/// <summary>
/// Fits the underlying distribution to a given set of observations.
/// </summary>
///
/// <param name="observations">The array of observations to fit the model against. The array
/// elements can be either of type double (for univariate data) or
/// type double[] (for multivariate data).</param>
/// <param name="weights">The weight vector containing the weight for each of the samples.</param>
/// <param name="options">Optional arguments which may be used during fitting, such
/// as regularization constants and additional parameters.</param>
///
public void Fit(double[] observations, double[] weights, MixtureOptions options)
{
var pdf = new IFittableDistribution <double> [coefficients.Length];
for (int i = 0; i < components.Length; i++)
{
pdf[i] = (IFittableDistribution <double>)components[i];
}
bool log = (options != null && options.Logarithm);
if (log)
{
if (weights != null)
{
throw new ArgumentException("The model fitting algorithm does not"
+ " currently support different weights when the logarithm option"
+ " is enabled. To avoid this exception, pass 'null' as the second"
+ " parameter's value when calling this method.");
}
var em = new LogExpectationMaximization <double>(coefficients, pdf);
if (options != null)
{
em.InnerOptions = options.InnerOptions;
em.Convergence.Iterations = options.Iterations;
em.Convergence.Tolerance = options.Threshold;
}
em.Compute(observations);
}
else
{
var em = new ExpectationMaximization <double>(coefficients, pdf);
if (options != null)
{
em.InnerOptions = options.InnerOptions;
em.Convergence.Iterations = options.Iterations;
em.Convergence.Tolerance = options.Threshold;
}
em.Compute(observations, weights);
}
for (int i = 0; i < components.Length; i++)
{
cache[i] = components[i] = (T)pdf[i];
}
this.initialize();
}
public void Learn(List <DataElement> data)
{
kMeans _kMeans = new kMeans(d);
_gaussianDistributions = _kMeans.GetGroupRepresentatives(data, threshold);
List <double[][]> mfccVectors = new List <double[][]>();
for (int i = 0; i < data.Count; i++)
{
mfccVectors.Add(data[i].MfccCoefficients);
}
em = new ExpectationMaximization(_gaussianDistributions.ToArray(), mfccVectors);
int iterations = 0;
while (iterations < maxIterations)
{
List <DataElement> prevMeans = new List <DataElement>();
foreach (var gd in _gaussianDistributions)
{
prevMeans.Add(new DataElement(gd.Mean));
}
em.Compute();
List <DataElement> currMeans = new List <DataElement>();
foreach (var gd in _gaussianDistributions)
{
currMeans.Add(new DataElement(gd.Mean));
}
List <double> meansDistances = MathHelper.CountMeansDistances(prevMeans, currMeans);
if (!MathHelper.meansDistancesChanged(threshold, meansDistances))
{
break;
}
iterations++;
}
AfterLearning = true;
}
/// <summary>
/// Computes the log-likelihood of the distribution
/// for a given set of observations.
/// </summary>
///
public double LogLikelihood(double[] observations)
{
return(ExpectationMaximization <double> .LogLikelihood(coefficients, cache, observations));
}
/// <summary>
/// Computes the log-likelihood of the distribution
/// for a given set of observations.
/// </summary>
///
public double LogLikelihood(double[][] observations, double[] weights)
{
return(ExpectationMaximization <double[]> .LogLikelihood(coefficients, cache,
observations, weights, weights.Sum()));
}
