Beispiel #1
0
// Train converts the Attributes into equivalently named FloatAttributes,
// leaves FloatAttributes unmodified and processes
// CategoricalAttributes as follows.
//
// If the CategoricalAttribute has two values, one of them is
// designated 0.0 and the other 1.0, and a single identically-named
// FloatAttribute is returned.
//
// If the CategoricalAttribute has more than two (n) values, the Filter
// generates n FloatAttributes and sets each of them if the value's observed.
func (f *FloatConvertFilter) Train() error {
	for _, a := range f.attrs {
		if ac, ok := a.(*base.CategoricalAttribute); ok {
			vals := ac.GetValues()
			if len(vals) <= 2 {
				nAttr := base.NewFloatAttribute(ac.GetName())
				fAttr := base.FilteredAttribute{ac, nAttr}
				f.converted = append(f.converted, fAttr)
				f.twoValuedCategoricalAttributes[a] = true
			} else {
				if _, ok := f.nValuedCategoricalAttributeMap[a]; !ok {
					f.nValuedCategoricalAttributeMap[a] = make(map[uint64]base.Attribute)
				}
				for i := uint64(0); i < uint64(len(vals)); i++ {
					v := vals[i]
					newName := fmt.Sprintf("%s_%s", ac.GetName(), v)
					newAttr := base.NewFloatAttribute(newName)
					fAttr := base.FilteredAttribute{ac, newAttr}
					f.converted = append(f.converted, fAttr)
					f.nValuedCategoricalAttributeMap[a][i] = newAttr
				}
			}
		} else if ab, ok := a.(*base.FloatAttribute); ok {
			fAttr := base.FilteredAttribute{ab, ab}
			f.converted = append(f.converted, fAttr)
		} else if af, ok := a.(*base.BinaryAttribute); ok {
			newAttr := base.NewFloatAttribute(af.GetName())
			fAttr := base.FilteredAttribute{af, newAttr}
			f.converted = append(f.converted, fAttr)
		} else {
			return fmt.Errorf("Unsupported Attribute type: %v", a)
		}
	}
	return nil
}
Beispiel #2
0
func main() {

	// Instances can be read using ParseCsvToInstances
	rawData, err := base.ParseCSVToInstances("../datasets/iris_headers.csv", true)
	if err != nil {
		panic(err)
	}

	// Instances can be printed, and you'll see a human-readable summary
	// if you do so. The first section is a line like
	//     Instances with 150 row(s) and 5 attribute(s)
	//
	// It next prints all the attributes
	//     FloatAttribute(Sepal length)
	//     FloatAttribute(Sepal width)
	//     FloatAttribute(Petal length)
	//     FloatAttribute(Petal width)
	//     CategoricalAttribute([Iris-setosa Iris-versicolor Iris-viriginica])
	// The final attribute has an asterisk (*) printed before it,
	// meaning that it is the class variable. It then prints out up to
	// 30 rows which correspond to those attributes.
	// 	5.10 3.50 1.40 0.20 Iris-setosa
	// 	4.90 3.00 1.40 0.20 Iris-setosa
	fmt.Println(rawData)

	// If two decimal places isn't enough, you can update the
	// Precision field on any FloatAttribute
	if attr, ok := rawData.GetAttr(0).(*base.FloatAttribute); !ok {
		panic("Invalid cast")
	} else {
		attr.Precision = 4
	}
	// Now the first column has more precision
	fmt.Println(rawData)

	// We can update the set of Instances, although the API
	// for doing so is not very sophisticated.
	rawData.SetAttrStr(0, 0, "1.00")
	rawData.SetAttrStr(0, rawData.ClassIndex, "Iris-unusual")
	fmt.Println(rawData)

	// There is a way of creating new Instances from scratch.
	// Inside an Instance, everything's stored as float64
	newData := make([]float64, 2)
	newData[0] = 1.0
	newData[1] = 0.0

	// Let's create some attributes
	attrs := make([]base.Attribute, 2)
	attrs[0] = base.NewFloatAttribute()
	attrs[0].SetName("Arbitrary Float Quantity")
	attrs[1] = new(base.CategoricalAttribute)
	attrs[1].SetName("Class")
	// Insert a standard class
	attrs[1].GetSysValFromString("A")

	// Now let's create the final instances set
	newInst := base.NewInstancesFromRaw(attrs, 1, newData)
	fmt.Println(newInst)
}
Beispiel #3
0
func (m *OneVsAllModel) generateAttributes(from base.FixedDataGrid) map[base.Attribute]base.Attribute {
	attrs := from.AllAttributes()
	classAttrs := from.AllClassAttributes()
	if len(classAttrs) != 1 {
		panic("Only 1 class Attribute is supported!")
	}
	ret := make(map[base.Attribute]base.Attribute)
	for _, a := range attrs {
		ret[a] = a
		for _, b := range classAttrs {
			if a.Equals(b) {
				cur := base.NewFloatAttribute(b.GetName())
				ret[a] = cur
			}
		}
	}
	return ret
}