private void RealizaTreinamentoWeka()
{
TempData["DataTreinamento"] = DateTime.Now;
Instances dadosTreinamento = ImportaArquivosServidor();
// Aplica o filter StringToWordVector
weka.filters.Filter[] filters = new weka.filters.Filter[2];
filters[0] = new StringToWordVector();
filters[1] = AttributeSelectionFilter(2);
weka.filters.MultiFilter filter = new weka.filters.MultiFilter();
filter.setInputFormat(dadosTreinamento);
filter.setFilters(filters);
// Cria o Classificador a partir dos dados de treinamento
FilteredClassifier classifier = new FilteredClassifier();
classifier.setFilter(filter);
classifier.setClassifier(new NaiveBayes());
classifier.buildClassifier(dadosTreinamento);
// Realiza um CrossValidation pra expôr as estatísticas do Classificador
/*
* Evaluation eval = new Evaluation(dadosTreinamento);
* eval.crossValidateModel(classifier, dadosTreinamento, 10, new java.util.Random(1));
*
* var EstatisticasTexto =
* "Instâncias Corretas: \t" + eval.correct() + " (" + Math.Round(eval.pctCorrect(),2) + "%)" + System.Environment.NewLine
+ "Instâncias Incorretas: \t" + eval.incorrect() + " (" + Math.Round(eval.pctIncorrect(),2) + "%)" + System.Environment.NewLine
+ "Total de Instâncias: \t\t" + eval.numInstances();
+
+
+ TempData["TreinamentoRealizado"] = EstatisticasTexto;
*/
// Salva o Classificador (model) como /Classificador/Classificador.model
SerializationHelper.write(string.Format("{0}Classificador.model", DiretorioClassificadorServidor), classifier);
// Salva os dados de treinamento como /Classificador/DadosTreinamento.arff
Utilidades.SalvarArff(dadosTreinamento, DiretorioClassificadorServidor, "DadosTreinamento.arff");
}
/// <summary>
/// Filtered Support Vector Machine Classification with type specified. i.e. BOF or BOW
/// </summary>
/// <param name="type"></param>
private void FilteredSVM(string type, string trainingFilePath, string directoryName, TextFilterType textFilterType)
{
var currDir = System.Environment.GetFolderPath(System.Environment.SpecialFolder.ApplicationData);
// Combine the base folder with your specific folder....
string specificFolder = System.IO.Path.Combine(currDir, "MARC 2.0");
// Check if folder exists and if not, create it
if (!Directory.Exists(specificFolder))
{
Directory.CreateDirectory(specificFolder);
}
try
{
var trainingDatatsetFilePath = "";
if (type == "BOF")
{
trainingDatatsetFilePath = specificFolder + "\\InputData\\TrainingDatasets\\BOF Dataset.arff";
}
else
{
trainingDatatsetFilePath = specificFolder + "\\InputData\\TrainingDatasets\\BOW Dataset.arff";
}
var testDatasetFilePath = specificFolder + "\\InputData\\TrainingDatasets\\Test.arff";
// If training file path is supplied then use it.
