// generateTrainingAttrs selects RandomFeatures number of base.Attributes from
// the provided base.Instances.
func (b *BaggedModel) generateTrainingAttrs(model int, from *base.Instances) []base.Attribute {
ret := make([]base.Attribute, 0)
if b.RandomFeatures == 0 {
for j := 0; j < from.Cols; j++ {
attr := from.GetAttr(j)
ret = append(ret, attr)
}
} else {
for {
if len(ret) >= b.RandomFeatures {
break
}
attrIndex := rand.Intn(from.Cols)
if attrIndex == from.ClassIndex {
continue
}
attr := from.GetAttr(attrIndex)
matched := false
for _, a := range ret {
if a.Equals(attr) {
matched = true
break
}
}
if !matched {
ret = append(ret, attr)
}
}
}
ret = append(ret, from.GetClassAttr())
b.lock.Lock()
b.selectedAttributes[model] = ret
b.lock.Unlock()
return ret
}
// GetSplitAttributeFromSelection returns the class Attribute which maximises
// the information gain amongst consideredAttributes
//
// IMPORTANT: passing a zero-length consideredAttributes parameter will panic()
func (r *InformationGainRuleGenerator) GetSplitAttributeFromSelection(consideredAttributes []int, f *base.Instances) base.Attribute {
// Next step is to compute the information gain at this node
// for each randomly chosen attribute, and pick the one
// which maximises it
maxGain := math.Inf(-1)
selectedAttribute := -1
// Compute the base entropy
classDist := f.GetClassDistribution()
baseEntropy := getBaseEntropy(classDist)
// Compute the information gain for each attribute
for _, s := range consideredAttributes {
proposedClassDist := f.GetClassDistributionAfterSplit(f.GetAttr(s))
localEntropy := getSplitEntropy(proposedClassDist)
informationGain := baseEntropy - localEntropy
if informationGain > maxGain {
maxGain = informationGain
selectedAttribute = s
}
}
// Pick the one which maximises IG
return f.GetAttr(selectedAttribute)
}
// Run discretises the set of Instances `on'
//
// IMPORTANT: ChiMergeFilter discretises in place.
func (c *ChiMergeFilter) Run(on *base.Instances) {
if !c._Trained {
panic("Call Build() beforehand")
}
for attr := range c.Tables {
table := c.Tables[attr]
for i := 0; i < on.Rows; i++ {
val := on.Get(i, attr)
dis := 0
for j, k := range table {
if k.Value < val {
dis = j
continue
}
break
}
on.Set(i, attr, float64(dis))
}
newAttribute := new(base.CategoricalAttribute)
newAttribute.SetName(on.GetAttr(attr).GetName())
for _, k := range table {
newAttribute.GetSysValFromString(fmt.Sprintf("%f", k.Value))
}
on.ReplaceAttr(attr, newAttribute)
}
}
// Run applies a trained BinningFilter to a set of Instances,
// discretising any numeric attributes added.
//
// IMPORTANT: Run discretises in-place, so make sure to take
// a copy if the original instances are still needed
//
// IMPORTANT: This function panic()s if the filter has not been
// trained. Call Build() before running this function
//
// IMPORTANT: Call Build() after adding any additional attributes.
// Otherwise, the training structure will be out of date from
// the values expected and could cause a panic.
func (b *BinningFilter) Run(on *base.Instances) {
if !b.trained {
panic("Call Build() beforehand")
}
for attr := range b.Attributes {
minVal := b.MinVals[attr]
maxVal := b.MaxVals[attr]
disc := 0
// Casts to float32 to replicate a floating point precision error
delta := float32(maxVal - minVal)
delta /= float32(b.BinCount)
for i := 0; i < on.Rows; i++ {
val := on.Get(i, attr)
if val <= minVal {
disc = 0
} else {
disc = int(math.Floor(float64(float32(val-minVal) / delta)))
if disc >= b.BinCount {
disc = b.BinCount - 1
}
}
on.Set(i, attr, float64(disc))
}
newAttribute := new(base.CategoricalAttribute)
newAttribute.SetName(on.GetAttr(attr).GetName())
for i := 0; i < b.BinCount; i++ {
newAttribute.GetSysValFromString(fmt.Sprintf("%d", i))
}
on.ReplaceAttr(attr, newAttribute)
}
}
func ChiMBuildFrequencyTable(attr int, inst *base.Instances) []*FrequencyTableEntry {
ret := make([]*FrequencyTableEntry, 0)
var attribute *base.FloatAttribute
attribute, ok := inst.GetAttr(attr).(*base.FloatAttribute)
if !ok {
panic("only use Chi-M on numeric stuff")
}
for i := 0; i < inst.Rows; i++ {
value := inst.Get(i, attr)
valueConv := attribute.GetUsrVal(value)
class := inst.GetClass(i)
// Search the frequency table for the value
found := false
for _, entry := range ret {
if entry.Value == valueConv {
found = true
entry.Frequency[class] += 1
}
}
if !found {
newEntry := &FrequencyTableEntry{
valueConv,
make(map[string]int),
}
newEntry.Frequency[class] = 1
ret = append(ret, newEntry)
}
}
return ret
}
