public void NormalizeTest()
{
var v1 = new SparseVector(new double[] { 1.0, -1.0 });
v1.Normalize();
//Проверяем длину вектора - не должна отличаться от 1
Assert.IsTrue(Math.Abs(Math.Sqrt(v1[0] * v1[0] + v1[1] * v1[1]) - 1) < epsilon);
}
private static void BuildExample(TextExample example, Vocabulary voc, int exampleCount)
{
int dimension = voc.Count;
SparseVector vector = new SparseVector(dimension);
foreach (string word in example.Tokens.Keys)
{
int pos = voc.GetWordPosition(word);
if (pos == Constants.KEY_NOT_FOUND)
continue;
// phi i(x) = tfi log(idfi) /k
// tfi: number of occurences of the term i in the document x
// idfi: the ratio between the total number of documents and the
// number of documents containing the term
// k: normalisation constant ensuring that ||phi|| = 1
double phi = example.Tokens[word] * Math.Log(exampleCount / voc.WordExampleOccurMap[word]);
vector.Components.Add(pos, phi);
}
vector.Normalize();
example.X = vector;
}
private static void BuildExample(TextExample example, Vocabulary voc, int exampleCount)
{
int dimension = voc.Count;
SparseVector vector = new SparseVector(dimension);
foreach (string word in example.Tokens.Keys)
{
int pos = voc.GetWordPosition(word);
if (pos == Constants.KEY_NOT_FOUND)
{
continue;
}
// phi i(x) = tfi log(idfi) /k
// tfi: number of occurences of the term i in the document x
// idfi: the ratio between the total number of documents and the
// number of documents containing the term
// k: normalisation constant ensuring that ||phi|| = 1
double phi = example.Tokens[word] * Math.Log(exampleCount / voc.WordExampleOccurMap[word]);
vector.Components.Add(pos, phi);
}
vector.Normalize();
example.X = vector;
}
public void NormalizeThrowsExceptionWhenNullVector()
{
SparseVector v = new SparseVector(5);
v.Normalize();
}
