private void Btn30Duc2005ExcelClick(object sender, EventArgs e)
{
var appSettings = ConfigurationManager.AppSettings;
var d1 = new DUCDataSet("DUC2001",
appSettings["DUC2001-dirRouge"],
appSettings["DUC2001-dirMatrix"]);
var d2 = new DUCDataSet("DUC2002",
appSettings["DUC2002-dirRouge"],
appSettings["DUC2002-dirMatrix"]);
switch (lsbDataSet.SelectedItem.ToString())
{
case "DUC2001": _chosenDUC = d1;
break;
case "DUC2002": _chosenDUC = d2;
break;
}
_totalRepetitions = int.Parse((string)lsbTotalEjecuciones.SelectedItem);
_experimentId = int.Parse((string)lsbIdExperimento.SelectedItem);
_weight = (TFIDFWeight)Enum.Parse(typeof(TFIDFWeight), (string)lsbModelos.SelectedItem);
_docRep = (DocumentRepresentation)Enum.Parse(typeof(DocumentRepresentation), (string)lsbDocRep.SelectedItem);
_normalized = bool.Parse((string)lstNormalized.SelectedItem);
_algorithm = (string)lsAlgorithm.SelectedItem;
btn30DUC2001excel.Enabled = false;
backgroundWorker1.RunWorkerAsync();
}
public void Ejecutar(DUCDataSet midataset, SummaryParameters myParameters,
int idEjecution, int maxRepetitions, string theAlgorithm)
{
//Se establece el Identification de la ejecucion y se crea el directorio de salida
var directorioDeSalida = midataset.RougeRootDirectory + @"experimentos\" + idEjecution.ToString("0000");
Directory.CreateDirectory(directorioDeSalida);
//Se define el nombre del archivo en el que se colocaran los resultados por medio de los parámetros de ejecución.
var theDate = DateTime.Now.Year + "-" + DateTime.Now.Month.ToString("00") + "-" + DateTime.Now.Day.ToString("00") + "-" + DateTime.Now.Hour.ToString("00") + "-" + DateTime.Now.Minute.ToString("00");
var outputFileName = theDate + "-Exp-" + maxRepetitions + "-" + myParameters + ".xlsx";
outputFileName = outputFileName.Replace(",", ".");
var directoryList = new List <string>();
directoryList.AddRange(Directory.GetDirectories(midataset.RougeRootDirectory + "documents")); //Tiene la ruta de cada documento
directoryList.Sort();
var fileAccount = 0;
var allFullNews = new List <string>();
foreach (var fullDirectory in directoryList) //Recorre cada directorio de documentos y hace ...
{
var lasNoticiasFull = Directory.GetFiles(fullDirectory);
allFullNews.AddRange(lasNoticiasFull);
}
foreach (var fullNews in allFullNews)
{
fileAccount++;
var theFullNews = fullNews;
var x = new FileInfo(theFullNews);
var thisNews = x.Name; //Deja solo el nombre de la noticia
Debug.WriteLine(thisNews + " " + fileAccount);
var nombreArchivosCache = midataset.MatricesRootDirectory + thisNews + "-" +
myParameters.MyTDMParameters.MinimumFrequencyThresholdOfTermsForPhrase + "-" +
myParameters.MyTDMParameters.MinimumThresholdForTheAcceptanceOfThePhrase + "-" +
myParameters.MyTDMParameters.TheTFIDFWeight + "-" +
myParameters.MyTDMParameters.TheDocumentRepresentation;
nombreArchivosCache = nombreArchivosCache.Replace(",", ".");
Parallel.For(0, maxRepetitions, repetition =>
//for (var repetition=0; repetition < maxRepetitions; repetition++)
{
//if (laNoticia != "LA042190-0060")
// continue;
// Create the experiment folder If it does not exists
var directorioExperimento = directorioDeSalida + @"\" + repetition.ToString("000");
if (!Directory.Exists(directorioExperimento))
{
Directory.CreateDirectory(directorioExperimento);
}
directorioExperimento += @"\systems";
if (!Directory.Exists(directorioExperimento))
{
Directory.CreateDirectory(directorioExperimento);
}
SummarizerAlgorithm summarizer = null;
switch (theAlgorithm)
{
case "ContinuousLexRank":
summarizer = new ContinuousLexRank();
summarizer.Summarize(myParameters, theFullNews, nombreArchivosCache);
break;
case "DegreeCentralityLexRank":
summarizer = new DegreeCentralityLexRank();
summarizer.Summarize(myParameters, theFullNews, nombreArchivosCache);
