Exemplo n.º 1
0
// Prune eliminates branches which hurt accuracy
func (d *DecisionTreeNode) Prune(using *base.Instances) {
	// If you're a leaf, you're already pruned
	if d.Children == nil {
		return
	} else {
		if d.SplitAttr == nil {
			return
		}
		// Recursively prune children of this node
		sub := using.DecomposeOnAttributeValues(d.SplitAttr)
		for k := range d.Children {
			if sub[k] == nil {
				continue
			}
			d.Children[k].Prune(sub[k])
		}
	}

	// Get a baseline accuracy
	baselineAccuracy := computeAccuracy(d.Predict(using), using)

	// Speculatively remove the children and re-evaluate
	tmpChildren := d.Children
	d.Children = nil
	newAccuracy := computeAccuracy(d.Predict(using), using)

	// Keep the children removed if better, else restore
	if newAccuracy < baselineAccuracy {
		d.Children = tmpChildren
	}
}
Exemplo n.º 2
0
// 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
}