// 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
}
func findBestSplit(partition base.FixedDataGrid) {
var delta float64
delta = math.MinInt64
attrs := partition.AllAttributes()
classAttrs := partition.AllClassAttributes()
candidates := base.AttributeDifferenceReferences(attrs, classAttrs)
fmt.Println(delta)
fmt.Println(classAttrs)
fmt.Println(reflect.TypeOf(partition))
fmt.Println(reflect.TypeOf(candidates))
for i, n := range attrs {
fmt.Println(i)
//fmt.Println(partition)
fmt.Println(reflect.TypeOf(n))
attributeSpec, _ := partition.GetAttribute(n)
fmt.Println(partition.GetAttribute(n))
_, rows := partition.Size()
for j := 0; j < rows; j++ {
data := partition.Get(attributeSpec, j)
fmt.Println(base.UnpackBytesToFloat(data))
}
}
}
// 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
}
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
}
// Transform converts the given byte sequence using the old Attribute into the new
// byte sequence.
//
// If the old Attribute has a categorical value of at most two items, then a zero or
// non-zero byte sequence is returned.
//
// If the old Attribute has a categorical value of at most n-items, then a non-zero
// or zero byte sequence is returned based on the value of the new Attribute passed in.
//
// If the old Attribute is a float, it's value's unpacked and we check for non-zeroness
//
// If the old Attribute is a BinaryAttribute, just return the input
func (b *BinaryConvertFilter) Transform(a base.Attribute, n base.Attribute, attrBytes []byte) []byte {
ret := make([]byte, 1)
// Check for CategoricalAttribute
if _, ok := a.(*base.CategoricalAttribute); ok {
// Unpack byte value
val := base.UnpackBytesToU64(attrBytes)
// If it's a two-valued one, check for non-zero
if b.twoValuedCategoricalAttributes[a] {
if val > 0 {
ret[0] = 1
} else {
ret[0] = 0
}
} else if an, ok := b.nValuedCategoricalAttributeMap[a]; ok {
// If it's an n-valued one, check the new Attribute maps onto
// the unpacked value
if af, ok := an[val]; ok {
if af.Equals(n) {
ret[0] = 1
} else {
ret[0] = 0
}
} else {
panic("Categorical value not defined!")
}
} else {
panic(fmt.Sprintf("Not a recognised Attribute %v", a))
}
} else if _, ok := a.(*base.BinaryAttribute); ok {
// Binary: just return the original value
ret = attrBytes
} else if _, ok := a.(*base.FloatAttribute); ok {
// Float: check for non-zero
val := base.UnpackBytesToFloat(attrBytes)
if val > 0 {
ret[0] = 1
} else {
ret[0] = 0
}
} else {
panic(fmt.Sprintf("Unrecognised Attribute: %v", a))
}
return ret
}
// Transform returns the byte sequence after discretisation
func (c *ChiMergeFilter) Transform(a base.Attribute, n base.Attribute, field []byte) []byte {
// Do we use this Attribute?
if !c.attrs[a] {
return field
}
// Find the Attribute value in the table
table := c.tables[a]
dis := 0
val := base.UnpackBytesToFloat(field)
for j, k := range table {
if k.Value < val {
dis = j
continue
}
break
}
return base.PackU64ToBytes(uint64(dis))
}
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
})
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
}
// Fit trains the neural network on the given fixed datagrid.
//
// Training stops when the mean-squared error acheived is less
// than the Convergence value, or when back-propagation has occured
// more times than the value set by MaxIterations.
