// GenerateSplitAttribute returns the best attribute out of those randomly chosen
// which maximises Information Gain
func (r *RandomTreeRuleGenerator) GenerateSplitAttribute(f *base.Instances) base.Attribute {
// First step is to generate the random attributes that we'll consider
maximumAttribute := f.GetAttributeCount()
consideredAttributes := make([]int, r.Attributes)
attrCounter := 0
for {
if len(consideredAttributes) >= r.Attributes {
break
}
selectedAttribute := rand.Intn(maximumAttribute)
fmt.Println(selectedAttribute, attrCounter, consideredAttributes, len(consideredAttributes))
if selectedAttribute != f.ClassIndex {
matched := false
for _, a := range consideredAttributes {
if a == selectedAttribute {
matched = true
break
}
}
if matched {
continue
}
consideredAttributes = append(consideredAttributes, selectedAttribute)
attrCounter++
}
}
return r.internalRule.GetSplitAttributeFromSelection(consideredAttributes, f)
}
func (lr *LinearRegression) Fit(inst *base.Instances) error {
if inst.Rows < inst.GetAttributeCount() {
return NotEnoughDataError
}
// Split into two matrices, observed results (dependent variable y)
// and the explanatory variables (X) - see http://en.wikipedia.org/wiki/Linear_regression
observed := mat64.NewDense(inst.Rows, 1, nil)
explVariables := mat64.NewDense(inst.Rows, inst.GetAttributeCount(), nil)
for i := 0; i < inst.Rows; i++ {
observed.Set(i, 0, inst.Get(i, inst.ClassIndex)) // Set observed data
for j := 0; j < inst.GetAttributeCount(); j++ {
if j == 0 {
// Set intercepts to 1.0
// Could / should be done better: http://www.theanalysisfactor.com/interpret-the-intercept/
explVariables.Set(i, 0, 1.0)
} else {
explVariables.Set(i, j, inst.Get(i, j-1))
}
}
}
n := inst.GetAttributeCount()
qr := mat64.QR(explVariables)
q := qr.Q()
reg := qr.R()
var transposed, qty mat64.Dense
transposed.TCopy(q)
qty.Mul(&transposed, observed)
regressionCoefficients := make([]float64, n)
for i := n - 1; i >= 0; i-- {
regressionCoefficients[i] = qty.At(i, 0)
for j := i + 1; j < n; j++ {
regressionCoefficients[i] -= regressionCoefficients[j] * reg.At(i, j)
}
regressionCoefficients[i] /= reg.At(i, i)
}
lr.disturbance = regressionCoefficients[0]
lr.regressionCoefficients = regressionCoefficients[1:]
lr.fitted = true
return nil
}
// InferID3Tree builds a decision tree using a RuleGenerator
// from a set of Instances (implements the ID3 algorithm)
func InferID3Tree(from *base.Instances, with RuleGenerator) *DecisionTreeNode {
// Count the number of classes at this node
classes := from.CountClassValues()
// If there's only one class, return a DecisionTreeLeaf with
// the only class available
if len(classes) == 1 {
maxClass := ""
for i := range classes {
maxClass = i
}
ret := &DecisionTreeNode{
LeafNode,
nil,
nil,
classes,
maxClass,
from.GetClassAttrPtr(),
}
return ret
}
// Only have the class attribute
maxVal := 0
maxClass := ""
for i := range classes {
if classes[i] > maxVal {
maxClass = i
maxVal = classes[i]
}
}
// If there are no more Attributes left to split on,
// return a DecisionTreeLeaf with the majority class
if from.GetAttributeCount() == 2 {
ret := &DecisionTreeNode{
LeafNode,
nil,
nil,
classes,
maxClass,
from.GetClassAttrPtr(),
}
return ret
}
ret := &DecisionTreeNode{
RuleNode,
nil,
nil,
classes,
maxClass,
from.GetClassAttrPtr(),
}
// Generate a return structure
// Generate the splitting attribute
splitOnAttribute := with.GenerateSplitAttribute(from)
if splitOnAttribute == nil {
// Can't determine, just return what we have
return ret
}
// Split the attributes based on this attribute's value
splitInstances := from.DecomposeOnAttributeValues(splitOnAttribute)
// Create new children from these attributes
ret.Children = make(map[string]*DecisionTreeNode)
for k := range splitInstances {
newInstances := splitInstances[k]
ret.Children[k] = InferID3Tree(newInstances, with)
}
ret.SplitAttr = splitOnAttribute
return ret
}
