Golang filters.NewChiMergeFilter函数代码示例

func main() {

	var tree base.Classifier

	rand.Seed(44111342)

	// Load in the iris dataset
	iris, err := base.ParseCSVToInstances("/home/kralli/go/src/github.com/sjwhitworth/golearn/examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	// Discretise the iris dataset with Chi-Merge
	filt := filters.NewChiMergeFilter(iris, 0.999)
	for _, a := range base.NonClassFloatAttributes(iris) {
		filt.AddAttribute(a)
	}
	filt.Train()
	irisf := base.NewLazilyFilteredInstances(iris, filt)

	// Create a 60-40 training-test split
	//testData
	trainData, _ := base.InstancesTrainTestSplit(iris, 0.60)

	findBestSplit(trainData)

	//fmt.Println(trainData)
	//fmt.Println(testData)

	fmt.Println(tree)
	fmt.Println(irisf)
}

func BenchmarkBaggingRandomForestPredict(t *testing.B) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		t.Fatal("Unable to parse CSV to instances: %s", err.Error())
	}

	rand.Seed(time.Now().UnixNano())
	filt := filters.NewChiMergeFilter(inst, 0.90)
	for _, a := range base.NonClassFloatAttributes(inst) {
		filt.AddAttribute(a)
	}
	filt.Train()
	instf := base.NewLazilyFilteredInstances(inst, filt)

	rf := new(BaggedModel)
	for i := 0; i < 10; i++ {
		rf.AddModel(trees.NewRandomTree(2))
	}

	rf.Fit(instf)
	t.ResetTimer()
	for i := 0; i < 20; i++ {
		rf.Predict(instf)
	}
}

func TestPruning(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}
	trainData, testData := base.InstancesTrainTestSplit(inst, 0.6)
	filt := filters.NewChiMergeFilter(inst, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	fmt.Println(testData)
	filt.Run(testData)
	filt.Run(trainData)
	root := NewRandomTree(2)
	fittrainData, fittestData := base.InstancesTrainTestSplit(trainData, 0.6)
	root.Fit(fittrainData)
	root.Prune(fittestData)
	fmt.Println(root)
	predictions := root.Predict(testData)
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(testData, predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetMacroPrecision(confusionMat))
	fmt.Println(eval.GetMacroRecall(confusionMat))
	fmt.Println(eval.GetSummary(confusionMat))
}

func main() {

	var tree base.Classifier

	rand.Seed(time.Now().UTC().UnixNano())

	// Load in the iris dataset
	iris, err := base.ParseCSVToInstances("../datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	// Discretise the iris dataset with Chi-Merge
	filt := filters.NewChiMergeFilter(iris, 0.99)
	filt.AddAllNumericAttributes()
	filt.Build()
	filt.Run(iris)

	// Create a 60-40 training-test split
	insts := base.InstancesTrainTestSplit(iris, 0.60)

	//
	// First up, use ID3
	//
	tree = trees.NewID3DecisionTree(0.6)
	// (Parameter controls train-prune split.)

	// Train the ID3 tree
	tree.Fit(insts[0])

	// Generate predictions
	predictions := tree.Predict(insts[1])

	// Evaluate
	fmt.Println("ID3 Performance")
	cf := eval.GetConfusionMatrix(insts[1], predictions)
	fmt.Println(eval.GetSummary(cf))

	//
	// Next up, Random Trees
	//

	// Consider two randomly-chosen attributes
	tree = trees.NewRandomTree(2)
	tree.Fit(insts[0])
	predictions = tree.Predict(insts[1])
	fmt.Println("RandomTree Performance")
	cf = eval.GetConfusionMatrix(insts[1], predictions)
	fmt.Println(eval.GetSummary(cf))

