Golang FixedDataGrid.MapOverRows方法代码示例

func (lr *LogisticRegression) Predict(X base.FixedDataGrid) base.FixedDataGrid {

	// Only support 1 class Attribute
	classAttrs := X.AllClassAttributes()
	if len(classAttrs) != 1 {
		panic(fmt.Sprintf("%d Wrong number of classes", len(classAttrs)))
	}
	// Generate return structure
	ret := base.GeneratePredictionVector(X)
	classAttrSpecs := base.ResolveAttributes(ret, classAttrs)
	// Retrieve numeric non-class Attributes
	numericAttrs := base.NonClassFloatAttributes(X)
	numericAttrSpecs := base.ResolveAttributes(X, numericAttrs)

	// Allocate row storage
	row := make([]float64, len(numericAttrSpecs))
	X.MapOverRows(numericAttrSpecs, func(rowBytes [][]byte, rowNo int) (bool, error) {
		for i, r := range rowBytes {
			row[i] = base.UnpackBytesToFloat(r)
		}
		val := Predict(lr.model, row)
		vals := base.PackFloatToBytes(val)
		ret.Set(classAttrSpecs[0], rowNo, vals)
		return true, nil
	})

	return ret
}

func ChiMBuildFrequencyTable(attr base.Attribute, inst base.FixedDataGrid) []*FrequencyTableEntry {
	ret := make([]*FrequencyTableEntry, 0)
	attribute := attr.(*base.FloatAttribute)

	attrSpec, err := inst.GetAttribute(attr)
	if err != nil {
		panic(err)
	}
	attrSpecs := []base.AttributeSpec{attrSpec}

	err = inst.MapOverRows(attrSpecs, func(row [][]byte, rowNo int) (bool, error) {
		value := row[0]
		valueConv := attribute.GetFloatFromSysVal(value)
		class := base.GetClass(inst, rowNo)
		// Search the frequency table for the value
		found := false
		for _, entry := range ret {
			if entry.Value == valueConv {
				found = true
				entry.Frequency[class] += 1
			}
		}
		if !found {
			newEntry := &FrequencyTableEntry{
				valueConv,
				make(map[string]int),
			}
			newEntry.Frequency[class] = 1
			ret = append(ret, newEntry)
		}
		return true, nil
	})

	return ret
}

// Predict outputs a base.Instances containing predictions from this tree
func (d *DecisionTreeNode) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error) {
	predictions := base.GeneratePredictionVector(what)
	classAttr := getClassAttr(predictions)
	classAttrSpec, err := predictions.GetAttribute(classAttr)
	if err != nil {
		panic(err)
	}
	predAttrs := base.AttributeDifferenceReferences(what.AllAttributes(), predictions.AllClassAttributes())
	predAttrSpecs := base.ResolveAttributes(what, predAttrs)
	what.MapOverRows(predAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
		cur := d
		for {
			if cur.Children == nil {
				predictions.Set(classAttrSpec, rowNo, classAttr.GetSysValFromString(cur.Class))
				break
			} else {
				splitVal := cur.SplitRule.SplitVal
				at := cur.SplitRule.SplitAttr
				ats, err := what.GetAttribute(at)
				if err != nil {
					//predictions.Set(classAttrSpec, rowNo, classAttr.GetSysValFromString(cur.Class))
					//break
					panic(err)
				}

				var classVar string
				if _, ok := ats.GetAttribute().(*base.FloatAttribute); ok {
					// If it's a numeric Attribute (e.g. FloatAttribute) check that
					// the value of the current node is greater than the old one
					classVal := base.UnpackBytesToFloat(what.Get(ats, rowNo))
					if classVal > splitVal {
						classVar = "1"
					} else {
						classVar = "0"
					}
				} else {
					classVar = ats.GetAttribute().GetStringFromSysVal(what.Get(ats, rowNo))
				}
				if next, ok := cur.Children[classVar]; ok {
					cur = next
				} else {
					// Suspicious of this
					var bestChild string
					for c := range cur.Children {
						bestChild = c
						if c > classVar {
							break
						}
					}
					cur = cur.Children[bestChild]
				}
			}
		}
		return true, nil
	})
	return predictions, nil
}

func getNumericAttributeEntropy(f base.FixedDataGrid, attr *base.FloatAttribute) (float64, float64) {

	// Resolve Attribute
	attrSpec, err := f.GetAttribute(attr)
	if err != nil {
		panic(err)
	}

