func TestDictionaryJSON(t *testing.T) {
dict := NewDictionary(1)
dict.GetIdFromName("f1")
dict.GetIdFromName("f2")
dict.GetIdFromName("f3")
dict.GetIdFromName("f4")
dictJson, _ := json.Marshal(dict)
var newDict Dictionary
json.Unmarshal(dictJson, &newDict)
util.Expect(t, "1", newDict.GetIdFromName("f1"))
util.Expect(t, "2", newDict.GetIdFromName("f2"))
util.Expect(t, "3", newDict.GetIdFromName("f3"))
util.Expect(t, "4", newDict.GetIdFromName("f4"))
util.Expect(t, "f1", newDict.GetNameFromId(1))
util.Expect(t, "f2", newDict.GetNameFromId(2))
util.Expect(t, "f3", newDict.GetNameFromId(3))
util.Expect(t, "f4", newDict.GetNameFromId(4))
}
func TestSkipIterator(t *testing.T) {
set := NewInmemDataset()
instance1 := new(Instance)
instance1.Features = util.NewVector(3)
instance1.Features.SetValues([]float64{1, 2, 3})
util.Expect(t, "true", set.AddInstance(instance1))
instance2 := new(Instance)
instance2.Features = util.NewVector(3)
instance2.Features.SetValues([]float64{3, 4, 5})
util.Expect(t, "true", set.AddInstance(instance2))
instance3 := new(Instance)
instance3.Features = util.NewVector(3)
instance3.Features.SetValues([]float64{7, 8, 9})
util.Expect(t, "true", set.AddInstance(instance3))
instance4 := new(Instance)
instance4.Features = util.NewVector(3)
instance4.Features.SetValues([]float64{30, 40, 50})
util.Expect(t, "true", set.AddInstance(instance4))
instance5 := new(Instance)
instance5.Features = util.NewVector(3)
instance5.Features.SetValues([]float64{70, 80, 90})
util.Expect(t, "true", set.AddInstance(instance5))
instance6 := new(Instance)
instance6.Features = util.NewVector(3)
instance6.Features.SetValues([]float64{31, 41, 51})
util.Expect(t, "true", set.AddInstance(instance6))
set.Finalize()
iter := NewSkipIterator(set, []int{0, 4})
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, "70", iter.GetInstance().Features.Get(0))
util.Expect(t, "80", iter.GetInstance().Features.Get(1))
util.Expect(t, "90", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
iter = NewSkipIterator(set, []int{3, 1})
iter.Start()
util.Expect(t, "false", iter.End())
util.Expect(t, "30", iter.GetInstance().Features.Get(0))
util.Expect(t, "40", iter.GetInstance().Features.Get(1))
util.Expect(t, "50", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
iter = NewSkipIterator(set, []int{1, 2, 1})
iter.Start()
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, "false", iter.End())
util.Expect(t, "30", iter.GetInstance().Features.Get(0))
util.Expect(t, "40", iter.GetInstance().Features.Get(1))
util.Expect(t, "50", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "false", iter.End())
util.Expect(t, "31", iter.GetInstance().Features.Get(0))
util.Expect(t, "41", iter.GetInstance().Features.Get(1))
util.Expect(t, "51", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
}
func TestSkipDataset(t *testing.T) {
set := NewInmemDataset()
instance1 := new(Instance)
instance1.Features = util.NewVector(3)
instance1.Features.SetValues([]float64{1, 2, 3})
util.Expect(t, "true", set.AddInstance(instance1))
instance2 := new(Instance)
instance2.Features = util.NewVector(3)
instance2.Features.SetValues([]float64{3, 4, 5})
util.Expect(t, "true", set.AddInstance(instance2))
instance3 := new(Instance)
instance3.Features = util.NewVector(3)
instance3.Features.SetValues([]float64{7, 8, 9})
util.Expect(t, "true", set.AddInstance(instance3))
instance4 := new(Instance)
instance4.Features = util.NewVector(3)
instance4.Features.SetValues([]float64{30, 40, 50})
util.Expect(t, "true", set.AddInstance(instance4))
instance5 := new(Instance)
instance5.Features = util.NewVector(3)
instance5.Features.SetValues([]float64{70, 80, 90})
util.Expect(t, "true", set.AddInstance(instance5))
instance6 := new(Instance)
instance6.Features = util.NewVector(3)
