet].semanticCloud.CloneIntoType <lemmaSemanticCloud>(true);
knowledgeByClass[classSet].semanticCloudFiltered.className = classSet.name;
filteredClouds.Add(knowledgeByClass[classSet].semanticCloudFiltered);
}
cloudMatrix matrix = new cloudMatrix("CloudMatrix", "Diagnostic cloud matrix created from the complete sample set of [" + clouds.Count() + "] classes");
matrix.build(filteredClouds, experimentContext.logger);
lemmaSemanticCloud mergedCloudInitial = matrix.GetUnifiedCloud();
mergedCloudInitial.Save(matrixReport.pathFor("unified_initial_cloud.xml", imbSCI.Data.enums.getWritableFileMode.overwrite, "Serialized object - Initial version of Semantic Cloud built as union of full-sample set Semantic Clouds of all categories"));
var reductions = matrix.TransformClouds(experimentContext.masterExtractor.settings.semanticCloudFilter, experimentContext.logger);
var p = matrixReport.pathFor("reductions_nodes.txt", imbSCI.Data.enums.getWritableFileMode.overwrite, "Report on Cloud Matrix transformation process");
File.WriteAllLines(p, reductions);
matrix.BuildTable(experimentContext.masterExtractor.settings.semanticCloudFilter, cloudMatrixDataTableType.initialState | cloudMatrixDataTableType.maxCloudFrequency | cloudMatrixDataTableType.absoluteValues).GetReportAndSave(matrixReport, appManager.AppInfo, "matrix_max_cf_initial", true, experimentContext.tools.operation.doReportsInParalell);
matrix.BuildTable(experimentContext.masterExtractor.settings.semanticCloudFilter, cloudMatrixDataTableType.initialState | cloudMatrixDataTableType.overlapSize | cloudMatrixDataTableType.absoluteValues).GetReportAndSave(matrixReport, appManager.AppInfo, "matrix_overlap_size_initial", true, experimentContext.tools.operation.doReportsInParalell);
matrix.BuildTable(experimentContext.masterExtractor.settings.semanticCloudFilter, cloudMatrixDataTableType.initialState | cloudMatrixDataTableType.overlapValue | cloudMatrixDataTableType.absoluteValues).GetReportAndSave(matrixReport, appManager.AppInfo, "matrix_overlap_value_initial", true, experimentContext.tools.operation.doReportsInParalell);
matrix.ExportTextReports(matrixReport, true, "matrix_cf");
matrix.ExportTextReports(matrixReport, false, "matrix_cf");
lemmaSemanticCloud mergedCloudAfterReduction = matrix.GetUnifiedCloud();
mergedCloudAfterReduction.Save(matrixReport.pathFor("unified_reduced_cloud.xml", imbSCI.Data.enums.getWritableFileMode.overwrite, "Serialized object -Version of all-categories diagnostic Semantic Cloud, after Cloud Matrix filter was applied"));
if (experimentContext.tools.operation.doUseSimpleGraphs)
{
mergedCloudInitial.GetSimpleGraph(true).Save(matrixReport.pathFor("unified_initial_cloud", imbSCI.Data.enums.getWritableFileMode.overwrite, "DirectedGraphML file - unified Semantic Cloud, before Cloud Matrix filter was applied - Open this in VisualStudo)"));
}
else
{
converter = lemmaSemanticCloud.GetDGMLConverter();
converter.ConvertToDMGL(mergedCloudInitial).Save(matrixReport.pathFor("unified_initial_cloud", imbSCI.Data.enums.getWritableFileMode.overwrite, "DirectedGraphML file - unified Semantic Cloud, before Cloud Matrix filter was applied - Open this in VisualStudo)"));
}
// <-------- analysis -----------------------------------------------------------------------------------
DataTableTypeExtended <freeGraphReport> cloudReports = new DataTableTypeExtended <freeGraphReport>();
foreach (var cl in filteredClouds)
{
freeGraphReport fgReport = new freeGraphReport(cl);
fgReport.Save(matrixReport);
cloudReports.AddRow(fgReport);
}
freeGraphReport unifiedReport = new freeGraphReport(mergedCloudAfterReduction);
unifiedReport.Save(matrixReport);
cloudReports.AddRow(unifiedReport);
cloudReports.GetReportAndSave(matrixReport, appManager.AppInfo, "analysis_SemanticClouds");
// <-------- analysis -----------------------------------------------------------------------------------
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
var cloud = knowledgeByClass[classSet].semanticCloudFiltered; // .WLChunkTableOfIndustryClass, knowledgeByClass[classSet].WLTableOfIndustryClass, knowledgeByClass[classSet].semanticCloud, experimentContext.logger, tokenBySite.Keys.ToList());
if (experimentContext.tools.operation.doUseSimpleGraphs)
{
cloud.GetSimpleGraph(true).Save(matrixReport.pathFor("unified_initial_cloud", imbSCI.Data.enums.getWritableFileMode.overwrite, "DirectedGraphML file - unified Semantic Cloud, before Cloud Matrix filter was applied - Open this in VisualStudo)"));