	// Build sortable vector
	_, rows := f.Size()
	refs := make([]numericSplitRef, rows)
	f.MapOverRows([]base.AttributeSpec{attrSpec}, func(val [][]byte, row int) (bool, error) {
		cls := base.GetClass(f, row)
		v := base.UnpackBytesToFloat(val[0])
		refs[row] = numericSplitRef{v, cls}
		return true, nil
	})

	// Sort
	sort.Sort(splitVec(refs))

	generateCandidateSplitDistribution := func(val float64) map[string]map[string]int {
		presplit := make(map[string]int)
		postplit := make(map[string]int)
		for _, i := range refs {
			if i.val < val {
				presplit[i.class]++
			} else {
				postplit[i.class]++
			}
		}
		ret := make(map[string]map[string]int)
		ret["0"] = presplit
		ret["1"] = postplit
		return ret
	}

	minSplitEntropy := math.Inf(1)
	minSplitVal := math.Inf(1)
	// Consider each possible function
	for i := 0; i < len(refs)-1; i++ {
		val := refs[i].val + refs[i+1].val
		val /= 2
		splitDist := generateCandidateSplitDistribution(val)
		splitEntropy := getSplitEntropy(splitDist)
		if splitEntropy < minSplitEntropy {
			minSplitEntropy = splitEntropy
			minSplitVal = val
		}
	}

	return minSplitEntropy, minSplitVal
}

// Predict is just a wrapper for the PredictOne function.
//
// IMPORTANT: Predict panics if Fit was not called or if the
// document vector and train matrix have a different number of columns.
func (nb *BernoulliNBClassifier) Predict(what base.FixedDataGrid) base.FixedDataGrid {
	// Generate return vector
	ret := base.GeneratePredictionVector(what)

	// Get the features
	featAttrSpecs := base.ResolveAttributes(what, nb.attrs)

	what.MapOverRows(featAttrSpecs, func(row [][]byte, i int) (bool, error) {
		base.SetClass(ret, i, nb.PredictOne(row))
		return true, nil
	})

	return ret
}

func processData(x base.FixedDataGrid) instances {
	_, rows := x.Size()

	result := make(instances, rows)

	// Retrieve numeric non-class Attributes
	numericAttrs := base.NonClassFloatAttributes(x)
	numericAttrSpecs := base.ResolveAttributes(x, numericAttrs)

	// Retrieve class Attributes
	classAttrs := x.AllClassAttributes()
	if len(classAttrs) != 1 {
		panic("Only one classAttribute supported!")
	}

	// Check that the class Attribute is categorical
	// (with two values) or binary
	classAttr := classAttrs[0]
	if attr, ok := classAttr.(*base.CategoricalAttribute); ok {
		if len(attr.GetValues()) != 2 {
			panic("To many values for Attribute!")
		}
	} else if _, ok := classAttr.(*base.BinaryAttribute); ok {
	} else {
		panic("Wrong class Attribute type!")
	}

	// Convert each row
	x.MapOverRows(numericAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
		// Allocate a new row
		probRow := make([]float64, len(numericAttrSpecs))

		// Read out the row
		for i, _ := range numericAttrSpecs {
			probRow[i] = base.UnpackBytesToFloat(row[i])
		}

		// Get the class for the values
		class := base.GetClass(x, rowNo)
		instance := instance{class, probRow}
		result[rowNo] = instance
		return true, nil
	})
	return result
}

// Predict outputs a base.Instances containing predictions from this tree
func (d *DecisionTreeNode) Predict(what base.FixedDataGrid) base.FixedDataGrid {
	predictions := base.GeneratePredictionVector(what)
	classAttr := getClassAttr(predictions)
	classAttrSpec, err := predictions.GetAttribute(classAttr)
	if err != nil {
		panic(err)
	}
	predAttrs := base.AttributeDifferenceReferences(what.AllAttributes(), predictions.AllClassAttributes())
	predAttrSpecs := base.ResolveAttributes(what, predAttrs)
	what.MapOverRows(predAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
		cur := d
		for {
			if cur.Children == nil {
				predictions.Set(classAttrSpec, rowNo, classAttr.GetSysValFromString(cur.Class))
				break
			} else {
				at := cur.SplitAttr
				ats, err := what.GetAttribute(at)
				if err != nil {
					predictions.Set(classAttrSpec, rowNo, classAttr.GetSysValFromString(cur.Class))
					break
				}

				classVar := ats.GetAttribute().GetStringFromSysVal(what.Get(ats, rowNo))
				if next, ok := cur.Children[classVar]; ok {
					cur = next
				} else {
					var bestChild string
					for c := range cur.Children {
						bestChild = c
						if c > classVar {
							break
						}
					}
					cur = cur.Children[bestChild]
				}
			}
		}
		return true, nil
	})
	return predictions
}

