//
// Init will initialize LNSmote runtime by checking input values and set it to
// default if not set or invalid.
//
func (in *Runtime) Init(dataset tabula.ClasetInterface) {
in.Runtime.Init()
in.NSynthetic = in.PercentOver / 100.0
in.datasetRows = dataset.GetDataAsRows()
in.minorset = tabula.SelectRowsWhere(dataset, in.ClassIndex,
in.ClassMinor)
in.outliers = make(tabula.Rows, 0)
if DEBUG >= 1 {
fmt.Println("[lnsmote] n:", in.NSynthetic)
fmt.Println("[lnsmote] n minority:", in.minorset.Len())
}
}
//
// ClassifySetByWeight will classify each instance in samples by weight
// with respect to its single performance.
//
// Algorithm,
// (1) For each instance in samples,
// (1.1) for each stage,
// (1.1.1) collect votes for instance in current stage.
// (1.1.2) Compute probabilities of each classes in votes.
//
// prob_class = count_of_class / total_votes
//
// (1.1.3) Compute total of probabilites times of stage weight.
//
// stage_prob = prob_class * stage_weight
//
// (1.2) Divide each class stage probabilites with
//
// stage_prob = stage_prob /
// (sum_of_all_weights * number_of_tree_in_forest)
//
// (1.3) Select class label with highest probabilites.
// (1.4) Save stage probabilities for positive class.
// (2) Compute confusion matrix.
//
func (crf *Runtime) ClassifySetByWeight(samples tabula.ClasetInterface,
sampleIds []int,
) (
predicts []string, cm *classifier.CM, probs []float64,
) {
stat := classifier.Stat{}
stat.Start()
vs := samples.GetClassValueSpace()
stageProbs := make([]float64, len(vs))
stageSumProbs := make([]float64, len(vs))
sumWeights := numerus.Floats64Sum(crf.weights)
// (1)
rows := samples.GetDataAsRows()
for _, row := range *rows {
for y := range stageSumProbs {
stageSumProbs[y] = 0
}
// (1.1)
for y, forest := range crf.forests {
// (1.1.1)
votes := forest.Votes(row, -1)
// (1.1.2)
probs := tekstus.WordsProbabilitiesOf(votes, vs, false)
// (1.1.3)
for z := range probs {
stageSumProbs[z] += probs[z]
stageProbs[z] += probs[z] * crf.weights[y]
}
}
// (1.2)
stageWeight := sumWeights * float64(crf.NTree)
for x := range stageProbs {
stageProbs[x] = stageProbs[x] / stageWeight
}
// (1.3)
_, maxi, ok := numerus.Floats64FindMax(stageProbs)
if ok {
predicts = append(predicts, vs[maxi])
}
probs = append(probs, stageSumProbs[0]/
float64(len(crf.forests)))
}
// (2)
actuals := samples.GetClassAsStrings()
cm = crf.ComputeCM(sampleIds, vs, actuals, predicts)
crf.ComputeStatFromCM(&stat, cm)
stat.End()
_ = stat.Write(crf.StatFile)
return predicts, cm, probs
}