示例#1
0
// GetSplitAttributeFromSelection returns the class Attribute which maximises
// the information gain amongst consideredAttributes
//
// IMPORTANT: passing a zero-length consideredAttributes parameter will panic()
func (r *InformationGainRuleGenerator) GetSplitAttributeFromSelection(consideredAttributes []base.Attribute, f base.FixedDataGrid) base.Attribute {

	var selectedAttribute base.Attribute

	// Parameter check
	if len(consideredAttributes) == 0 {
		panic("More Attributes should be considered")
	}

	// Next step is to compute the information gain at this node
	// for each randomly chosen attribute, and pick the one
	// which maximises it
	maxGain := math.Inf(-1)

	// Compute the base entropy
	classDist := base.GetClassDistribution(f)
	baseEntropy := getBaseEntropy(classDist)

	// Compute the information gain for each attribute
	for _, s := range consideredAttributes {
		proposedClassDist := base.GetClassDistributionAfterSplit(f, s)
		localEntropy := getSplitEntropy(proposedClassDist)
		informationGain := baseEntropy - localEntropy
		if informationGain > maxGain {
			maxGain = informationGain
			selectedAttribute = s
		}
	}

	// Pick the one which maximises IG
	return selectedAttribute
}
示例#2
0
文件: entropy.go 项目: CTLife/golearn
// GetSplitRuleFromSelection returns a DecisionTreeRule which maximises
// the information gain amongst the considered Attributes.
//
// IMPORTANT: passing a zero-length consideredAttributes parameter will panic()
func (r *InformationGainRuleGenerator) GetSplitRuleFromSelection(consideredAttributes []base.Attribute, f base.FixedDataGrid) *DecisionTreeRule {

	var selectedAttribute base.Attribute

	// Parameter check
	if len(consideredAttributes) == 0 {
		panic("More Attributes should be considered")
	}

	// Next step is to compute the information gain at this node
	// for each randomly chosen attribute, and pick the one
	// which maximises it
	maxGain := math.Inf(-1)
	selectedVal := math.Inf(1)

	// Compute the base entropy
	classDist := base.GetClassDistribution(f)
	baseEntropy := getBaseEntropy(classDist)

	// Compute the information gain for each attribute
	for _, s := range consideredAttributes {
		var informationGain float64
		var splitVal float64
		if fAttr, ok := s.(*base.FloatAttribute); ok {
			var attributeEntropy float64
			attributeEntropy, splitVal = getNumericAttributeEntropy(f, fAttr)
			informationGain = baseEntropy - attributeEntropy
		} else {
			proposedClassDist := base.GetClassDistributionAfterSplit(f, s)
			localEntropy := getSplitEntropy(proposedClassDist)
			informationGain = baseEntropy - localEntropy
		}

		if informationGain > maxGain {
			maxGain = informationGain
			selectedAttribute = s
			selectedVal = splitVal
		}
	}

	// Pick the one which maximises IG
	return &DecisionTreeRule{selectedAttribute, selectedVal}
}
示例#3
0
文件: id3.go 项目: tanduong/golearn
// InferID3Tree builds a decision tree using a RuleGenerator
// from a set of Instances (implements the ID3 algorithm)
func InferID3Tree(from base.FixedDataGrid, with RuleGenerator) *DecisionTreeNode {
	// Count the number of classes at this node
	classes := base.GetClassDistribution(from)
	// 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,
			classes,
			maxClass,
			getClassAttr(from),
			&DecisionTreeRule{nil, 0.0},
		}
		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
	cols, _ := from.Size()
	if cols == 2 {
		ret := &DecisionTreeNode{
			LeafNode,
			nil,
			classes,
			maxClass,
			getClassAttr(from),
			&DecisionTreeRule{nil, 0.0},
		}
		return ret
	}

	// Generate a return structure
	ret := &DecisionTreeNode{
		RuleNode,
		nil,
		classes,
		maxClass,
		getClassAttr(from),
		nil,
	}

	// Generate the splitting rule
	splitRule := with.GenerateSplitRule(from)
	if splitRule == nil {
		// Can't determine, just return what we have
		return ret
	}

	// Split the attributes based on this attribute's value
	var splitInstances map[string]base.FixedDataGrid
	if _, ok := splitRule.SplitAttr.(*base.FloatAttribute); ok {
		splitInstances = base.DecomposeOnNumericAttributeThreshold(from,
			splitRule.SplitAttr, splitRule.SplitVal)
	} else {
		splitInstances = base.DecomposeOnAttributeValues(from, splitRule.SplitAttr)
	}
	// 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.SplitRule = splitRule
	return ret
}