private double CalculateChiSquared(string word, TextDocument[] documents, string tag)
{
var cacheKey = string.Format("{0}:{1}", word, tag);
if (cache.ContainsKey(cacheKey))
{
return cache[cacheKey];
}
var N = (double)documents.Length;
var A = (double)documents.WhereMarkedWith(tag).WhereContains(word).Count() + 0.5;
var B = (double)documents.WhereNotMarkedWith(tag).WhereContains(word).Count() + 0.5;
var C = (double)documents.WhereMarkedWith(tag).WhereNotContains(word).Count() + 0.5;
var D = (double)documents.WhereNotMarkedWith(tag).WhereNotContains(word).Count() + 0.5;
return cache[cacheKey] = N * (A * D - C * B) * (A * D - C * B) /
((A + C) * (B + D) * (A + B) * (C + D));
}
private void PrintStats(string message, TextDocument[] textDocument, string targetTag)
{
var positive = textDocument.WhereMarkedWith(targetTag).Count();
var negative = textDocument.WhereNotMarkedWith(targetTag).Count();
Console.WriteLine("{0} Pos = {1}, Neg = {2}", message, positive, negative);
}