}
else
{
converter = lemmaSemanticCloud.GetDGMLConverter();
converter.ConvertToDMGL(cloud).Save(matrixReport.pathFor("unified_initial_cloud", imbSCI.Data.enums.getWritableFileMode.overwrite, "DirectedGraphML file - unified Semantic Cloud, before Cloud Matrix filter was applied - Open this in VisualStudo)"));
}
//converter.ConvertToDMGL(cloud).Save(matrixReport.pathFor("cloud_reduced_" + classSet.name, imbSCI.Data.enums.getWritableFileMode.none, "DirectedGraphML file - Initial version of Semantic Cloud built as union of full-sample set Semantic Clouds of all categories (Open this with VS)"), imbSCI.Data.enums.getWritableFileMode.overwrite);
}
instanceCountCollection <String> tfcounter = new instanceCountCollection <string>();
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
var wlt = knowledgeByClass[classSet].WLTableOfIndustryClass.GetDataTable();
wlt.DefaultView.Sort = "termFrequency desc";
var sorted = wlt.DefaultView.ToTable();
var tbl = wlt.GetClonedShema <DataTable>(true);
tbl.CopyRowsFrom(sorted, 0, 100);
tbl.GetReportAndSave(classReportFolder, appManager.AppInfo, classSet.name + "_WebLemma", true, experimentContext.tools.operation.doReportsInParalell);
var cht = knowledgeByClass[classSet].WLChunkTableOfIndustryClass.GetDataTable();
cht.DefaultView.Sort = "termFrequency desc";
var csorted = cht.DefaultView.ToTable();
tbl = cht.GetClonedShema <DataTable>(true);
tbl.CopyRowsFrom(csorted, 0, 100);
tbl.GetReportAndSave(classReportFolder, appManager.AppInfo, classSet.name + "_Chunks", true, experimentContext.tools.operation.doReportsInParalell);
tfcounter.AddInstanceRange(knowledgeByClass[classSet].WLTableOfIndustryClass.unresolved);
knowledgeByClass[classSet].OnBeforeSave();
}
List <String> countSorted = tfcounter.getSorted();
StringBuilder sb = new StringBuilder();
foreach (String s in countSorted)
{
sb.AppendLine(String.Format("{1} : {0}", s, tfcounter[s]));
}
String pt = classReportFolder.pathFor("unresolved_tokens.txt", imbSCI.Data.enums.getWritableFileMode.none, "Cloud Frequency list of all unresolved letter-only tokens");
File.WriteAllText(pt, sb.ToString());
}
if (tools.operation.doFullDiagnosticReport)
{
experimentContext.notes.log("Generating full diagnostic report on classes...");
DataTable rep = null;
foreach (IDocumentSetClass classSet in experimentContext.classes.GetClasses())
{
rep = this.GetClassKnowledgeReport(classSet, rep);
}
rep.SetAdditionalInfoEntry("Experiment", experimentContext.setup.name);
rep.AddExtra("Experiment: " + experimentContext.setup.name);
rep.AddExtra("Info: " + experimentContext.setup.description);
rep.SetDescription("Structural report for all classes in the experiment");
rep.GetReportAndSave(classReportFolder, appManager.AppInfo, "structural_class_report", true, experimentContext.tools.operation.doReportsInParalell);
}
classReportFolder.generateReadmeFiles(appManager.AppInfo);
experimentContext.notes.log("Mining Context preprocessing done in [" + DateTime.Now.Subtract(startTime).TotalMinutes.ToString("F2") + "] minutes");
return(caseKnowledgeSet);
}
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);
}
public void Save(ILogBuilder log, Boolean SubLevelCall = false)
{
//if (folder == null) folder = notes.folder_corpus;
if (folder == null)
{
return;
}
if (purpose != FeatureCWPAnalysisSettings.AnalysisPurpose.application)
{
SaveFeatures(folder.Add("Features", "Features", "Features"), featuresByClass);
EntryDictionary.Save(folder, log, name);
if (!SubLevelCall)
{
var flds = fields();
DataSet dataSet = new DataSet("rep_" + name);
// List<DataTableForStatistics> rdt_list = new List<DataTableForStatistics>();
foreach (String n in flds)
{
DataTable dt = EntryDictionary.MakeTable(n + "_" + name, EntryDictionary.description,
flds
, 500, flds.IndexOf(n));
dt.AddStringLine("Report for " + name);
dataSet.Tables.Add(dt);
//DataTableForStatistics rdt = dt.GetReportTableVersion();
//rdt_list.Add(rdt);
}
DataSetForStatistics report = dataSet.GetReportAndSave(folder, null, "cwp_" + name);
var keys = Keys.ToList();
keys.Sort();
DataTableTypeExtended <FeatureCWPAnalysisSiteMetrics> metrics = new DataTableTypeExtended <FeatureCWPAnalysisSiteMetrics>();
Int32 c = 0;
foreach (var key in keys)
{
metrics.AddRow(this[key]);
c++;
if (c > 2000)
{
break;
}
}
metrics.GetReportAndSave(folder, null, "cwp_" + name + "metrics");
//foreach (var pair in entryReport)
//{
// folderNode fn = folder.Add(pair.Key, pair.Key, "Sub entry report");
// pair.Value.Save(log, true);
//}
}
}
}
