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 void ScanTrainData(SimilarityAlgorithm sim)
{
StringBuilder sb = new StringBuilder();
foreach (string path in Directory.GetFiles("TrainData"))
{
string fileContents = "";
using (StreamReader sr = new StreamReader(path))
{
fileContents = sr.ReadToEnd();
}
Document document = ConstructDocument(fileContents);
for (int i = 0; i < document.Statements.Length - 1; i += 2)
{
Statement s1 = document.Statements[i];
Statement s2 = document.Statements[i + 1];
double s12 = sim.StatementSimilarityToStatement(s1, s2);
double s21 = sim.StatementSimilarityToStatement(s2, s1);
sb.AppendFormat("{0},{1},{2},{3}\r\n",
s1.ToString(),
s2.ToString(),
Math.Min(s12, s21),
Math.Abs(s12 - s21));
}
}
string filename = "autorss_Threshold_" + Guid.NewGuid().ToString() + ".csv";
using (FileStream fs = new FileStream(filename, FileMode.CreateNew))
{
StreamWriter sw = new StreamWriter(fs);
sw.WriteLine(sb.ToString());
sw.Flush();
}
Console.WriteLine("Threshold Report: " + filename);
}