instance6.Features.SetValues([]float64{31, 41, 51})
util.Expect(t, "true", set.AddInstance(instance6))
set.Finalize()
buckets := []SkipBucket{}
buckets = append(buckets, SkipBucket{true, 0})
buckets = append(buckets, SkipBucket{false, 1})
buckets = append(buckets, SkipBucket{true, 3})
ss := NewSkipDataset(set, buckets)
util.Expect(t, "2", ss.NumInstances())
iter := ss.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, "70", iter.GetInstance().Features.Get(0))
util.Expect(t, "80", iter.GetInstance().Features.Get(1))
util.Expect(t, "90", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
buckets = []SkipBucket{}
buckets = append(buckets, SkipBucket{true, 3})
buckets = append(buckets, SkipBucket{false, 1})
ss = NewSkipDataset(set, buckets)
util.Expect(t, "1", ss.NumInstances())
iter = ss.CreateIterator()
iter.Start()
util.Expect(t, "false", iter.End())
util.Expect(t, "30", iter.GetInstance().Features.Get(0))
util.Expect(t, "40", iter.GetInstance().Features.Get(1))
util.Expect(t, "50", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
buckets = []SkipBucket{}
buckets = append(buckets, SkipBucket{true, 1})
buckets = append(buckets, SkipBucket{false, 1})
buckets = append(buckets, SkipBucket{true, 1})
buckets = append(buckets, SkipBucket{false, 1})
ss = NewSkipDataset(set, buckets)
util.Expect(t, "3", ss.NumInstances())
iter = ss.CreateIterator()
iter.Start()
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, "false", iter.End())
util.Expect(t, "30", iter.GetInstance().Features.Get(0))
util.Expect(t, "40", iter.GetInstance().Features.Get(1))
util.Expect(t, "50", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "false", iter.End())
util.Expect(t, "31", iter.GetInstance().Features.Get(0))
util.Expect(t, "41", iter.GetInstance().Features.Get(1))
util.Expect(t, "51", iter.GetInstance().Features.Get(2))
iter.Next()
util.Expect(t, "true", iter.End())
}
func TestDictionary(t *testing.T) {
dict := NewDictionary(1)
util.Expect(t, "1", dict.GetIdFromName("feature1"))
util.Expect(t, "2", dict.GetIdFromName("feature2"))
util.Expect(t, "3", dict.GetIdFromName("feature3"))
util.Expect(t, "2", dict.GetIdFromName("feature2"))
util.Expect(t, "3", dict.GetIdFromName("feature3"))
util.Expect(t, "1", dict.GetIdFromName("feature1"))
util.Expect(t, "4", dict.GetIdFromName("feature4"))
util.Expect(t, "", dict.GetNameFromId(0))
util.Expect(t, "feature1", dict.GetNameFromId(1))
util.Expect(t, "feature2", dict.GetNameFromId(2))
util.Expect(t, "feature3", dict.GetNameFromId(3))
util.Expect(t, "feature4", dict.GetNameFromId(4))
util.Expect(t, "", dict.GetNameFromId(5))
}
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)
}
func TestTrainWithNamedFeatures(t *testing.T) {
set := data.NewInmemDataset()
instance1 := new(data.Instance)
instance1.NamedFeatures = map[string]float64{
"1": 1,
"2": 1,
"3": 1,
"4": 3,
}
instance1.Output = &data.InstanceOutput{Label: 0}
set.AddInstance(instance1)
instance2 := new(data.Instance)
instance2.NamedFeatures = map[string]float64{
"1": 1,
"2": 3,
"3": 1,
"4": 5,
}
instance2.Output = &data.InstanceOutput{Label: 0}
set.AddInstance(instance2)
instance3 := new(data.Instance)
instance3.NamedFeatures = map[string]float64{
"1": 1,
"2": 3,
"3": 4,
"4": 7,
}
instance3.Output = &data.InstanceOutput{Label: 1}
set.AddInstance(instance3)
instance4 := new(data.Instance)
instance4.NamedFeatures = map[string]float64{
"1": 1,
"2": 2,
"3": 8,
"4": 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)
}
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())
}
func TestLibsvmLoader(t *testing.T) {
set := LoadLibSVMDataset("test.txt", false)
util.Expect(t, "10", set.NumInstances())
util.Expect(t, "45", set.GetOptions().FeatureDimension)
util.Expect(t, "2", set.GetOptions().NumLabels)
}
