func (f *oneVsAllFilter) Transform(old, to base.Attribute, seq []byte) []byte {
if !old.Equals(f.classAttr) {
return seq
}
val := base.UnpackBytesToU64(seq)
if val == f.classAttrVal {
return base.PackFloatToBytes(1.0)
}
return base.PackFloatToBytes(0.0)
}
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 (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
}
func (f *FloatConvertFilter) Transform(a base.Attribute, n base.Attribute, attrBytes []byte) []byte {
ret := make([]byte, 8)
// 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 f.twoValuedCategoricalAttributes[a] {
if val > 0 {
ret = base.PackFloatToBytes(1.0)
} else {
ret = base.PackFloatToBytes(0.0)
}
} else if an, ok := f.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 = base.PackFloatToBytes(1.0)
} else {
ret = base.PackFloatToBytes(0.0)
}
} else {
panic("Categorical value not defined!")
}
} else {
panic(fmt.Sprintf("Not a recognised Attribute %v", a))
}
} else if _, ok := a.(*base.FloatAttribute); ok {
// Binary: just return the original value
ret = attrBytes
} else if _, ok := a.(*base.BinaryAttribute); ok {
// Float: check for non-zero
if attrBytes[0] > 0 {
ret = base.PackFloatToBytes(1.0)
} else {
ret = base.PackFloatToBytes(0.0)
}
} else {
panic(fmt.Sprintf("Unrecognised Attribute: %v", a))
}
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 TestFloatFilter(t *testing.T) {
Convey("Given a contrived dataset...", t, func() {
// Read the contrived dataset
inst, err := base.ParseCSVToInstances("./binary_test.csv", true)
So(err, ShouldEqual, nil)
// Add Attributes to the filter
bFilt := NewFloatConvertFilter()
bAttrs := base.NonClassAttributes(inst)
for _, a := range bAttrs {
bFilt.AddAttribute(a)
}
bFilt.Train()
// Construct a LazilyFilteredInstances to handle it
instF := base.NewLazilyFilteredInstances(inst, bFilt)
Convey("All the non-class Attributes should be floats...", func() {
// Check that all the Attributes are the right type
for _, a := range base.NonClassAttributes(instF) {
_, ok := a.(*base.FloatAttribute)
So(ok, ShouldEqual, true)
}
})
// Check that all the class Attributes made it
Convey("All the class Attributes should have survived...", func() {
origClassAttrs := inst.AllClassAttributes()
newClassAttrs := instF.AllClassAttributes()
intersectClassAttrs := base.AttributeIntersect(origClassAttrs, newClassAttrs)
So(len(intersectClassAttrs), ShouldEqual, len(origClassAttrs))
})
// Check that the Attributes have the right names
Convey("Attribute names should be correct...", func() {
origNames := []string{"floatAttr", "shouldBe1Binary",
"shouldBe3Binary_stoicism", "shouldBe3Binary_heroism",
"shouldBe3Binary_romanticism", "arbitraryClass"}
origMap := make(map[string]bool)
for _, a := range origNames {
origMap[a] = false
}
for _, a := range instF.AllAttributes() {
name := a.GetName()
_, ok := origMap[name]
So(ok, ShouldBeTrue)
origMap[name] = true
}
for a := range origMap {
So(origMap[a], ShouldEqual, true)
}
})
Convey("All Attributes should be the correct type...", func() {
for _, a := range instF.AllAttributes() {
if a.GetName() == "arbitraryClass" {
_, ok := a.(*base.CategoricalAttribute)
So(ok, ShouldEqual, true)
} else {
_, ok := a.(*base.FloatAttribute)
So(ok, ShouldEqual, true)
}
}
})
// Check that the Attributes have been discretised correctly
Convey("FloatConversion should have worked", func() {
// Build Attribute map
attrMap := make(map[string]base.Attribute)
for _, a := range instF.AllAttributes() {
attrMap[a.GetName()] = a
}
// For each attribute
for name := range attrMap {
So(name, ShouldBeIn, []string{
"floatAttr",
"shouldBe1Binary",
"shouldBe3Binary_stoicism",
"shouldBe3Binary_heroism",
"shouldBe3Binary_romanticism",
"arbitraryClass",
})
attr := attrMap[name]
as, err := instF.GetAttribute(attr)
So(err, ShouldEqual, nil)
if name == "floatAttr" {
So(instF.Get(as, 0), ShouldResemble, base.PackFloatToBytes(1.0))
So(instF.Get(as, 1), ShouldResemble, base.PackFloatToBytes(1.0))
So(instF.Get(as, 2), ShouldResemble, base.PackFloatToBytes(0.0))
} else if name == "shouldBe1Binary" {
So(instF.Get(as, 0), ShouldResemble, base.PackFloatToBytes(0.0))
So(instF.Get(as, 1), ShouldResemble, base.PackFloatToBytes(1.0))
So(instF.Get(as, 2), ShouldResemble, base.PackFloatToBytes(1.0))
} else if name == "shouldBe3Binary_stoicism" {
So(instF.Get(as, 0), ShouldResemble, base.PackFloatToBytes(1.0))
So(instF.Get(as, 1), ShouldResemble, base.PackFloatToBytes(0.0))
So(instF.Get(as, 2), ShouldResemble, base.PackFloatToBytes(0.0))
} else if name == "shouldBe3Binary_heroism" {
So(instF.Get(as, 0), ShouldResemble, base.PackFloatToBytes(0.0))
So(instF.Get(as, 1), ShouldResemble, base.PackFloatToBytes(1.0))
So(instF.Get(as, 2), ShouldResemble, base.PackFloatToBytes(0.0))
} else if name == "shouldBe3Binary_romanticism" {
So(instF.Get(as, 0), ShouldResemble, base.PackFloatToBytes(0.0))
So(instF.Get(as, 1), ShouldResemble, base.PackFloatToBytes(0.0))
So(instF.Get(as, 2), ShouldResemble, base.PackFloatToBytes(1.0))
} else if name == "arbitraryClass" {
}
}
})
})
}
