// Predict issues predictions. Each class-specific classifier is expected
// to output a value between 0 (indicating that a given instance is not
// a given class) and 1 (indicating that the given instance is definitely
// that class). For each instance, the class with the highest value is chosen.
// The result is undefined if several underlying models output the same value.
func (m *OneVsAllModel) Predict(what base.FixedDataGrid) (base.FixedDataGrid, error) {
ret := base.GeneratePredictionVector(what)
vecs := make([]base.FixedDataGrid, m.maxClassVal+1)
specs := make([]base.AttributeSpec, m.maxClassVal+1)
for i := uint64(0); i <= m.maxClassVal; i++ {
f := m.filters[i]
c := base.NewLazilyFilteredInstances(what, f)
p, err := m.classifiers[i].Predict(c)
if err != nil {
return nil, err
}
vecs[i] = p
specs[i] = base.ResolveAttributes(p, p.AllClassAttributes())[0]
}
_, rows := ret.Size()
spec := base.ResolveAttributes(ret, ret.AllClassAttributes())[0]
for i := 0; i < rows; i++ {
class := uint64(0)
best := 0.0
for j := uint64(0); j <= m.maxClassVal; j++ {
val := base.UnpackBytesToFloat(vecs[j].Get(specs[j], i))
if val > best {
class = j
best = val
}
}
ret.Set(spec, i, base.PackU64ToBytes(class))
}
return ret, nil
}
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
}
// 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
}
// 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
}
// 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
}
// param base.IFixedDataGrid
// return base.IFixedDataGrid
func (p *AveragePerceptron) Predict(what base.FixedDataGrid) base.FixedDataGrid {
if !p.trained {
panic("Cannot call Predict on an untrained AveragePerceptron")
}
data := processData(what)
allAttrs := base.CheckCompatible(what, p.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)
}
}
ret := base.GeneratePredictionVector(what)
classAttr := ret.AllClassAttributes()[0]
classSpec, err := ret.GetAttribute(classAttr)
if err != nil {
panic(err)
}
for i, datum := range data {
result := p.score(datum)
if result > 0.0 {
ret.Set(classSpec, i, base.PackU64ToBytes(1))
} else {
ret.Set(classSpec, 1, []byte{0, 0, 0, 0, 0, 0, 0, 0})
}
}
return ret
}
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
})
return ret
}
// Predict gathers predictions from all the classifiers
// and outputs the most common (majority) class
//
// IMPORTANT: in the event of a tie, the first class which
// achieved the tie value is output.
func (b *BaggedModel) Predict(from base.FixedDataGrid) base.FixedDataGrid {
n := runtime.NumCPU()
// Channel to receive the results as they come in
votes := make(chan base.DataGrid, n)
// Count the votes for each class
voting := make(map[int](map[string]int))
// Create a goroutine to collect the votes
var votingwait sync.WaitGroup
votingwait.Add(1)
go func() {
for { // Need to resolve the voting problem
incoming, ok := <-votes
if ok {
cSpecs := base.ResolveAttributes(incoming, incoming.AllClassAttributes())
incoming.MapOverRows(cSpecs, func(row [][]byte, predRow int) (bool, error) {
// Check if we've seen this class before...
if _, ok := voting[predRow]; !ok {
// If we haven't, create an entry
voting[predRow] = make(map[string]int)
// Continue on the current row
}
voting[predRow][base.GetClass(incoming, predRow)]++
return true, nil
})
} else {
votingwait.Done()
break
}
}
}()
// Create workers to process the predictions
processpipe := make(chan int, n)
var processwait sync.WaitGroup
for i := 0; i < n; i++ {
processwait.Add(1)
go func() {
for {
if i, ok := <-processpipe; ok {
c := b.Models[i]
l := b.generatePredictionInstances(i, from)
votes <- c.Predict(l)
} else {
processwait.Done()
break
}
}
}()
}
// Send all the models to the workers for prediction
for i := range b.Models {
processpipe <- i
}
close(processpipe) // Finished sending models to be predicted
processwait.Wait() // Predictors all finished processing
close(votes) // Close the vote channel and allow it to drain
votingwait.Wait() // All the votes are in
// Generate the overall consensus
ret := base.GeneratePredictionVector(from)
for i := range voting {
maxClass := ""
maxCount := 0
// Find the most popular class
for c := range voting[i] {
votes := voting[i][c]
if votes > maxCount {
maxClass = c
maxCount = votes
}
}
base.SetClass(ret, i, maxClass)
}
return ret
}
// 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
}
// Predict uses the underlying network to produce predictions for the
// class variables of X.
