// NewModel creates a new Gaussian mixture model.
func NewModel(dim, numComponents int, options ...Option) *Model {
gmm := &Model{
ModelName: "GMM", // default name
ModelDim: dim,
NComponents: numComponents,
Diag: true,
tmpProbs: make([]float64, numComponents),
}
gmm.Type = reflect.TypeOf(*gmm).String()
// Set options.
for _, option := range options {
option(gmm)
}
if len(gmm.PosteriorSum) == 0 {
gmm.PosteriorSum = make([]float64, gmm.NComponents)
}
// Create components if not provided.
if len(gmm.Components) == 0 {
gmm.Components = make([]*gaussian.Model, numComponents, numComponents)
for i := range gmm.Components {
cname := componentName(gmm.ModelName, i, gmm.NComponents)
gmm.Components[i] = gaussian.NewModel(gmm.ModelDim, gaussian.Name(cname))
}
}
// Initialize weights.
// Caller may pass weight, log(weights), or no weights.
switch {
case len(gmm.LogWeights) > 0 && len(gmm.Weights) > 0:
glog.Fatal("options not allowed: provide only one of LogWeights or Weights")
case len(gmm.LogWeights) == 0 && len(gmm.Weights) == 0:
gmm.LogWeights = make([]float64, numComponents)
logw := -math.Log(float64(gmm.NComponents))
floatx.Apply(floatx.SetValueFunc(logw), gmm.LogWeights, nil)
gmm.Weights = make([]float64, gmm.NComponents)
floatx.Exp(gmm.Weights, gmm.LogWeights)
glog.Infof("init weights with equal values: %.6f", gmm.Weights[0])
case len(gmm.LogWeights) > 0:
gmm.Weights = make([]float64, gmm.NComponents)
floatx.Exp(gmm.Weights, gmm.LogWeights)
case len(gmm.Weights) > 0:
gmm.LogWeights = make([]float64, numComponents)
floatx.Log(gmm.LogWeights, gmm.Weights)
}
return gmm
}
// Estimate computes model parameters using sufficient statistics.
func (gmm *Model) UpdateOne(o model.Obs, w float64) {
obs, _, _ := model.ObsToF64(o)
maxProb := gmm.logProbInternal(obs, gmm.tmpProbs)
gmm.Likelihood += maxProb
floatx.Apply(floatx.AddScalarFunc(-maxProb+math.Log(w)), gmm.tmpProbs, nil)
// Compute posterior probabilities.
floatx.Exp(gmm.tmpProbs, gmm.tmpProbs)
// Update posterior sum, needed to compute mixture weights.
floats.Add(gmm.PosteriorSum, gmm.tmpProbs)
// Update Gaussian components.
for i, c := range gmm.Components {
c.UpdateOne(o, gmm.tmpProbs[i])
}
// Count number of observations.
gmm.NSamples += w
}
