//
// refillWithFP will copy the false-positive data in training set `tnset`
// and append it to `samples`.
//
func (crf *Runtime) refillWithFP(samples, tnset tabula.ClasetInterface,
cm *classifier.CM,
) {
// Get and sort FP.
fpids := cm.FPIndices()
sort.Ints(fpids)
// Move FP samples from TN-set to training set samples.
for _, i := range fpids {
samples.PushRow(tnset.GetRow(i))
}
// Delete FP from training set.
var row *tabula.Row
c := 0
for x, i := range fpids {
row = tnset.DeleteRow(i - x)
if row != nil {
c++
}
}
if DEBUG >= 1 {
fmt.Println(tag, "# FP", len(fpids), "# refilled", c)
}
}
func (crf *Runtime) deleteTrueNegative(samples tabula.ClasetInterface,
cm *classifier.CM,
) {
var row *tabula.Row
tnids := cm.TNIndices()
sort.Ints(tnids)
// (1)
if len(crf.weights) <= 1 {
for _, i := range tnids {
crf.tnset.PushRow(samples.GetRow(i))
}
}
// (2)
c := 0
for x, i := range tnids {
row = samples.DeleteRow(i - x)
if row != nil {
c++
}
}
if DEBUG >= 1 {
fmt.Println(tag, "# TN", len(tnids), "# deleted", c)
}
}
//
// Build given a sample dataset, build the stage with randomforest.
//
func (crf *Runtime) Build(samples tabula.ClasetInterface) (e error) {
if samples == nil {
return ErrNoInput
}
e = crf.Initialize(samples)
if e != nil {
return
}
fmt.Println(tag, "Training samples:", samples)
fmt.Println(tag, "Sample (one row):", samples.GetRow(0))
fmt.Println(tag, "Config:", crf)
for x := 0; x < crf.NStage; x++ {
if DEBUG >= 1 {
fmt.Println(tag, "Stage #", x)
}
forest, e := crf.createForest(samples)
if e != nil {
return e
}
e = crf.finalizeStage(forest)
if e != nil {
return e
}
}
return crf.Finalize()
}
//
// ClassifySet given a samples predict their class by running each sample in
// forest, adn return their class prediction with confusion matrix.
// `samples` is the sample that will be predicted, `sampleIds` is the index of
// samples.
// If `sampleIds` is not nil, then sample index will be checked in each tree,
// if the sample is used for training, their vote is not counted.
//
// Algorithm,
//
// (0) Get value space (possible class values in dataset)
// (1) For each row in test-set,
// (1.1) collect votes in all trees,
// (1.2) select majority class vote, and
// (1.3) compute and save the actual class probabilities.
// (2) Compute confusion matrix from predictions.
// (3) Compute stat from confusion matrix.
// (4) Write the stat to file only if sampleIds is empty, which mean its run
// not from OOB set.
//
func (forest *Runtime) ClassifySet(samples tabula.ClasetInterface,
sampleIds []int,
) (
predicts []string, cm *classifier.CM, probs []float64,
) {
stat := classifier.Stat{}
stat.Start()
if len(sampleIds) <= 0 {
fmt.Println(tag, "Classify set:", samples)
fmt.Println(tag, "Classify set sample (one row):",
samples.GetRow(0))
}
// (0)
vs := samples.GetClassValueSpace()
actuals := samples.GetClassAsStrings()
sampleIdx := -1
// (1)
rows := samples.GetRows()
for x, row := range *rows {
// (1.1)
if len(sampleIds) > 0 {
sampleIdx = sampleIds[x]
}
votes := forest.Votes(row, sampleIdx)
// (1.2)
classProbs := tekstus.WordsProbabilitiesOf(votes, vs, false)
_, idx, ok := numerus.Floats64FindMax(classProbs)
if ok {
predicts = append(predicts, vs[idx])
}
// (1.3)
probs = append(probs, classProbs[0])
}
// (2)
cm = forest.ComputeCM(sampleIds, vs, actuals, predicts)
// (3)
forest.ComputeStatFromCM(&stat, cm)
stat.End()
if len(sampleIds) <= 0 {
fmt.Println(tag, "CM:", cm)
fmt.Println(tag, "Classifying stat:", stat)
_ = stat.Write(forest.StatFile)
}
return predicts, cm, probs
}
/*
ClassifySet set the class attribute based on tree classification.
*/
func (runtime *Runtime) ClassifySet(data tabula.ClasetInterface) (e error) {
nrow := data.GetNRow()
targetAttr := data.GetClassColumn()
for i := 0; i < nrow; i++ {
class := runtime.Classify(data.GetRow(i))
_ = (*targetAttr).Records[i].SetValue(class, tabula.TString)
}
return
}
/*
Build the forest using samples dataset.
Algorithm,
(0) Recheck input value: number of tree, percentage bootstrap, etc; and
Open statistic file output.
(1) For 0 to NTree,
(1.1) Create new tree, repeat until all trees has been build.
(2) Compute and write total statistic.
*/
func (forest *Runtime) Build(samples tabula.ClasetInterface) (e error) {
// check input samples
if samples == nil {
return ErrNoInput
}
// (0)
e = forest.Initialize(samples)
if e != nil {
return
}
fmt.Println(tag, "Training set :", samples)
fmt.Println(tag, "Sample (one row):", samples.GetRow(0))
fmt.Println(tag, "Forest config :", forest)
// (1)
for t := 0; t < forest.NTree; t++ {
if DEBUG >= 1 {
fmt.Println(tag, "tree #", t)
}
// (1.1)
for {
_, _, e = forest.GrowTree(samples)
if e == nil {
break
}
fmt.Println(tag, "error:", e)
}
}
// (2)
return forest.Finalize()
}