	//
	// Finally, Random Forests
	//
	tree = ensemble.NewRandomForest(100, 3)
	tree.Fit(insts[0])
	predictions = tree.Predict(insts[1])
	fmt.Println("RandomForest Performance")
	cf = eval.GetConfusionMatrix(insts[1], predictions)
	fmt.Println(eval.GetSummary(cf))
}

func TestRandomForest1(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	rand.Seed(time.Now().UnixNano())
	trainData, testData := base.InstancesTrainTestSplit(inst, 0.6)
	filt := filters.NewChiMergeFilter(inst, 0.90)
	for _, a := range base.NonClassFloatAttributes(inst) {
		filt.AddAttribute(a)
	}
	filt.Train()
	trainDataf := base.NewLazilyFilteredInstances(trainData, filt)
	testDataf := base.NewLazilyFilteredInstances(testData, filt)
	rf := new(BaggedModel)
	for i := 0; i < 10; i++ {
		rf.AddModel(trees.NewRandomTree(2))
	}
	rf.Fit(trainDataf)
	fmt.Println(rf)
	predictions := rf.Predict(testDataf)
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(testDataf, predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetMacroPrecision(confusionMat))
	fmt.Println(eval.GetMacroRecall(confusionMat))
	fmt.Println(eval.GetSummary(confusionMat))
}

func TestRandomForest1(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	rand.Seed(time.Now().UnixNano())
	insts := base.InstancesTrainTestSplit(inst, 0.6)
	filt := filters.NewChiMergeFilter(inst, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	filt.Run(insts[1])
	filt.Run(insts[0])
	rf := new(BaggedModel)
	for i := 0; i < 10; i++ {
		rf.AddModel(trees.NewRandomTree(2))
	}
	rf.Fit(insts[0])
	fmt.Println(rf)
	predictions := rf.Predict(insts[1])
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(insts[1], predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetMacroPrecision(confusionMat))
	fmt.Println(eval.GetMacroRecall(confusionMat))
	fmt.Println(eval.GetSummary(confusionMat))
}

func TestRandomTree(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	filt := filters.NewChiMergeFilter(inst, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	filt.Run(inst)
	fmt.Println(inst)
	r := new(RandomTreeRuleGenerator)
	r.Attributes = 2
	root := InferID3Tree(inst, r)
	fmt.Println(root)
}

func TestRandomTreeClassificationAfterDiscretisation(t *testing.T) {
	Convey("Predictions on filtered data with a Random Tree", t, func() {
		instances, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
		So(err, ShouldBeNil)

		trainData, testData := base.InstancesTrainTestSplit(instances, 0.6)

		filter := filters.NewChiMergeFilter(instances, 0.9)
		for _, a := range base.NonClassFloatAttributes(instances) {
			filter.AddAttribute(a)
		}
		filter.Train()
		filteredTrainData := base.NewLazilyFilteredInstances(trainData, filter)
		filteredTestData := base.NewLazilyFilteredInstances(testData, filter)
		verifyTreeClassification(filteredTrainData, filteredTestData)
	})
}

func TestRandomForest(t *testing.T) {
	Convey("Given a valid CSV file", t, func() {
		inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
		So(err, ShouldBeNil)

		Convey("When Chi-Merge filtering the data", func() {
			filt := filters.NewChiMergeFilter(inst, 0.90)
			for _, a := range base.NonClassFloatAttributes(inst) {
				filt.AddAttribute(a)
			}
			filt.Train()
			instf := base.NewLazilyFilteredInstances(inst, filt)

			Convey("Splitting the data into test and training sets", func() {
				trainData, testData := base.InstancesTrainTestSplit(instf, 0.60)

				Convey("Fitting and predicting with a Random Forest", func() {
					rf := NewRandomForest(10, 3)
					err = rf.Fit(trainData)
					So(err, ShouldBeNil)

					predictions, err := rf.Predict(testData)
					So(err, ShouldBeNil)

					confusionMat, err := evaluation.GetConfusionMatrix(testData, predictions)
					So(err, ShouldBeNil)

					Convey("Predictions should be somewhat accurate", func() {
						So(evaluation.GetAccuracy(confusionMat), ShouldBeGreaterThan, 0.35)
					})
				})
			})
		})

		Convey("Fitting with a Random Forest with too many features compared to the data", func() {
			rf := NewRandomForest(10, len(base.NonClassAttributes(inst))+1)
			err = rf.Fit(inst)

