gistfile1.cs

//calculate tfidf value with given input parameters
private double TFIDF(int TermFrequency, int DocumentFrequency, int NormalizationValue, int NumberOfDocuments)
{
     //it is important to specify that a divide is a double otherwise the compiler will assume its an integer since the paramaters are integers
     return ((double)TermFrequency / NormalizationValue) * Math.Log(((double)NumberOfDocuments / DocumentFrequency), 2);
}

Term Frequency, Inverse Document Frequency Equation

Definitions from the equation above:

• TermFrequency = frequency of a term in some document
• NormalizationValue = usually the length of the document
• NumberOfDocuments = number of documents in the corpus
• DocumentFrequency = frequency of the term in the entire corpus

Should be easy to convert to Java since its C# syntax