func (classifier *MaxEntClassifier) Predict(instance *data.Instance) data.InstanceOutput {
output := data.InstanceOutput{}
// 当使用NamedFeatures时转化为Features
if instance.NamedFeatures != nil {
if classifier.FeatureDictionary == nil {
return output
}
instance.Features = util.NewSparseVector()
// 第0个feature始终是1
instance.Features.Set(0, 1.0)
for k, v := range instance.NamedFeatures {
id := classifier.FeatureDictionary.TranslateIdFromName(k)
instance.Features.Set(id, v)
}
}
output.LabelDistribution = util.NewVector(classifier.NumLabels)
output.LabelDistribution.Set(0, 1.0)
z := float64(1)
mostPossibleLabel := 0
mostPossibleLabelWeight := float64(1)
for iLabel := 1; iLabel < classifier.NumLabels; iLabel++ {
sum := float64(0)
for _, k := range classifier.Weights.GetValues(iLabel - 1).Keys() {
sum += classifier.Weights.Get(iLabel-1, k) * instance.Features.Get(k)
}
exp := math.Exp(sum)
if exp > mostPossibleLabelWeight {
mostPossibleLabel = iLabel
mostPossibleLabelWeight = exp
}
z += exp
output.LabelDistribution.Set(iLabel, exp)
}
output.LabelDistribution.Scale(1 / z)
output.Label = mostPossibleLabel
if classifier.LabelDictionary != nil {
output.LabelString = classifier.LabelDictionary.GetNameFromId(output.Label)
}
return output
}
// 使用当前训练出的模型对一个样本的输出进行预测
func (classifier *OnlineSGDClassifier) Predict(instance *data.Instance) data.InstanceOutput {
output := data.InstanceOutput{}
predictedLabel := 0
maxWeight := float64(0)
for iLabel := 1; iLabel < classifier.weights.NumLabels()+1; iLabel++ {
sum := float64(0)
for _, k := range instance.Features.Keys() {
sum += classifier.weights.Get(iLabel-1, k) * instance.Features.Get(k)
}
if sum > maxWeight {
predictedLabel = iLabel
maxWeight = sum
}
}
output.Label = predictedLabel
return output
}