func (m *MultiLayerNet) Fit(X base.FixedDataGrid) {
// Make sure everything's a FloatAttribute
insts := m.convertToFloatInsts(X)
// The size of the first layer is the number of things
// in the revised instances which aren't class Attributes
inputAttrsVec := base.NonClassAttributes(insts)
// The size of the output layer is the number of things
// in the revised instances which are class Attributes
classAttrsVec := insts.AllClassAttributes()
// The total number of layers is input layer + output layer
// plus number of layers specified
totalLayers := 2 + len(m.layers)
// The size is then augmented by the number of nodes
// in the centre
size := len(inputAttrsVec)
size += len(classAttrsVec)
hiddenSize := 0
for _, a := range m.layers {
size += a
hiddenSize += a
}
// Enumerate the Attributes
trainingAttrs := make(map[base.Attribute]int)
classAttrs := make(map[base.Attribute]int)
attrCounter := 0
for i, a := range inputAttrsVec {
attrCounter = i
m.attrs[a] = attrCounter
trainingAttrs[a] = attrCounter
}
m.classAttrOffset = attrCounter + 1
for _, a := range classAttrsVec {
attrCounter++
m.attrs[a] = attrCounter + hiddenSize
classAttrs[a] = attrCounter + hiddenSize
m.classAttrCount++
}
// Create the underlying Network
m.network = NewNetwork(size, len(inputAttrsVec), Sigmoid)
// Initialise inter-hidden layer weights and biases to small random values
layerOffset := len(inputAttrsVec)
for i := 0; i < len(m.layers)-1; i++ {
// Get the size of this layer
thisLayerSize := m.layers[i]
// Next layer size
nextLayerSize := m.layers[i+1]
// For every node in this layer
for j := 1; j <= thisLayerSize; j++ {
// Compute the offset
nodeOffset1 := layerOffset + j
// For every node in the next layer
for k := 1; k <= nextLayerSize; k++ {
// Compute offset
nodeOffset2 := layerOffset + thisLayerSize + k
// Set weight randomly
m.network.SetWeight(nodeOffset1, nodeOffset2, rand.NormFloat64()*0.1)
}
}
layerOffset += thisLayerSize
}
// Initialise biases with each hidden layer
layerOffset = len(inputAttrsVec)
for _, l := range m.layers {
for j := 1; j <= l; j++ {
nodeOffset := layerOffset + j
m.network.SetBias(nodeOffset, rand.NormFloat64()*0.1)
}
layerOffset += l
}
// Initialise biases for output layer
for i := 0; i < len(classAttrsVec); i++ {
nodeOffset := layerOffset + i
m.network.SetBias(nodeOffset, rand.NormFloat64()*0.1)
}
// Connect final hidden layer with the output layer
layerOffset = len(inputAttrsVec)
for i, l := range m.layers {
if i == len(m.layers)-1 {
for j := 1; j <= l; j++ {
nodeOffset1 := layerOffset + j
for k := 1; k <= len(classAttrsVec); k++ {
nodeOffset2 := layerOffset + l + k
m.network.SetWeight(nodeOffset1, nodeOffset2, rand.NormFloat64()*0.1)
}
}
}
layerOffset += l
}
// Connect input layer with first hidden layer (or output layer
for i := 1; i <= len(inputAttrsVec); i++ {
nextLayerLen := 0
if len(m.layers) > 0 {
nextLayerLen = m.layers[0]
} else {
nextLayerLen = len(classAttrsVec)
}
for j := 1; j <= nextLayerLen; j++ {
nodeOffset := len(inputAttrsVec) + j
v := rand.NormFloat64() * 0.1
m.network.SetWeight(i, nodeOffset, v)
}
}
// Create the training activation vector
trainVec := mat64.NewDense(size, 1, make([]float64, size))
// Create the error vector
errVec := mat64.NewDense(size, 1, make([]float64, size))
// Resolve training AttributeSpecs
trainAs := base.ResolveAllAttributes(insts)
// Feed-forward, compute error and update for each training example
// until convergence (what's that)
for iteration := 0; iteration < m.MaxIterations; iteration++ {
totalError := 0.0
maxRow := 0
insts.MapOverRows(trainAs, func(row [][]byte, i int) (bool, error) {
maxRow = i
// Clear vectors
for i := 0; i < size; i++ {
trainVec.Set(i, 0, 0.0)
errVec.Set(i, 0, 0.0)
}
// Build vectors
for i, vb := range row {
v := base.UnpackBytesToFloat(vb)
if attrIndex, ok := trainingAttrs[trainAs[i].GetAttribute()]; ok {
// Add to Activation vector
trainVec.Set(attrIndex, 0, v)
} else if attrIndex, ok := classAttrs[trainAs[i].GetAttribute()]; ok {
// Set to error vector
errVec.Set(attrIndex, 0, v)
} else {
panic("Should be able to find this Attribute!")
}
}
// Activate the network
m.network.Activate(trainVec, totalLayers-1)
// Compute the error
for a := range classAttrs {
cIndex := classAttrs[a]
errVec.Set(cIndex, 0, errVec.At(cIndex, 0)-trainVec.At(cIndex, 0))
}
// Update total error
totalError += math.Abs(errVec.Sum())
// Back-propagate the error
b := m.network.Error(trainVec, errVec, totalLayers)
// Update the weights
m.network.UpdateWeights(trainVec, b, m.LearningRate)
// Update the biases
m.network.UpdateBias(b, m.LearningRate)
return true, nil
})
totalError /= float64(maxRow)
// If we've converged, no need to carry on
if totalError < m.Convergence {
break
}
}
}
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
}