func convertInstancesToLabelVec(X base.FixedDataGrid) []float64 {
	// Get the class Attributes
	classAttrs := X.AllClassAttributes()
	// Only support 1 class Attribute
	if len(classAttrs) != 1 {
		panic(fmt.Sprintf("%d ClassAttributes (1 expected)", len(classAttrs)))
	}
	// ClassAttribute must be numeric
	if _, ok := classAttrs[0].(*base.FloatAttribute); !ok {
		panic(fmt.Sprintf("%s: ClassAttribute must be a FloatAttribute", classAttrs[0]))
	}
	// Allocate return structure
	_, rows := X.Size()
	labelVec := make([]float64, rows)
	// Resolve class Attribute specification
	classAttrSpecs := base.ResolveAttributes(X, classAttrs)
	X.MapOverRows(classAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
		labelVec[rowNo] = base.UnpackBytesToFloat(row[0])
		return true, nil
	})
	return labelVec
}

func convertInstancesToProblemVec(X base.FixedDataGrid) [][]float64 {
	// Allocate problem array
	_, rows := X.Size()
	problemVec := make([][]float64, rows)

	// Retrieve numeric non-class Attributes
	numericAttrs := base.NonClassFloatAttributes(X)
	numericAttrSpecs := base.ResolveAttributes(X, numericAttrs)

	// Convert each row
	X.MapOverRows(numericAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
		// Allocate a new row
		probRow := make([]float64, len(numericAttrSpecs))
		// Read out the row
		for i, _ := range numericAttrSpecs {
			probRow[i] = base.UnpackBytesToFloat(row[i])
		}
		// Add the row
		problemVec[rowNo] = probRow
		return true, nil
	})
	return problemVec
}

func (lr *LinearRegression) Predict(X base.FixedDataGrid) (base.FixedDataGrid, error) {
	if !lr.fitted {
		return nil, NoTrainingDataError
	}

	ret := base.GeneratePredictionVector(X)
	attrSpecs := base.ResolveAttributes(X, lr.attrs)
	clsSpec, err := ret.GetAttribute(lr.cls)
	if err != nil {
		return nil, err
	}

	X.MapOverRows(attrSpecs, func(row [][]byte, i int) (bool, error) {
		var prediction float64 = lr.disturbance
		for j, r := range row {
			prediction += base.UnpackBytesToFloat(r) * lr.regressionCoefficients[j]
		}

		ret.Set(clsSpec, i, base.PackFloatToBytes(prediction))
		return true, nil
	})

	return ret, nil
}

// Predict returns a classification for the vector, based on a vector input, using the KNN algorithm.
func (KNN *KNNClassifier) Predict(what base.FixedDataGrid) base.FixedDataGrid {

	// Check what distance function we are using
	var distanceFunc pairwise.PairwiseDistanceFunc
	switch KNN.DistanceFunc {
	case "euclidean":
		distanceFunc = pairwise.NewEuclidean()
	case "manhattan":
		distanceFunc = pairwise.NewManhattan()
	default:
		panic("unsupported distance function")

	}
	// Check Compatibility
	allAttrs := base.CheckCompatible(what, KNN.TrainingData)
	if allAttrs == nil {
		// Don't have the same Attributes
		return nil
	}

	// Remove the Attributes which aren't numeric
	allNumericAttrs := make([]base.Attribute, 0)
	for _, a := range allAttrs {
		if fAttr, ok := a.(*base.FloatAttribute); ok {
			allNumericAttrs = append(allNumericAttrs, fAttr)
		}
	}

	// Generate return vector
	ret := base.GeneratePredictionVector(what)

	// Resolve Attribute specifications for both
	whatAttrSpecs := base.ResolveAttributes(what, allNumericAttrs)
	trainAttrSpecs := base.ResolveAttributes(KNN.TrainingData, allNumericAttrs)

	// Reserve storage for most the most similar items
	distances := make(map[int]float64)

	// Reserve storage for voting map
	maxmap := make(map[string]int)

	// Reserve storage for row computations
	trainRowBuf := make([]float64, len(allNumericAttrs))
	predRowBuf := make([]float64, len(allNumericAttrs))

	// Iterate over all outer rows
	what.MapOverRows(whatAttrSpecs, func(predRow [][]byte, predRowNo int) (bool, error) {
		// Read the float values out
		for i, _ := range allNumericAttrs {
			predRowBuf[i] = base.UnpackBytesToFloat(predRow[i])
		}

		predMat := utilities.FloatsToMatrix(predRowBuf)

