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
}
// 读入一个训练样本
func (classifier *OnlineSGDClassifier) TrainOnOneInstance(instance *data.Instance) {
if instance.NamedFeatures != nil {
// 将样本中的特征转化为稀疏向量并加入词典
instance.Features = nil
data.ConvertNamedFeatures(instance, classifier.featureDictionary)
}
if instance.Output == nil {
return
} else {
// 将样本中的标注字符串转化为整数ID
if instance.Output.LabelString != "" {
instance.Output.Label =
classifier.labelDictionary.GetIdFromName(
instance.Output.LabelString)
}
}
// 预测并记录
prediction := classifier.Predict(instance)
classifier.evaluator.Evaluate(*instance.Output, prediction)
classifier.instanceDerivative.Clear()
supervised.MaxEntComputeInstanceDerivative(
classifier.weights, instance, classifier.instanceDerivative)
classifier.derivative.Increment(classifier.instanceDerivative, 1.0)
classifier.instancesProcessed++
if classifier.instancesProcessed >= classifier.options.BatchSize {
// 添加正则化项
classifier.derivative.Increment(optimizer.ComputeRegularization(
classifier.weights, classifier.options.Optimizer), 1.0/float64(classifier.options.NumInstancesForEvaluation))
// 根据学习率更新权重
classifier.weights.Increment(
classifier.derivative,
-1*classifier.options.Optimizer.LearningRate/float64(classifier.options.NumInstancesForEvaluation))
// 重置
classifier.derivative.Clear()
classifier.instancesProcessed = 0
}
}
func TestComputeInstanceDerivative(t *testing.T) {
weights := util.NewMatrix(2, 3)
weights.GetValues(0).SetValues([]float64{1, 2, 3})
weights.GetValues(1).SetValues([]float64{3, 4, 5})
de := util.NewMatrix(2, 3)
instance := data.Instance{}
instance.Features = util.NewVector(3)
instance.Features.SetValues([]float64{1, 0.3, 0.4})
instance.Output = &data.InstanceOutput{Label: 0}
MaxEntComputeInstanceDerivative(weights, &instance, de)
util.ExpectNear(t, 0.0322, de.Get(0, 0), 0.0001)
util.ExpectNear(t, 0.0096, de.Get(0, 1), 0.0001)
util.ExpectNear(t, 0.0128, de.Get(0, 2), 0.0001)
util.ExpectNear(t, 0.9658, de.Get(1, 0), 0.0001)
util.ExpectNear(t, 0.2897, de.Get(1, 1), 0.0001)
util.ExpectNear(t, 0.3863, de.Get(1, 2), 0.0001)
instance.Features.SetValues([]float64{1, 0.6, 0.7})
instance.Output.Label = 1
MaxEntComputeInstanceDerivative(weights, &instance, de)
util.ExpectNear(t, -0.9900, de.Get(0, 0), 0.0001)
util.ExpectNear(t, -0.5940, de.Get(0, 1), 0.0001)
util.ExpectNear(t, -0.6930, de.Get(0, 2), 0.0001)
util.ExpectNear(t, 0.9899, de.Get(1, 0), 0.0001)
util.ExpectNear(t, 0.5939, de.Get(1, 1), 0.0001)
util.ExpectNear(t, 0.6929, de.Get(1, 2), 0.0001)
instance.Features.SetValues([]float64{1, 0.4, 0.2})
instance.Output.Label = 2
MaxEntComputeInstanceDerivative(weights, &instance, de)
util.ExpectNear(t, 0.0390, de.Get(0, 0), 0.0001)
util.ExpectNear(t, 0.0156, de.Get(0, 1), 0.0001)
util.ExpectNear(t, 0.0078, de.Get(0, 2), 0.0001)
util.ExpectNear(t, -0.0425, de.Get(1, 0), 0.0001)
util.ExpectNear(t, -0.0170, de.Get(1, 1), 0.0001)
util.ExpectNear(t, -0.0085, de.Get(1, 2), 0.0001)
}
func LoadLibSVMDataset(path string, usingSparseRepresentation bool) data.Dataset {
log.Print("载入libsvm格式文件", path)
content, err := ioutil.ReadFile(path)
if err != nil {
log.Fatalf("无法打开文件\"%v\"，错误提示：%v\n", path, err)
}
lines := strings.Split(string(content), "\n")
minFeature := 10000