break;
case "LexRankWithThreshold":
summarizer = new LexRankWithThreshold();
summarizer.Summarize(myParameters, theFullNews, nombreArchivosCache);
break;
case "FSP":
((FSPParameters)myParameters).RandomGenerator = new Random(repetition);
summarizer = new FSP();
summarizer.Summarize(myParameters, theFullNews, nombreArchivosCache);
break;
case "GBHS":
((GBHSParameters)myParameters).RandomGenerator = new Random(repetition);
summarizer = new GBHS();
summarizer.Summarize(myParameters, theFullNews, nombreArchivosCache);
break;
case "SFLA":
((SFLAParameters)myParameters).RandomGenerator = new Random(repetition);
summarizer = new SFLA();
summarizer.Summarize(myParameters, theFullNews, nombreArchivosCache);
break;
}
if (summarizer != null)
{
var contenidoResumenFinal = summarizer.TextSummary;
File.WriteAllText(directorioExperimento + @"\" + thisNews, contenidoResumenFinal);
}
Debug.Write(repetition + ", ");
//} // Fin de for
}); // Fin de Parallel.For
Debug.WriteLine("");
Debug.WriteLine("THREAD :" + Thread.CurrentThread.ManagedThreadId +
" NEWS " + thisNews);
}
Debug.WriteLine("--- EVALUATING ---");
// Se realizan los Calculus de ROUGE para todos los experimentos de la segunda forma (segun normas exactas de DUC 2005)
Parallel.For(0, maxRepetitions, experimento =>
{
var directorioExperimento = directorioDeSalida + @"\" + experimento.ToString("000");
Rouge.EvaluateAnExperimentWithAllNewsPartA(midataset.RougeRootDirectory, directorioExperimento);
});
var salidaExperimentos = "Exp.\tR1R\tR1P\tR1F\tR2R\tR2P\tR2F\tRLR\tRLP\tRLF\tRSU4R\tRSU4P\tRSU4F\r\n";
var resumenTodosExperimentos = new double[12];
var subtotalesPorGrupoEvaluador = new SubTotalsByDataSet();
for (var experimento = 0; experimento < maxRepetitions; experimento++)
{
var directorioExperimento = directorioDeSalida + @"\" + experimento.ToString("000");
var resultadoEstaNoticia = new double[12];
Rouge.EvaluateAnExperimentWithAllNewsPartB(midataset.RougeRootDirectory, directorioExperimento,
ref resultadoEstaNoticia, ref subtotalesPorGrupoEvaluador);
salidaExperimentos += experimento.ToString("00") + "\t";
for (var i = 0; i < 12; i++)
{
salidaExperimentos += resultadoEstaNoticia[i] + "\t";
resumenTodosExperimentos[i] += resultadoEstaNoticia[i];
}
salidaExperimentos += "\r\n";
}
salidaExperimentos += "TOTAL\t";
var salidaGlobal = outputFileName + "\t";
for (var i = 0; i < 12; i++)
{
resumenTodosExperimentos[i] = resumenTodosExperimentos[i] / maxRepetitions;
salidaExperimentos += resumenTodosExperimentos[i] + "\t";
salidaGlobal += resumenTodosExperimentos[i] + "\t";
}
salidaExperimentos += "\r\n";
salidaGlobal += "\r\n";
File.AppendAllText(@"D:\SalidaGlobal.txt", salidaGlobal);
//Thread.Sleep(2000);
//GrabarEnExcelExperimentosPorNoticia(midataset.DirectorioRaizRouge, nombreArchivoDeSalida, "TodoExp", salidaExperimentos, true);
//foreach (SubTotalsByDataSet.GrupoEvaluadorRow fila in subtotalesPorGrupoEvaluador.GrupoEvaluador.Rows)
//{
// fila.Recall = decimal.Divide(fila.Recall, fila.Contador);
// fila.Precision = decimal.Divide(fila.Precision, fila.Contador);
// fila.Fmeasure = decimal.Divide(fila.Fmeasure, fila.Contador);
//}
//var listaRouges = new[] { "ROUGE-1", "ROUGE-2", "ROUGE-SU4" };
//foreach (var elRouge in listaRouges)
//{
// var salida = "Grupo\tRecall\tPrecision\tFmeasure\r\n";
// foreach (var dataRow in subtotalesPorGrupoEvaluador.GrupoEvaluador.Select("Rouge = '" + elRouge + "'"))
// {
// var fila = (SubTotalsByDataSet.GrupoEvaluadorRow)dataRow;
// salida += fila.Name + "\t" + fila.Recall + "\t" + fila.Precision + "\t" + fila.Fmeasure + "\r\n";
// }
// Thread.Sleep(2000);
// GrabarEnExcelExperimentosPorNoticia(midataset.DirectorioRaizRouge, nombreArchivoDeSalida, elRouge, salida, true);
//}
}