		// Find the closest match in the training data
		KNN.TrainingData.MapOverRows(trainAttrSpecs, func(trainRow [][]byte, srcRowNo int) (bool, error) {

			// Read the float values out
			for i, _ := range allNumericAttrs {
				trainRowBuf[i] = base.UnpackBytesToFloat(trainRow[i])
			}

			// Compute the distance
			trainMat := utilities.FloatsToMatrix(trainRowBuf)
			distances[srcRowNo] = distanceFunc.Distance(predMat, trainMat)
			return true, nil
		})

		sorted := utilities.SortIntMap(distances)
		values := sorted[:KNN.NearestNeighbours]

		// Reset maxMap
		for a := range maxmap {
			maxmap[a] = 0
		}

		// Refresh maxMap
		for _, elem := range values {
			label := base.GetClass(KNN.TrainingData, elem)
			if _, ok := maxmap[label]; ok {
				maxmap[label]++
			} else {
				maxmap[label] = 1
			}
		}

		// Sort the maxMap
		var maxClass string
		maxVal := -1
		for a := range maxmap {
			if maxmap[a] > maxVal {
				maxVal = maxmap[a]
				maxClass = a
			}
		}

		base.SetClass(ret, predRowNo, maxClass)
		return true, nil

//.........这里部分代码省略.........

// Fill data matrix with Bernoulli Naive Bayes model. All values
// necessary for calculating prior probability and p(f_i)
func (nb *BernoulliNBClassifier) Fit(X base.FixedDataGrid) {

	// Check that all Attributes are binary
	classAttrs := X.AllClassAttributes()
	allAttrs := X.AllAttributes()
	featAttrs := base.AttributeDifference(allAttrs, classAttrs)
	for i := range featAttrs {
		if _, ok := featAttrs[i].(*base.BinaryAttribute); !ok {
			panic(fmt.Sprintf("%v: Should be BinaryAttribute", featAttrs[i]))
		}
	}
	featAttrSpecs := base.ResolveAttributes(X, featAttrs)

	// Check that only one classAttribute is defined
	if len(classAttrs) != 1 {
		panic("Only one class Attribute can be used")
	}

	// Number of features and instances in this training set
	_, nb.trainingInstances = X.Size()
	nb.attrs = featAttrs
	nb.features = len(featAttrs)

	// Number of instances in class
	nb.classInstances = make(map[string]int)

	// Number of documents with given term (by class)
	docsContainingTerm := make(map[string][]int)

	// This algorithm could be vectorized after binarizing the data
	// matrix. Since mat64 doesn't have this function, a iterative
	// version is used.
	X.MapOverRows(featAttrSpecs, func(docVector [][]byte, r int) (bool, error) {
		class := base.GetClass(X, r)

		// increment number of instances in class
		t, ok := nb.classInstances[class]
		if !ok {
			t = 0
		}
		nb.classInstances[class] = t + 1

		for feat := 0; feat < len(docVector); feat++ {
			v := docVector[feat]
			// In Bernoulli Naive Bayes the presence and absence of
			// features are considered. All non-zero values are
			// treated as presence.
			if v[0] > 0 {
				// Update number of times this feature appeared within
				// given label.
				t, ok := docsContainingTerm[class]
				if !ok {
					t = make([]int, nb.features)
					docsContainingTerm[class] = t
				}
				t[feat] += 1
			}
		}
		return true, nil
	})

	// Pre-calculate conditional probabilities for each class
	for c, _ := range nb.classInstances {
		nb.condProb[c] = make([]float64, nb.features)
		for feat := 0; feat < nb.features; feat++ {
			classTerms, _ := docsContainingTerm[c]
			numDocs := classTerms[feat]
			docsInClass, _ := nb.classInstances[c]

			classCondProb, _ := nb.condProb[c]
			// Calculate conditional probability with laplace smoothing
			classCondProb[feat] = float64(numDocs+1) / float64(docsInClass+1)
		}
	}
}

// Predict returns a classification for the vector, based on a vector input, using the KNN algorithm.
func (KNN *KNNClassifier) Predict(what base.FixedDataGrid) base.FixedDataGrid {
	// Check what distance function we are using
	var distanceFunc pairwise.PairwiseDistanceFunc
	switch KNN.DistanceFunc {
	case "euclidean":
		distanceFunc = pairwise.NewEuclidean()
	case "manhattan":
		distanceFunc = pairwise.NewManhattan()
	default:
		panic("unsupported distance function")
	}
	// Check Compatibility
	allAttrs := base.CheckCompatible(what, KNN.TrainingData)
	if allAttrs == nil {
		// Don't have the same Attributes
		return nil
	}

