/// <summary>
/// Computes a vector of the average weight for each term in the matrix
/// </summary>
/// <param name="matrix">Input matrix</param>
/// <param name="IDs">Collection of artifacts ids</param>
/// <returns>Average vector</returns>
public static double[] ComputeAverageVector(TermDocumentMatrix matrix, IEnumerable<string> IDs)
{
double[] avg = new double[matrix.NumTerms];
for (int j = 0; j < matrix.NumTerms; j++)
{
foreach (string docID in IDs)
{
int docIndex = matrix.GetDocumentIndex(docID);
avg[j] += matrix[docIndex, j];
}
avg[j] = avg[j] / IDs.Count();
}
return avg;
}
/// <summary>
/// Computes a vector of the average weight for each term in the matrix
/// </summary>
/// <param name="matrix">Input matrix</param>
/// <param name="IDs">Collection of artifacts ids</param>
/// <returns>Average vector</returns>
public static double[] ComputeAverageVector(TermDocumentMatrix matrix, IEnumerable <string> IDs)
{
double[] avg = new double[matrix.NumTerms];
for (int j = 0; j < matrix.NumTerms; j++)
{
foreach (string docID in IDs)
{
int docIndex = matrix.GetDocumentIndex(docID);
avg[j] += matrix[docIndex, j];
}
avg[j] = avg[j] / IDs.Count();
}
return(avg);
}
/// <summary>
/// Smoothing filter from ICPC'11 paper "Improving IR-based Traceability Recovery Using Smoothing Filters"
/// </summary>
/// <param name="matrix">Term-by-document matrix</param>
/// <param name="IDs">Collection of document ids to smooth.</param>
/// <returns>Smoothed artifacts</returns>
public static TermDocumentMatrix Compute(TermDocumentMatrix matrix, IEnumerable <string> IDs)
{
double[] avg = WeightUtil.ComputeAverageVector(matrix, IDs);
if (avg.Length != matrix.NumTerms)
{
throw new ArgumentException("Average vector does not have the correct number of terms.");
}
foreach (string docID in IDs)
{
int i = matrix.GetDocumentIndex(docID);
for (int j = 0; j < matrix.NumTerms; j++)
{
matrix[i, j] -= avg[j];
if (matrix[i, j] < 0.0)
{
matrix[i, j] = 0.0;
}
}
}
return(matrix);
}
/// <summary>
/// Smoothing filter from ICPC'11 paper "Improving IR-based Traceability Recovery Using Smoothing Filters"
/// </summary>
/// <param name="matrix">Term-by-document matrix</param>
/// <param name="IDs">Collection of document ids to smooth.</param>
/// <returns>Smoothed artifacts</returns>
public static TermDocumentMatrix Compute(TermDocumentMatrix matrix, IEnumerable<string> IDs)
{
double[] avg = WeightUtil.ComputeAverageVector(matrix, IDs);
if (avg.Length != matrix.NumTerms)
throw new ArgumentException("Average vector does not have the correct number of terms.");
foreach (string docID in IDs)
{
int i = matrix.GetDocumentIndex(docID);
for (int j = 0; j < matrix.NumTerms; j++)
{
matrix[i, j] -= avg[j];
if (matrix[i, j] < 0.0)
{
matrix[i, j] = 0.0;
}
}
}
return matrix;
}
