func TestSmote(t *testing.T) {
smot := smote.New(PercentOver, K, 5)
// Read samples.
dataset := tabula.Claset{}
_, e := dsv.SimpleRead(fcfg, &dataset)
if nil != e {
t.Fatal(e)
}
fmt.Println("[smote_test] Total samples:", dataset.Len())
minorset := dataset.GetMinorityRows()
fmt.Println("[smote_test] # minority samples:", minorset.Len())
e = smot.Resampling(*minorset)
if e != nil {
t.Fatal(e)
}
fmt.Println("[smote_test] # synthetic:", smot.GetSynthetics().Len())
e = smot.Write("phoneme_smote.csv")
if e != nil {
t.Fatal(e)
}
}
func getSamples() (train, test tabula.ClasetInterface) {
samples := tabula.Claset{}
_, e := dsv.SimpleRead(SampleDsvFile, &samples)
if nil != e {
log.Fatal(e)
}
if !DoTest {
return &samples, nil
}
ntrain := int(float32(samples.Len()) * (float32(NBootstrap) / 100.0))
bag, oob, _, _ := tabula.RandomPickRows(&samples, ntrain, false)
train = bag.(tabula.ClasetInterface)
test = oob.(tabula.ClasetInterface)
train.SetClassIndex(samples.GetClassIndex())
test.SetClassIndex(samples.GetClassIndex())
return train, test
}