Golang ClasetInterface.GetNRow方法代码示例

//
// Initialize will check forest inputs and set it to default values if invalid.
//
// It will also calculate number of random samples for each tree using,
//
//	number-of-sample * percentage-of-bootstrap
//
//
func (forest *Runtime) Initialize(samples tabula.ClasetInterface) error {
	if forest.NTree <= 0 {
		forest.NTree = DefNumTree
	}
	if forest.PercentBoot <= 0 {
		forest.PercentBoot = DefPercentBoot
	}
	if forest.NRandomFeature <= 0 {
		// Set default value to square-root of features.
		ncol := samples.GetNColumn() - 1
		forest.NRandomFeature = int(math.Sqrt(float64(ncol)))
	}
	if forest.OOBStatsFile == "" {
		forest.OOBStatsFile = DefOOBStatsFile
	}
	if forest.PerfFile == "" {
		forest.PerfFile = DefPerfFile
	}
	if forest.StatFile == "" {
		forest.StatFile = DefStatFile
	}

	forest.nSubsample = int(float32(samples.GetNRow()) *
		(float32(forest.PercentBoot) / 100.0))

	return forest.Runtime.Initialize()
}

/*
ClassifySet set the class attribute based on tree classification.
*/
func (runtime *Runtime) ClassifySet(data tabula.ClasetInterface) (e error) {
	nrow := data.GetNRow()
	targetAttr := data.GetClassColumn()

	for i := 0; i < nrow; i++ {
		class := runtime.Classify(data.GetRow(i))

		_ = (*targetAttr).Records[i].SetValue(class, tabula.TString)
	}

	return
}

/*
splitTreeByGain calculate the gain in all dataset, and split into two node:
left and right.

Return node with the split information.
*/
func (runtime *Runtime) splitTreeByGain(D tabula.ClasetInterface) (
	node *binary.BTNode,
	e error,
) {
	node = &binary.BTNode{}

	D.RecountMajorMinor()

	// if dataset is empty return node labeled with majority classes in
	// dataset.
	nrow := D.GetNRow()

	if nrow <= 0 {
		if DEBUG >= 2 {
			fmt.Printf("[cart] empty dataset (%s) : %v\n",
				D.MajorityClass(), D)
		}

		node.Value = NodeValue{
			IsLeaf: true,
			Class:  D.MajorityClass(),
			Size:   0,
		}
		return node, nil
	}

	// if all dataset is in the same class, return node as leaf with class
	// is set to that class.
	single, name := D.IsInSingleClass()
	if single {
		if DEBUG >= 2 {
			fmt.Printf("[cart] in single class (%s): %v\n", name,
				D.GetColumns())
		}

		node.Value = NodeValue{
			IsLeaf: true,
			Class:  name,
			Size:   nrow,
		}
		return node, nil
	}

	if DEBUG >= 2 {
		fmt.Println("[cart] D:", D)
	}

	// calculate the Gini gain for each attribute.
	gains := runtime.computeGain(D)

	// get attribute with maximum Gini gain.
	MaxGainIdx := gini.FindMaxGain(&gains)
	MaxGain := gains[MaxGainIdx]

	// if maxgain value is 0, use majority class as node and terminate
	// the process
	if MaxGain.GetMaxGainValue() == 0 {
		if DEBUG >= 2 {
			fmt.Println("[cart] max gain 0 with target",
				D.GetClassAsStrings(),
				" and majority class is ", D.MajorityClass())
		}

		node.Value = NodeValue{
			IsLeaf: true,
			Class:  D.MajorityClass(),
			Size:   0,
		}
		return node, nil
	}

	// using the sorted index in MaxGain, sort all field in dataset
	tabula.SortColumnsByIndex(D, MaxGain.SortedIndex)

	if DEBUG >= 2 {
		fmt.Println("[cart] maxgain:", MaxGain)
	}

	// Now that we have attribute with max gain in MaxGainIdx, and their
	// gain dan partition value in Gains[MaxGainIdx] and
	// GetMaxPartValue(), we split the dataset based on type of max-gain
	// attribute.
	// If its continuous, split the attribute using numeric value.
	// If its discrete, split the attribute using subset (partition) of
	// nominal values.
	var splitV interface{}

	if MaxGain.IsContinu {
		splitV = MaxGain.GetMaxPartGainValue()
	} else {
		attrPartV := MaxGain.GetMaxPartGainValue()
		attrSubV := attrPartV.(tekstus.ListStrings)
		splitV = attrSubV[0].Normalize()
	}
//.........这里部分代码省略.........