public void Normalize(IList <Vector> data)
{
if (data.Count == 0)
{
return;
}
VectorMeanVarianceAccumulator acc = new VectorMeanVarianceAccumulator(data[0].Count);
foreach (Vector v in data)
{
acc.Add(v);
}
Vector mean = acc.Mean;
Vector variance = acc.Variance.Diagonal();
Vector stddev = Vector.Zero(variance.Count);
stddev.SetToFunction(variance, Math.Sqrt);
for (int i = 0; i < stddev.Count; i++)
{
if (stddev[i] == 0.0)
{
mean[i] = 0.0;
stddev[i] = 1.0;
}
}
foreach (Vector v in data)
{
v.SetToDifference(v, mean);
v.SetToRatio(v, stddev);
}
}
public void RandNormalP()
{
double[] m_init = { 1, 2, 3 };
Vector mt = Vector.FromArray(m_init);
double[,] v_init = { { 2, 1, 1 }, { 1, 2, 1 }, { 1, 1, 2 } };
PositiveDefiniteMatrix vt = new PositiveDefiniteMatrix(v_init);
PositiveDefiniteMatrix pt = ((PositiveDefiniteMatrix)vt.Clone()).SetToInverse(vt);
int d = mt.Count;
Vector x = Vector.Zero(d);
VectorMeanVarianceAccumulator mva = new VectorMeanVarianceAccumulator(d);
for (int i = 0; i < nsamples; i++)
{
Rand.NormalP(mt, pt, x);
mva.Add(x);
}
Vector m = mva.Mean;
PositiveDefiniteMatrix v = mva.Variance;
Console.WriteLine("");
Console.WriteLine("Multivariate NormalP");
Console.WriteLine("--------------------");
Console.WriteLine("m = {0}", m);
double dError = m.MaxDiff(mt);
if (dError > TOLERANCE)
{
Assert.True(false, String.Format("m: error = {0}", dError));
}
Console.WriteLine("v = \n{0}", v);
dError = v.MaxDiff(vt);
if (dError > TOLERANCE)
{
Assert.True(false, String.Format("v: error = {0}", dError));
}
}
public void Normalize(IList<Vector> data)
{
if (data.Count == 0) return;
VectorMeanVarianceAccumulator acc = new VectorMeanVarianceAccumulator(data[0].Count);
foreach (Vector v in data) {
acc.Add(v);
}
Vector mean = acc.Mean;
Vector variance = acc.Variance.Diagonal();
Vector stddev = Vector.Zero(variance.Count);
stddev.SetToFunction(variance, Math.Sqrt);
for (int i = 0; i < stddev.Count; i++) {
if (stddev[i] == 0.0) {
mean[i] = 0.0;
stddev[i] = 1.0;
}
}
foreach (Vector v in data) {
v.SetToDifference(v, mean);
v.SetToRatio(v, stddev);
}
}
/// <summary>
/// Creates a new VectorGaussian estimator of a given dimension
/// </summary>
/// <param name="dimension">The dimension</param>
public VectorGaussianEstimator(int dimension)
{
x = Vector.Zero(dimension);
noiseVariance = new PositiveDefiniteMatrix(dimension, dimension);
mva = new VectorMeanVarianceAccumulator(dimension);
}
