public override sealed float Score(BasicStats stats, float tfn)
{
double F = stats.TotalTermFreq + 1 + tfn;
// approximation only holds true when F << N, so we use N += F
double N = F + stats.NumberOfDocuments;
return((float)(-SimilarityBase.Log2((N - 1) * Math.E) + this.F(N + F - 1, N + F - tfn - 2) - this.F(F, F - tfn)));
}
public override sealed float Score(BasicStats stats, float tfn)
{
long N = stats.NumberOfDocuments;
long F = stats.TotalTermFreq;
double ne = N * (1 - Math.Pow((N - 1) / (double)N, F));
return(tfn * (float)(SimilarityBase.Log2((N + 1) / (ne + 0.5))));
}
public override sealed float Score(BasicStats stats, float tfn)
{
// we have to ensure phi is always < 1 for tiny TTF values, otherwise nphi can go negative,
// resulting in NaN. cleanest way is to unconditionally always add tfn to totalTermFreq
// to create a 'normalized' F.
double F = stats.TotalTermFreq + 1 + tfn;
double phi = (double)tfn / F;
double nphi = 1 - phi;
double p = 1.0 / (stats.NumberOfDocuments + 1);
double D = phi * SimilarityBase.Log2(phi / p) + nphi * SimilarityBase.Log2(nphi / (1 - p));
return((float)(D * F + 0.5 * SimilarityBase.Log2(1 + 2 * Math.PI * tfn * nphi)));
}
/// <summary>
/// The <em>f</em> helper function defined for <em>B<sub>E</sub></em>. </summary>
private double F(double n, double m)
{
return((m + 0.5) * SimilarityBase.Log2(n / m) + (n - m) * SimilarityBase.Log2(n));
}
internal BasicSimScorer(SimilarityBase outerInstance, BasicStats stats, NumericDocValues norms)
{
this.outerInstance = outerInstance;
this.stats = stats;
this.norms = norms;
}
public override sealed float Score(BasicStats stats, float tfn)
{
float lambda = (float)(stats.TotalTermFreq + 1) / (stats.NumberOfDocuments + 1);
return((float)(tfn * SimilarityBase.Log2(tfn / lambda) + (lambda + 1 / (12 * tfn) - tfn) * LOG2_E + 0.5 * SimilarityBase.Log2(2 * Math.PI * tfn)));
}