	// Use optimised version if permitted
	if KNN.AllowOptimisations {
		if KNN.DistanceFunc == "euclidean" {
			if KNN.canUseOptimisations(what) {
				return KNN.optimisedEuclideanPredict(what.(*base.DenseInstances))
			}
		}
	}
	fmt.Println("Optimisations are switched off")

	// Remove the Attributes which aren't numeric
	allNumericAttrs := make([]base.Attribute, 0)
	for _, a := range allAttrs {
		if fAttr, ok := a.(*base.FloatAttribute); ok {
			allNumericAttrs = append(allNumericAttrs, fAttr)
		}
	}

	// Generate return vector
	ret := base.GeneratePredictionVector(what)

	// Resolve Attribute specifications for both
	whatAttrSpecs := base.ResolveAttributes(what, allNumericAttrs)
	trainAttrSpecs := base.ResolveAttributes(KNN.TrainingData, allNumericAttrs)

	// Reserve storage for most the most similar items
	distances := make(map[int]float64)

	// Reserve storage for voting map
	maxmap := make(map[string]int)

	// Reserve storage for row computations
	trainRowBuf := make([]float64, len(allNumericAttrs))
	predRowBuf := make([]float64, len(allNumericAttrs))

	_, maxRow := what.Size()
	curRow := 0

	// Iterate over all outer rows
	what.MapOverRows(whatAttrSpecs, func(predRow [][]byte, predRowNo int) (bool, error) {

		if (curRow%1) == 0 && curRow > 0 {
			fmt.Printf("KNN: %.2f %% done\n", float64(curRow)*100.0/float64(maxRow))
		}
		curRow++

		// Read the float values out
		for i, _ := range allNumericAttrs {
			predRowBuf[i] = base.UnpackBytesToFloat(predRow[i])
		}

		predMat := utilities.FloatsToMatrix(predRowBuf)

		// Find the closest match in the training data
		KNN.TrainingData.MapOverRows(trainAttrSpecs, func(trainRow [][]byte, srcRowNo int) (bool, error) {
			// Read the float values out
			for i, _ := range allNumericAttrs {
				trainRowBuf[i] = base.UnpackBytesToFloat(trainRow[i])
			}

			// Compute the distance
			trainMat := utilities.FloatsToMatrix(trainRowBuf)
			distances[srcRowNo] = distanceFunc.Distance(predMat, trainMat)
			return true, nil
		})

		sorted := utilities.SortIntMap(distances)
		values := sorted[:KNN.NearestNeighbours]

		maxClass := KNN.vote(maxmap, values)

		base.SetClass(ret, predRowNo, maxClass)
		return true, nil

	})

	return ret
}

func (lr *LinearRegression) Fit(inst base.FixedDataGrid) error {

	// Retrieve row size
	_, rows := inst.Size()

	// Validate class Attribute count
	classAttrs := inst.AllClassAttributes()
	if len(classAttrs) != 1 {
		return fmt.Errorf("Only 1 class variable is permitted")
	}
	classAttrSpecs := base.ResolveAttributes(inst, classAttrs)

	// Retrieve relevant Attributes
	allAttrs := base.NonClassAttributes(inst)
	attrs := make([]base.Attribute, 0)
	for _, a := range allAttrs {
		if _, ok := a.(*base.FloatAttribute); ok {
			attrs = append(attrs, a)
		}
	}

	cols := len(attrs) + 1

	if rows < cols {
		return NotEnoughDataError
	}

	// Retrieve relevant Attribute specifications
	attrSpecs := base.ResolveAttributes(inst, attrs)

	// 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(rows, 1, nil)
	explVariables := mat64.NewDense(rows, cols, nil)

	// Build the observed matrix
	inst.MapOverRows(classAttrSpecs, func(row [][]byte, i int) (bool, error) {
		val := base.UnpackBytesToFloat(row[0])
		observed.Set(i, 0, val)
		return true, nil
	})

	// Build the explainatory variables
	inst.MapOverRows(attrSpecs, func(row [][]byte, i int) (bool, error) {
		// Set intercepts to 1.0
		explVariables.Set(i, 0, 1.0)
		for j, r := range row {
			explVariables.Set(i, j+1, base.UnpackBytesToFloat(r))
		}
		return true, nil
	})

	n := cols
	qr := new(mat64.QR)
	qr.Factorize(explVariables)
	var q, reg mat64.Dense
	q.QFromQR(qr)
	reg.RFromQR(qr)

	var transposed, qty mat64.Dense
	transposed.Clone(q.T())
	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
	lr.attrs = attrs
	lr.cls = classAttrs[0]
	return nil
}