/**
* Used to compare between clusters. If this cluster is better, meaning less
* deviation, returns a negative number so that it is put first when sorted.
*/
public int CompareTo(Cluster other, DocumentAnalyzer analyzer)
{
// TODO: Find better method, this one favors smaller clusters
// Put clusters with only one article at the ends
if (Documents.Count == 1)
{
return(1);
}
if (other.Documents.Count == 1)
{
return(-1);
}
double simA, simB;
simA = simB = 0;
foreach (int i in this.Documents)
{
simA += analyzer.Similarity(this.Centroid, i);
}
foreach (int i in other.Documents)
{
simB += analyzer.Similarity(other.Centroid, i);
}
simA /= this.Documents.Count;
simB /= other.Documents.Count;
if (simA > simB)
{
return(-1);
}
else if (simA < simB)
{
return(1);
}
else
{
return(0);
}
}
public DocumentClusterer(List <NewsArticle> articles)
{
this.articles = articles;
analyzer = new DocumentAnalyzer(articles);
}