private void execSim()
{
int docId = Convert.ToInt32(ddlDocs.SelectedValue);
d.Index index = new d.Index(d.Helper.INDEX_PATH);
d.DocVSSearcher searcher = new d.DocVSSearcher(index, new d.DocsLoader(), new d.CatsLoader());
d.ResultDocument[] results = searcher.Search(docId, 20);
StringBuilder sb = new StringBuilder();
if (results != null)
{
sb.AppendFormat("<p>Displaying <b>20</b> most similar documents:</p><table cellpadding=5 cellspacing=0 border=1>", results.Length);
sb.Append("<tr bgcolor=#f1f1f1><td><b>similarity</b></td><td><b>title</b></td></tr>");
int max = Math.Min(20, results.Length);
for (int i = 0; i < max; i++)
{
sb.AppendFormat("<tr><td>{0}</td><td><a href='http://en.wikipedia.org/wiki/{1}'>{1}</a></td></tr>",
results[i].Similarity, index.GetURL(results[i].DocId));
}
sb.Append("</table>");
}
else
{
sb.Append("<p>Found <b>0</b> results");
}
ltrSimResults.Text = sb.ToString();
}
private void execSearch()
{
string query = tbxSearch.Text;
d.Index index = new d.Index(d.Helper.INDEX_PATH);
d.VSSearcher searcher = new d.VSSearcher(index);
d.ResultDocument[] results = searcher.Search(query);
StringBuilder sb = new StringBuilder();
if (results != null)
{
sb.AppendFormat("<p>Found <b>{0}</b> relevant documents / displaying top 20:</p><table cellpadding=5 cellspacing=0 border=1>", results.Length);
sb.Append("<tr bgcolor=#f1f1f1><td><b>similarity</b></td><td><b>title</b></td></tr>");
int max = Math.Min(20, results.Length);
for (int i = 0; i < max; i++)
{
sb.AppendFormat("<tr><td>{0}</td><td><a href='http://en.wikipedia.org/wiki/{1}'>{1}</a></td></tr>",
results[i].Similarity, index.GetURL(results[i].DocId));
}
sb.Append("</table>");
}
else
{
sb.Append("<p>Found <b>0</b> results");
}
ltrSearchResults.Text = sb.ToString();
}
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 void run()
{
Console.WriteLine("Index loading...");
DateTime t1 = DateTime.Now;
d.Index index = new d.Index(indexPath);
d.VSSearcher vs = new d.VSSearcher(index);
DateTime t2 = DateTime.Now;
Console.WriteLine("Query: ");
string query = Console.ReadLine();
Console.WriteLine("Searching for " + query);
d.ResultDocument[] results = vs.Search(query);
DateTime t3 = DateTime.Now;
TimeSpan diff1 = t2 - t1;
TimeSpan diff2 = t3 - t2;
Console.WriteLine("load index time: " + diff1.Seconds + "." + diff1.Milliseconds);
Console.WriteLine("search time: " + diff2.Seconds + "." + diff2.Milliseconds);
if (results != null)
{
Console.WriteLine(results.Length + " results:");
int max = Math.Min(10, results.Length);
for (int i = 0; i < max; i++)
{
Console.WriteLine("\t" + results[i].DocId + " " + results[i].Similarity + " " + index.GetURL(results[i].DocId));
}
}
}
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();
}
