// 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
}
// 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))
}
// 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
}
// Transform takes an Attribute and byte sequence and returns
// the transformed byte sequence.
func (b *BinningFilter) Transform(a base.Attribute, n base.Attribute, field []byte) []byte {
if !b.attrs[a] {
return field
}
af, ok := a.(*base.FloatAttribute)
if !ok {
panic("Attribute is the wrong type")
}
minVal := b.minVals[a]
maxVal := b.maxVals[a]
disc := 0
// Casts to float64 to replicate a floating point precision error
delta := float64(maxVal-minVal) / float64(b.bins)
val := float64(af.GetFloatFromSysVal(field))
if val <= minVal {
disc = 0
} else {
disc = int(math.Floor(float64(float64(val-minVal)/delta + 0.0001)))
}
return base.PackU64ToBytes(uint64(disc))
}
// 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
}