/// <summary>
/// Write the cosine similarity of the given <c>NewsItem</c>s to
/// the file cosine_similarity_log.txt.
/// </summary>
/// <param name="archivist">
/// The <c>Archivist</c> for getting database information.
/// </param>
/// <param name="news">
/// The <c>NewsItem</c>s to print the cosine similarity of.
/// </param>
private static void WriteCosineSimilarity(Archivist archivist, List<NewsItem> news)
{
// Sort the news according to title.
news.Sort((n1, n2) => int.Parse(n1.Title).CompareTo(int.Parse(n2.Title)));
// Get the vector of all news and add them to a matrix.
List<SparseVector> vectors = new List<SparseVector>();
foreach (NewsItem n in news)
{
vectors.Add(archivist.GetTfIdfVector(n));
}
// Create a matrix.
SparseMatrix matrix =
new SparseMatrix(vectors.First().Dimension, vectors.Count);
// Add entries to the matrix.
for (int i = 0; i < vectors.Count; i++)
{
for (int j = 0; j < vectors.First().Dimension; j++)
{
matrix[j, i] = vectors[i][j];
}
}
// Transpose matrix and thus prepare for multiplication.
SparseMatrix mTransposed = matrix.Transpose().NormalizeRows();
// Calculate the result.
SparseMatrix result = mTransposed.Product(matrix.Transpose().NormalizeRows().Transpose());
// Write to file.
using (StreamWriter file = new StreamWriter("cosine_similarity_log.txt"))
{
int rowLength = result.Rows;
int columnLength = result.Columns;
// Print header.
file.Write(" ");
for (int i = 0; i < result.Columns; i++)
{
file.Write("dok" + (i + 1).ToString("0#") + " ");
}
file.WriteLine();
// Print the matrix.
for (int i = 0; i < rowLength; i++)
{
// Print doc title.
file.Write("dok" + (i + 1).ToString("0#") + " ");
for (int j = 0; j < columnLength; j++)
{
file.Write(result[i, j].ToString("0.##0") + " ");
}
if (i != rowLength - 1)
{
file.WriteLine();
}
}
}
}
public void ProductTestGreaterThanZero()
{
SparseMatrix expected = new SparseMatrix(3, 3);
expected[0, 0] = 13.2000008f;
expected[0, 2] = 2.69999981f;
expected[1, 1] = 1.64f;
expected[2, 0] = 10.5f;
expected[2, 2] = 0.45f;
SparseMatrix factor = new SparseMatrix(3, 5);
factor[0, 1] = 2.0f;
factor[0, 2] = 3.0f;
factor[1, 3] = 0.1f;
factor[1, 4] = 1.3f;
factor[2, 0] = 0.9f;
factor[2, 1] = 1.5f;
factor = factor.Transpose();
SparseMatrix result = TestMatrix.Product(factor);
Assert.IsTrue(expected.ApproximatelyEqual(result));
}