private static void Main(string[] args)
{
var serviceProvider = DependencyResolver.GetServices().BuildServiceProvider();
documentDataBusinessLogic = serviceProvider.GetService <IDocumentDataBusinessLogic>();
topicPredictorEvaluator = serviceProvider.GetService <ITopicPredictorEvaluator>();
var selectedDirectory = HandleDirectorySelection();
var selectedRunCount = HandleRunCountSelection();
var documentDataList = HandleDocumentDataListProcessing(selectedDirectory);
var accuracies = new ConcurrentBag <double>();
Parallel.For(0, selectedRunCount, new ParallelOptions {
MaxDegreeOfParallelism = 3
}, (runNumber) =>
{
var featureSelector = serviceProvider.GetService <IFeatureSelector>();
var topicPredictor = new KNearestNeighborsTopicPredictor();
var lists = SplitListIntoTwoSeparateLists(documentDataList, 70);
var listForTraining = lists.Item1;
var listForValidation = lists.Item2;
var datasetRepresentationTraining = listForTraining.ToDatasetRepresentation();
datasetRepresentationTraining = datasetRepresentationTraining.ReconstructByEliminatingWordsBelowAndAboveThresholds(5, 95);
var features = featureSelector.GetMostImportantWords(datasetRepresentationTraining);
datasetRepresentationTraining = datasetRepresentationTraining.ReconstructByKeepingOnlyTheseWords(features);
topicPredictor.Train(datasetRepresentationTraining);
var evaluationResults = topicPredictorEvaluator.EvaluateTopicPredictor(topicPredictor, listForValidation);
double total = listForValidation.Count;
var successfullyPredicted = 0;
foreach (var documentData in listForValidation)
{
var predictedTopic = topicPredictor.PredictTopic(documentData);
if (documentData.Topics.Contains(predictedTopic))
{
successfullyPredicted++;
}
}
var accuracy = successfullyPredicted / total * 100;
accuracies.Add(accuracy);
ConsoleWriteLineWithColor($"Accuracy for run {runNumber}: {accuracy}");
});
ConsoleWriteLineWithColor("----------------------------------------------------------");
ConsoleWriteLineWithColor($"Average accuracy = {accuracies.Sum() / accuracies.Count}");
}
public DocumentDataExtractionUserControl()
{
InitializeComponent();
var serviceProvider = DependencyResolver.GetServices().BuildServiceProvider();
documentDataBusinessLogic = serviceProvider.GetService <IDocumentDataBusinessLogic>();
resultFormatter = serviceProvider.GetService <IResultFormatter>();
documentDataDisplayUserControl = new DocumentDataDisplayUserControl();
panelDocumentDataDisplayUserControl.Controls.Add(documentDataDisplayUserControl);
UpdateRunButtonEnabledProperty();
SetStatusLabel("Waiting for input", Color.DodgerBlue);
}
public GlobalDocumentDataBuilderUserControl()
{
InitializeComponent();
var serviceProvider = DependencyResolver.GetServices().BuildServiceProvider();
documentDataBusinessLogic = serviceProvider.GetService <IDocumentDataBusinessLogic>();
featureSelector = serviceProvider.GetService <IFeatureSelector>();
topicPredictor = serviceProvider.GetService <ITopicPredictor>();
documentDataDisplayUserControl = new DocumentDataDisplayUserControl();
panelDocumentDataDisplayUserControl.Controls.Add(documentDataDisplayUserControl);
UpdateRunButtonEnabledProperty();
SetStatusLabel("Waiting for input", Color.DodgerBlue);
filepathsToUseForDocumentData = new List <string>();
}
public void Setup()
{
var serviceProvider = DependencyResolver.GetServices().BuildServiceProvider();
stopWordsProviderMock = new Mock <IStopWordProvider>();
documentDataBusinessLogic = new DocumentDataBusinessLogic(new DocumentDataProvider(stopWordsProviderMock.Object, serviceProvider.GetService <IXmlService>(), serviceProvider.GetService <ITextAnalyzer>()));
filepath = $"{Environment.CurrentDirectory}\\{Constants.TestFileName}";
Tests.Common.Setup.CreateFileWithText(filepath, Constants.XmlFileText);
compareLogic = new CompareLogic
{
Config = new ComparisonConfig
{
IgnoreCollectionOrder = true
}
};
stopWordsProviderMock
.Setup(x => x.GetStopWords())
.Returns(new List <string>());
}
