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))
}
}
}
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
}
// generateTrainingAttrs selects RandomFeatures number of base.Attributes from
// the provided base.Instances.
func (b *BaggedModel) generateTrainingAttrs(model int, from base.FixedDataGrid) []base.Attribute {
ret := make([]base.Attribute, 0)
attrs := base.NonClassAttributes(from)
if b.RandomFeatures == 0 {
ret = attrs
} else {
for {
if len(ret) >= b.RandomFeatures {
break
}
attrIndex := rand.Intn(len(attrs))
attr := attrs[attrIndex]
matched := false
for _, a := range ret {
if a.Equals(attr) {
matched = true
break
}
}
if !matched {
ret = append(ret, attr)
}
}
}
for _, a := range from.AllClassAttributes() {
ret = append(ret, a)
}
b.lock.Lock()
b.selectedAttributes[model] = ret
b.lock.Unlock()
return ret
}
// GenerateSplitRule returns the best attribute out of those randomly chosen
// which maximises Information Gain
func (r *RandomTreeRuleGenerator) GenerateSplitRule(f base.FixedDataGrid) *DecisionTreeRule {
var consideredAttributes []base.Attribute
// First step is to generate the random attributes that we'll consider
allAttributes := base.AttributeDifferenceReferences(f.AllAttributes(), f.AllClassAttributes())
maximumAttribute := len(allAttributes)
attrCounter := 0
for {
if len(consideredAttributes) >= r.Attributes {
break
}
selectedAttrIndex := rand.Intn(maximumAttribute)
selectedAttribute := allAttributes[selectedAttrIndex]
matched := false
for _, a := range consideredAttributes {
if a.Equals(selectedAttribute) {
matched = true
break
}
}
if matched {
continue
}
consideredAttributes = append(consideredAttributes, selectedAttribute)
attrCounter++
}
return r.internalRule.GetSplitRuleFromSelection(consideredAttributes, f)
}
// GenerateSplitAttribute returns the non-class Attribute which maximises the
// information gain.
//
// IMPORTANT: passing a base.Instances with no Attributes other than the class
// variable will panic()
func (r *InformationGainRuleGenerator) GenerateSplitAttribute(f base.FixedDataGrid) base.Attribute {
attrs := f.AllAttributes()
classAttrs := f.AllClassAttributes()
candidates := base.AttributeDifferenceReferences(attrs, classAttrs)
return r.GetSplitAttributeFromSelection(candidates, f)
}
// GenerateSplitRule returns the non-class Attribute-based DecisionTreeRule
// which maximises the information gain.
//
// IMPORTANT: passing a base.Instances with no Attributes other than the class
// variable will panic()
func (g *GiniCoefficientRuleGenerator) GenerateSplitRule(f base.FixedDataGrid) *DecisionTreeRule {
attrs := f.AllAttributes()
classAttrs := f.AllClassAttributes()
candidates := base.AttributeDifferenceReferences(attrs, classAttrs)
return g.GetSplitRuleFromSelection(candidates, f)
}
func generateClassWeightVectorFromFixed(X base.FixedDataGrid) []float64 {
classAttrs := X.AllClassAttributes()
if len(classAttrs) != 1 {
panic("Wrong number of class Attributes")
}
if _, ok := classAttrs[0].(*base.FloatAttribute); ok {
ret := make([]float64, 2)
for i := range ret {
ret[i] = 1.0
}
return ret
} else {
panic("Must be a FloatAttribute")
}
}
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
}
func (m *OneVsAllModel) generateAttributes(from base.FixedDataGrid) map[base.Attribute]base.Attribute {
attrs := from.AllAttributes()
classAttrs := from.AllClassAttributes()
if len(classAttrs) != 1 {
panic("Only 1 class Attribute is supported!")
}
ret := make(map[base.Attribute]base.Attribute)
for _, a := range attrs {
ret[a] = a
for _, b := range classAttrs {
if a.Equals(b) {
cur := base.NewFloatAttribute(b.GetName())
ret[a] = cur
}
}
}
return ret
}
// Fit creates n filtered datasets (where n is the number of values
// a CategoricalAttribute can take) and uses them to train the
// underlying classifiers.
func (m *OneVsAllModel) Fit(using base.FixedDataGrid) {
var classAttr *base.CategoricalAttribute
// Do some validation
classAttrs := using.AllClassAttributes()
for _, a := range classAttrs {
if c, ok := a.(*base.CategoricalAttribute); !ok {
panic("Unsupported ClassAttribute type")
} else {
classAttr = c
}
}
attrs := m.generateAttributes(using)
// Find the highest stored value
val := uint64(0)
classVals := classAttr.GetValues()
for _, s := range classVals {
cur := base.UnpackBytesToU64(classAttr.GetSysValFromString(s))
if cur > val {
val = cur
}
}
if val == 0 {
panic("Must have more than one class!")
}
m.maxClassVal = val
// Create individual filtered instances for training
filters := make([]*oneVsAllFilter, val+1)
classifiers := make([]base.Classifier, val+1)
for i := uint64(0); i <= val; i++ {
f := &oneVsAllFilter{
attrs,
classAttr,
i,
}
filters[i] = f
classifiers[i] = m.NewClassifierFunction(classVals[int(i)])
classifiers[i].Fit(base.NewLazilyFilteredInstances(using, f))
}
m.filters = filters
m.classifiers = classifiers
}
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 getClassAttr(from base.FixedDataGrid) base.Attribute {
allClassAttrs := from.AllClassAttributes()
return allClassAttrs[0]
}
// 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)
}
}
}
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
}