maxFeature := 0
labels := make(map[string]int)
labelIndex := 0
for _, l := range lines {
if l == "" {
continue
}
fields := strings.Split(l, " ")
_, ok := labels[fields[0]]
if !ok {
labels[fields[0]] = labelIndex
labelIndex++
}
for i := 1; i < len(fields); i++ {
if fields[i] == "" {
continue
}
fs := strings.Split(fields[i], ":")
fid, _ := strconv.Atoi(fs[0])
if fid > maxFeature {
maxFeature = fid
}
if fid < minFeature {
minFeature = fid
}
}
}
if minFeature == 0 || maxFeature < 2 {
log.Fatal("文件输入格式不合法")
}
log.Printf("feature 数目 %d", maxFeature)
log.Printf("label 数目 %d", len(labels))
set := data.NewInmemDataset()
for _, l := range lines {
if l == "" {
continue
}
fields := strings.Split(l, " ")
instance := new(data.Instance)
instance.Output = &data.InstanceOutput{
Label: labels[fields[0]],
LabelString: fields[0],
}
if usingSparseRepresentation {
instance.NamedFeatures = make(map[string]float64)
} else {
instance.Features = util.NewVector(maxFeature + 1)
}
// 常数项
if !usingSparseRepresentation {
instance.Features.Set(0, 1)
}
for i := 1; i < len(fields); i++ {
if fields[i] == "" {
continue
}
fs := strings.Split(fields[i], ":")
fid, _ := strconv.Atoi(fs[0])
value, _ := strconv.ParseFloat(fs[1], 64)
if usingSparseRepresentation {
instance.NamedFeatures[fs[0]] = value
} else {
instance.Features.Set(fid, value)
}
}
set.AddInstance(instance)
}
set.Finalize()
log.Print("载入数据样本数目 ", set.NumInstances())
return set
}
func TestTrain(t *testing.T) {
set := data.NewInmemDataset()
instance1 := new(data.Instance)
instance1.Features = util.NewVector(4)
instance1.Features.SetValues([]float64{1, 1, 1, 3})
instance1.Output = &data.InstanceOutput{Label: 0}
set.AddInstance(instance1)
instance2 := new(data.Instance)
instance2.Features = util.NewVector(4)
instance2.Features.SetValues([]float64{1, 3, 1, 5})
instance2.Output = &data.InstanceOutput{Label: 0}
set.AddInstance(instance2)
instance3 := new(data.Instance)
instance3.Features = util.NewVector(4)
instance3.Features.SetValues([]float64{1, 3, 4, 7})
instance3.Output = &data.InstanceOutput{Label: 1}
set.AddInstance(instance3)
instance4 := new(data.Instance)
instance4.Features = util.NewVector(4)
instance4.Features.SetValues([]float64{1, 2, 8, 6})
instance4.Output = &data.InstanceOutput{Label: 1}
set.AddInstance(instance4)
set.Finalize()
gdTrainerOptions := TrainerOptions{
Optimizer: optimizer.OptimizerOptions{
OptimizerName: "gd",
RegularizationScheme: 2,
RegularizationFactor: 1,
LearningRate: 0.1,
ConvergingDeltaWeight: 1e-6,
ConvergingSteps: 3,
MaxIterations: 0,
GDBatchSize: 0, // full-bath
},
}
gdTrainer := NewMaxEntClassifierTrainer(gdTrainerOptions)
lbfgsTrainerOptions := TrainerOptions{
Optimizer: optimizer.OptimizerOptions{
OptimizerName: "lbfgs",
RegularizationScheme: 2,
RegularizationFactor: 1,
LearningRate: 1,
ConvergingDeltaWeight: 1e-6,
ConvergingSteps: 3,
MaxIterations: 0,
},
}
lbfgsTrainer := NewMaxEntClassifierTrainer(lbfgsTrainerOptions)
lbfgsTrainer.Train(set)
gdTrainer.Train(set).Write("test.mlf")
model := LoadModel("test.mlf")
util.Expect(t, "0", model.Predict(instance1).Label)
util.Expect(t, "0", model.Predict(instance2).Label)
util.Expect(t, "1", model.Predict(instance3).Label)
util.Expect(t, "1", model.Predict(instance4).Label)
}