if (trainingFilePath != null)
{
trainingDatatsetFilePath = trainingFilePath;
}
java.io.BufferedReader trainReader = new BufferedReader(new FileReader(trainingDatatsetFilePath)); //File with text examples
BufferedReader classifyReader = new BufferedReader(new FileReader(testDatasetFilePath)); //File with text to classify
Instances trainInsts = new Instances(trainReader);
Instances classifyInsts = new Instances(classifyReader);
trainInsts.setClassIndex(trainInsts.numAttributes() - 1);
classifyInsts.setClassIndex(classifyInsts.numAttributes() - 1);
FilteredClassifier model = new FilteredClassifier();
StringToWordVector stringtowordvector = new StringToWordVector();
stringtowordvector.setTFTransform(true);
model.setFilter(new StringToWordVector());
weka.classifiers.Classifier smocls = new weka.classifiers.functions.SMO();
//smocls.setOptions(weka.core.Utils.splitOptions("-C 1.0 -L 0.001 -P 1.0E-12 -N 0 -V -1 -W 1 -K \"weka.classifiers.functions.supportVector.Puk -C 250007 -O 1.0 -S 1.0\""));
smocls.setOptions(weka.core.Utils.splitOptions("-C 1.0 -L 0.0010 -P 1.0E-12 -N 0 -V -1 -W 1 -K \"weka.classifiers.functions.supportVector.PolyKernel -C 250007 -E 1.0\""));
model.setClassifier(smocls);
bool exists;
var directoryRoot = System.IO.Path.GetDirectoryName(Directory.GetCurrentDirectory());
directoryRoot = specificFolder;
//Check if the model exists and if not then build a model
switch (textFilterType)
{
case TextFilterType.NoFilter:
exists = SVMNoFilterCheckifModelExists(trainingDatatsetFilePath);
//if does not exists then build model and save it and save the file also for current filter
if (!exists)
{
model.buildClassifier(trainInsts);
Helper.Helper.WriteToBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMNoFilterModel.dat", model);
string content = System.IO.File.ReadAllText(trainingDatatsetFilePath);
using (var sW = new StreamWriter(directoryRoot + @"\Model\SVM\\SVMNoFilterFile.dat"))
{
sW.Write(content);
}
}
// if exists then read the file and use the model
else
{
model = Helper.Helper.ReadFromBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMNoFilterModel.dat");
}
break;
//Case Stopwords Removal
case TextFilterType.StopwordsRemoval:
exists = SVMSWRCheckifModelExists(trainingDatatsetFilePath);
//if does not exists then build model and save it and save the file also for current filter
if (!exists)
{
model.buildClassifier(trainInsts);
Helper.Helper.WriteToBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMSWRFilterModel.dat", model);
string content = System.IO.File.ReadAllText(trainingDatatsetFilePath);
using (var sW = new StreamWriter(directoryRoot + @"\Model\SVM\\SVMSWRFile.dat"))
{
sW.Write(content);
}
}
// if exists then read the file and use the model
else
{
model = Helper.Helper.ReadFromBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMSWRFilterModel.dat");
}
break;
//Case Stemming
case TextFilterType.Stemming:
exists = SVMSTCheckifModelExists(trainingDatatsetFilePath);
//if does not exists then build model and save it and save the file also for current filter
if (!exists)
{
model.buildClassifier(trainInsts);
Helper.Helper.WriteToBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMSTFilterModel.dat", model);
string content = System.IO.File.ReadAllText(trainingDatatsetFilePath);
using (var sW = new StreamWriter(directoryRoot + @"\Model\SVM\\SVMSTFile.dat"))
{
sW.Write(content);
}
}
// if exists then read the file and use the model
else
{
model = Helper.Helper.ReadFromBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMSTFilterModel.dat");
}
break;
//Case Stopwords Removal with Stemming
case TextFilterType.StopwordsRemovalStemming:
exists = SVMSWRSTCheckifModelExists(trainingDatatsetFilePath);
//if does not exists then build model and save it and save the file also for current filter
if (!exists)
{
model.buildClassifier(trainInsts);
Helper.Helper.WriteToBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMSWRSTFilterModel.dat", model);
string content = System.IO.File.ReadAllText(trainingDatatsetFilePath);
using (var sW = new StreamWriter(directoryRoot + @"\Model\SVM\\SVMSWRSTFile.dat"))
{
sW.Write(content);
}
}
// if exists then read the file and use the model
else
{
model = Helper.Helper.ReadFromBinaryFile <FilteredClassifier>(directoryRoot + @"\Model\SVM\SVMSWRSTFilterModel.dat");
}
break;
default:
break;
}
//model.buildClassifier(trainInsts);
for (int i = 0; i < classifyInsts.numInstances(); i++)
{
classifyInsts.instance(i).setClassMissing();
double cls = model.classifyInstance(classifyInsts.instance(i));
classifyInsts.instance(i).setClassValue(cls);
classification = cls == 0 ? "Bug Report"
: cls == 1 ? "Feature Request"
: "Other";
tempAllClassification.Add(classification);
}
AllClassification = tempAllClassification;
}
catch (Exception o)
{
error = o.ToString();
}
}