			Convey("Should return an error", func() {
				So(err, ShouldNotBeNil)
			})
		})
	})
}

func TestRandomForest1(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}
	trainData, testData := base.InstancesTrainTestSplit(inst, 0.60)
	filt := filters.NewChiMergeFilter(trainData, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	filt.Run(testData)
	filt.Run(trainData)
	rf := NewRandomForest(10, 3)
	rf.Fit(trainData)
	predictions := rf.Predict(testData)
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(testData, predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetSummary(confusionMat))
}

func BenchmarkBaggingRandomForestFit(testEnv *testing.B) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	rand.Seed(time.Now().UnixNano())
	filt := filters.NewChiMergeFilter(inst, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	filt.Run(inst)
	rf := new(BaggedModel)
	for i := 0; i < 10; i++ {
		rf.AddModel(trees.NewRandomTree(2))
	}
	testEnv.ResetTimer()
	for i := 0; i < 20; i++ {
		rf.Fit(inst)
	}
}

func TestBaggedModelRandomForest(t *testing.T) {
	Convey("Given data", t, func() {
		inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
		So(err, ShouldBeNil)

		Convey("Splitting the data into training and test data", func() {
			trainData, testData := base.InstancesTrainTestSplit(inst, 0.6)

			Convey("Filtering the split datasets", func() {
				rand.Seed(time.Now().UnixNano())
				filt := filters.NewChiMergeFilter(inst, 0.90)
				for _, a := range base.NonClassFloatAttributes(inst) {
					filt.AddAttribute(a)
				}
				filt.Train()
				trainDataf := base.NewLazilyFilteredInstances(trainData, filt)
				testDataf := base.NewLazilyFilteredInstances(testData, filt)

				Convey("Fitting and Predicting with a Bagged Model of 10 Random Trees", func() {
					rf := new(BaggedModel)
					for i := 0; i < 10; i++ {
						rf.AddModel(trees.NewRandomTree(2))
					}

					rf.Fit(trainDataf)
					predictions := rf.Predict(testDataf)

					confusionMat, err := evaluation.GetConfusionMatrix(testDataf, predictions)
					So(err, ShouldBeNil)

					Convey("Predictions are somewhat accurate", func() {
						So(evaluation.GetAccuracy(confusionMat), ShouldBeGreaterThan, 0.5)
					})
				})
			})
		})
	})
}

func TestRandomForest1(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	filt := filters.NewChiMergeFilter(inst, 0.90)
	for _, a := range base.NonClassFloatAttributes(inst) {
		filt.AddAttribute(a)
	}
	filt.Train()
	instf := base.NewLazilyFilteredInstances(inst, filt)

	trainData, testData := base.InstancesTrainTestSplit(instf, 0.60)

	rf := NewRandomForest(10, 3)
	rf.Fit(trainData)
	predictions := rf.Predict(testData)
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(testData, predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetSummary(confusionMat))
}

func TestRandomTreeClassification2(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}
	insts := base.InstancesTrainTestSplit(inst, 0.4)
	filt := filters.NewChiMergeFilter(inst, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	fmt.Println(insts[1])
	filt.Run(insts[1])
	filt.Run(insts[0])
	root := NewRandomTree(2)
	root.Fit(insts[0])
	fmt.Println(root)
	predictions := root.Predict(insts[1])
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(insts[1], predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetMacroPrecision(confusionMat))
	fmt.Println(eval.GetMacroRecall(confusionMat))
	fmt.Println(eval.GetSummary(confusionMat))
}

func TestRandomTreeClassification(testEnv *testing.T) {
	inst, err := base.ParseCSVToInstances("../examples/datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}
	trainData, testData := base.InstancesTrainTestSplit(inst, 0.6)
	filt := filters.NewChiMergeFilter(inst, 0.90)
	filt.AddAllNumericAttributes()
	filt.Build()
	filt.Run(trainData)
	filt.Run(testData)
	fmt.Println(inst)
	r := new(RandomTreeRuleGenerator)
	r.Attributes = 2
	root := InferID3Tree(trainData, r)
	fmt.Println(root)
	predictions := root.Predict(testData)
	fmt.Println(predictions)
	confusionMat := eval.GetConfusionMatrix(testData, predictions)
	fmt.Println(confusionMat)
	fmt.Println(eval.GetMacroPrecision(confusionMat))
	fmt.Println(eval.GetMacroRecall(confusionMat))
	fmt.Println(eval.GetSummary(confusionMat))
}