// 将instance中的NamedFeatures域转化为Features域
// 如果instance.Features不为nil则不转化
func ConvertNamedFeatures(instance *Instance, dict *dictionary.Dictionary) {
if instance.Features != nil {
return
}
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 := dict.GetIdFromName(k)
instance.Features.Set(id, v)
}
}
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
}
func TestInMemDataset(t *testing.T) {
set := NewInmemDataset()
instance1 := new(Instance)
instance1.Features = util.NewVector(3)
instance1.Features.SetValues([]float64{1, 2, 3})
instance1.Output = &InstanceOutput{Label: 1}
util.Expect(t, "true", set.AddInstance(instance1))
instance2 := new(Instance)
instance2.Features = util.NewVector(3)
instance2.Features.SetValues([]float64{3, 4, 5})
instance2.Output = &InstanceOutput{Label: 2}
util.Expect(t, "true", set.AddInstance(instance2))
instance3 := new(Instance)
instance3.Features = util.NewSparseVector()
instance3.Features.SetValues([]float64{3, 4, 5})
instance3.Output = &InstanceOutput{Label: 0}
util.Expect(t, "false", set.AddInstance(instance3))
instance4 := new(Instance)
instance4.Features = util.NewVector(4)
instance4.Features.SetValues([]float64{3, 4, 5, 6})
instance4.Output = &InstanceOutput{Label: 4}
util.Expect(t, "false", set.AddInstance(instance4))
instance5 := new(Instance)
instance5.Features = util.NewVector(3)
instance5.Features.SetValues([]float64{3, 5, 5})
util.Expect(t, "false", set.AddInstance(instance5))
set.Finalize()
// 检查数据集选项
util.Expect(t, "false", set.GetOptions().FeatureIsSparse)
util.Expect(t, "3", set.GetOptions().FeatureDimension)
util.Expect(t, "true", set.GetOptions().IsSupervisedLearning)
util.Expect(t, "3", set.GetOptions().NumLabels)
util.Expect(t, "2", set.NumInstances())
iter := set.CreateIterator()
iter.Start()
util.Expect(t, "false", iter.End())
util.Expect(t, "1", iter.GetInstance().Features.Get(0))
util.Expect(t, "2", iter.GetInstance().Features.Get(1))
util.Expect(t, "3", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "false", iter.End())
util.Expect(t, "3", iter.GetInstance().Features.Get(0))
util.Expect(t, "4", iter.GetInstance().Features.Get(1))
util.Expect(t, "5", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
iter = set.CreateIterator()
iter.Start()
iter.Skip(2)
util.Expect(t, "true", iter.End())
util.Expect(t, "2", set.NumInstances())
}
