public Tester(d.DocsLoader dLoader, d.CatsLoader cLoader, d.DocCatsLoader dcLoader)
{
this.dLoader = dLoader;
this.cLoader = cLoader;
this.dcLoader = dcLoader;
Console.WriteLine("Loading index...");
index = new d.Index(d.Helper.INDEX_PATH);
searcher = new d.DocVSSearcher(index, dLoader, cLoader);
}
public AggregateTester(
int minDoc, int maxDoc, int docIncr, int minK, int maxK, int kIncr, int minC, int maxC, int cIncr)
{
dLoader = new d.DocsLoader();
cLoader = new d.CatsLoader();
dcLoader = new d.DocCatsLoader(cLoader);
dataResults = new ArrayList();
this.minDoc = minDoc;
this.maxDoc = maxDoc;
this.docIncr = docIncr;
this.minK = minK;
this.maxK = maxK;
this.kIncr = kIncr;
this.minC = minC;
this.maxC = maxC;
this.cIncr = cIncr;
tab = "\t";
}
static void Main(string[] args)
{
AggregateTester at = new AggregateTester(0, 10, 1, 10, 100, 10, 5, 10, 1);
at.Run();
Hashtable result = new Hashtable();
result.Add(1, true);
result.Add(2, true);
result.Add(3, true);
Hashtable relevant = new Hashtable();
relevant.Add(1, true);
relevant.Add(3, true);
relevant.Add(5, true);
relevant.Add(7, true);
relevant.Add(8, true);
d.PerformanceCalculator pc = new d.PerformanceCalculator(result, relevant);
Console.WriteLine("Precision = " + pc.Precision);
Console.WriteLine("Recall = " + pc.Recall);
Console.WriteLine("FMeasure = " + pc.FMeasure);
d.DocsLoader dl = new d.DocsLoader();
d.CatsLoader cl = new d.CatsLoader();
d.DocCatsLoader dc = new d.DocCatsLoader(cl);
int docId = 1;
ArrayList al = dc.GetDocCategories(docId);
Console.WriteLine(dl.GetDocTitle(docId) + " has " + al.Count + " categories: ");
foreach (int catId in al)
{
Console.WriteLine(" " + cl.GetCategory(catId));
}
d.Index index = new d.Index(Helper.INDEX_PATH);
d.DocTermItem[] dterms = index.DocTerms(0);
SearchVS s = new SearchVS(Helper.INDEX_PATH);
s.run();
i.DataLoader dal = new i.DataLoader(Helper.SOURCE_PATH);
i.IndexBuilder ib = new i.IndexBuilder(dal, Helper.INDEX_PATH);
ib.BuildIndex();
PorterStemmerAlgorithm.PorterStemmer ps = new PorterStemmerAlgorithm.PorterStemmer();
Console.WriteLine(ps.stemTerm("beautify"));
TermFilter f = new TermFilter();
f.CreateNewTermsFile();
TermProcessor p = new TermProcessor();
p.CreateTermsFile();
TermDocsProcessor tdp = new TermDocsProcessor();
tdp.CreateTermDocsFile();
tdp.CreateTermDocsFile();
}
private void execCats()
{
int docId = Convert.ToInt32(ddlDocs.SelectedValue);
int k = Convert.ToInt32(tbxK.Text);
int c = Convert.ToInt32(tbxC.Text);
d.CatsLoader cLoader = new d.CatsLoader();
d.DocCatsLoader dcLoader = new d.DocCatsLoader(cLoader);
d.Tester tester = new d.Tester(new d.DocsLoader(), cLoader, dcLoader);
Hashtable result = tester.GetNewCategories(docId, k, c);
ArrayList arrRelevant = dcLoader.GetDocCategories(docId);
Hashtable relevant = new Hashtable();
if (arrRelevant != null)
{
foreach (int catId in arrRelevant)
{
relevant.Add(catId, true);
}
}
d.PerformanceCalculator pc = new d.PerformanceCalculator(result, relevant);
StringBuilder sb = new StringBuilder();
sb.Append("<p><b>Newly assigned categories:</b>");
if (result.Count > 0)
{
sb.Append("<ul>");
IDictionaryEnumerator en = result.GetEnumerator();
while (en.MoveNext())
{
int catId = Convert.ToInt32(en.Key);
sb.AppendFormat("<li><a href='http://en.wikipedia.org/wiki/Category:{0}'>{0}</a>", cLoader.GetCategory(catId));
}
sb.Append("</ul>");
}
else
{
sb.Append("<p>none assigned");
}
sb.Append("<p><b>Relevant categories:</b>");
if (relevant.Count > 0)
{
sb.Append("<ul>");
IDictionaryEnumerator en = relevant.GetEnumerator();
while (en.MoveNext())
{
int catId = Convert.ToInt32(en.Key);
sb.AppendFormat("<li><a href='http://en.wikipedia.org/wiki/Category:{0}'>{0}</a>", cLoader.GetCategory(catId));
}
sb.Append("</ul>");
}
else
{
sb.Append("<p>none relevant");
}
sb.Append("<p><b>Evaluation:</b>");
sb.Append("<ul>");
sb.AppendFormat("<li>Precision: {0}", pc.Precision);
sb.AppendFormat("<li>Recall: {0}", pc.Recall);
sb.AppendFormat("<li>F-Measure: {0}", pc.FMeasure);
sb.Append("</ul>");
ltrSimResults.Text = sb.ToString();
}