//
// Can only predict one CategoricalAttribute at a time, or up to n
// FloatAttributes. Set or unset ClassAttributes to work around this
// limitation.
func (m *MultiLayerNet) Predict(X base.FixedDataGrid) base.FixedDataGrid {
// Create the return vector
ret := base.GeneratePredictionVector(X)
// Make sure everything's a FloatAttribute
insts := m.convertToFloatInsts(X)
// Get the input/output Attributes
inputAttrs := base.NonClassAttributes(insts)
outputAttrs := ret.AllClassAttributes()
// Compute layers
layers := 2 + len(m.layers)
// Check that we're operating in a singular mode
floatMode := 0
categoricalMode := 0
for _, a := range outputAttrs {
if _, ok := a.(*base.CategoricalAttribute); ok {
categoricalMode++
} else if _, ok := a.(*base.FloatAttribute); ok {
floatMode++
} else {
panic("Unsupported output Attribute type!")
}
}
if floatMode > 0 && categoricalMode > 0 {
panic("Can't predict a mix of float and categorical Attributes")
} else if categoricalMode > 1 {
panic("Can't predict more than one categorical class Attribute")
}
// Create the activation vector
a := mat64.NewDense(m.network.size, 1, make([]float64, m.network.size))
// Resolve the input AttributeSpecs
inputAs := base.ResolveAttributes(insts, inputAttrs)
// Resolve the output Attributespecs
outputAs := base.ResolveAttributes(ret, outputAttrs)
// Map over each input row
insts.MapOverRows(inputAs, func(row [][]byte, rc int) (bool, error) {
// Clear the activation vector
for i := 0; i < m.network.size; i++ {
a.Set(i, 0, 0.0)
}
// Build the activation vector
for i, vb := range row {
if cIndex, ok := m.attrs[inputAs[i].GetAttribute()]; !ok {
panic("Can't resolve the Attribute!")
} else {
a.Set(cIndex, 0, base.UnpackBytesToFloat(vb))
}
}
// Robots, activate!
m.network.Activate(a, layers)
// Decide which class to set
if floatMode > 0 {
for _, as := range outputAs {
cIndex := m.attrs[as.GetAttribute()]
ret.Set(as, rc, base.PackFloatToBytes(a.At(cIndex, 0)))
}
} else {
maxIndex := 0
maxVal := 0.0
for i := m.classAttrOffset; i < m.classAttrOffset+m.classAttrCount; i++ {
val := a.At(i, 0)
if val > maxVal {
maxIndex = i
maxVal = val
}
}
maxIndex -= m.classAttrOffset
ret.Set(outputAs[0], rc, base.PackU64ToBytes(uint64(maxIndex)))
}
return true, nil
})
return ret
}
func (KNN *KNNClassifier) optimisedEuclideanPredict(d *base.DenseInstances) base.FixedDataGrid {
// Create return vector
ret := base.GeneratePredictionVector(d)
// Type-assert training data
tr := KNN.TrainingData.(*base.DenseInstances)
// Enumeration of AttributeGroups
agPos := make(map[string]int)
agTrain := tr.AllAttributeGroups()
agPred := d.AllAttributeGroups()
classAttrs := tr.AllClassAttributes()
counter := 0
for ag := range agTrain {
// Detect whether the AttributeGroup has any classes in it
attrs := agTrain[ag].Attributes()
//matched := false
if len(base.AttributeIntersect(classAttrs, attrs)) == 0 {
agPos[ag] = counter
}
counter++
}
// Pointers to the start of each prediction row
rowPointers := make([]*C.double, len(agPred))
trainPointers := make([]*C.double, len(agPred))
rowSizes := make([]int, len(agPred))
for ag := range agPred {
if ap, ok := agPos[ag]; ok {
rowPointers[ap] = (*C.double)(unsafe.Pointer(&(agPred[ag].Storage()[0])))
trainPointers[ap] = (*C.double)(unsafe.Pointer(&(agTrain[ag].Storage()[0])))
rowSizes[ap] = agPred[ag].RowSizeInBytes() / 8
}
}
_, predRows := d.Size()
_, trainRows := tr.Size()
// Crete the distance vector
distanceVec := distanceRecs(make([]_Ctype_struct_dist, trainRows))
// Additional datastructures
voteVec := make([]int, KNN.NearestNeighbours)
maxMap := make(map[string]int)
for row := 0; row < predRows; row++ {
for i := 0; i < trainRows; i++ {
distanceVec[i].dist = 0
}
for ag := range agPred {
if ap, ok := agPos[ag]; ok {
C.euclidean_distance(
&(distanceVec[0]),
C.int(trainRows),
C.int(len(agPred[ag].Attributes())),
C.int(row),
trainPointers[ap],
rowPointers[ap],
)
}
}
sort.Sort(distanceVec)
votes := distanceVec[:KNN.NearestNeighbours]
for i, v := range votes {
voteVec[i] = int(v.p)
}
maxClass := KNN.vote(maxMap, voteVec)
base.SetClass(ret, row, maxClass)
}
return ret
}