func AlgorithmRunOnDataSet(classifier algo.Classifier, train_dataset, test_dataset *core.DataSet, pred_path string, params map[string]string) (float64, []*eval.LabelPrediction) {
if train_dataset != nil {
classifier.Train(train_dataset)
}
predictions := []*eval.LabelPrediction{}
var pred_file *os.File
if pred_path != "" {
pred_file, _ = os.Create(pred_path)
}
for _, sample := range test_dataset.Samples {
prediction := classifier.Predict(sample)
if pred_file != nil {
pred_file.WriteString(strconv.FormatFloat(prediction, 'g', 5, 64) + "\n")
}
predictions = append(predictions, &(eval.LabelPrediction{Label: sample.Label, Prediction: prediction}))
}
if pred_path != "" {
defer pred_file.Close()
}
auc := eval.AUC(predictions)
return auc, predictions
}
func (algo *SAOptAUC) TrainAUC(samples []*core.Sample) float64 {
predictions := []*eval.LabelPrediction{}
for _, sample := range samples {
pred := algo.Predict(sample)
predictions = append(predictions, &(eval.LabelPrediction{Label: sample.Label, Prediction: pred}))
}
return eval.AUC(predictions)
}
func (c *CategoryFeatureCombination) OneCVAUC(dataset0 *core.RawDataSet, combines []core.CombinedFeature, total_cv, cv int) float64 {
dataset := dataset0.ToDataSet(nil, combines)
train := dataset.Split(func(i int) bool { return i%total_cv != cv })
c.algo.Train(train)
test := dataset.Split(func(i int) bool { return i%total_cv == cv })
predictions := []*eval.LabelPrediction{}
for _, sample := range test.Samples {
pred := c.algo.Predict(sample)
lp := eval.LabelPrediction{Label: sample.Label, Prediction: pred}
predictions = append(predictions, &lp)
}
auc := eval.AUC(predictions)
c.algo.Clear()
return auc
}