private static void TrainUsingGoogleNews(ProgramArguments programArgs)
{
ITrainer trainer = new GoogleNewsTrainer();
IEnumerable <string> documents = trainer.Filter(programArgs);
CorrelationMatrix matrix = trainer.CalculateCorrelationMatrix(documents);
}
private static void OutputThresholdReport(List <Tuple <Statement, Statement> > pairs, ProgramArguments programArgs)
{
CorrelationMatrix correlationMatrix = LoadCorrelationMatrix(programArgs);
SimilarityAlgorithm sim = new SimilarityAlgorithm(correlationMatrix);
StringBuilder sb = new StringBuilder();
foreach (Tuple <Statement, Statement> pair in pairs)
{
Statement s1 = StemStatement(pair.Item1);
Statement s2 = StemStatement(pair.Item2);
double s12 = sim.StatementSimilarityToStatement(s1, s2);
double s21 = sim.StatementSimilarityToStatement(s2, s1);
bool areEqual = sim.StatementEqualsToStatement(s1, s2);
sb.AppendFormat(
"{0},{1},{2},{2}\r\n",
pair.Item1.ToString().Replace(',', '.'),
pair.Item2.ToString().Replace(',', '.'),
Math.Min(s12, s21),
Math.Abs(s12 - s21));
}
string reportName = "autoRSS_thresholdReport_" + Guid.NewGuid().ToString() + ".csv";
using (StreamWriter sw = new StreamWriter(reportName))
{
sw.WriteLine(sb.ToString());
}
Console.WriteLine("Report: " + reportName);
}
private static IEnumerable <DocumentClusterErrorScore> CategorizeLabeledNewsArticles(ProgramArguments programArgs)
{
IEnumerable <DocumentCluster> originalClusters = GetSimilarNewsTopicFiles();
IEnumerable <Document> documents = Flatten(originalClusters);
CorrelationMatrix correlationMatrix = LoadCorrelationMatrix(programArgs);
DocumentCategorizer categorizer = new DocumentCategorizer(correlationMatrix);
IEnumerable <DocumentCluster> resultClusters = categorizer.Cluster(documents);
OutputClusters(resultClusters);
IEnumerable <DocumentClusterErrorScore> errorScores = CalculateErrorScore(originalClusters, resultClusters);
return(errorScores);
}