func main() {
train_path, _, _, method, params := hector.PrepareParams()
global, _ := strconv.ParseInt(params["global"], 10, 64)
profile, _ := params["profile"]
dataset := core.NewDataSet()
dataset.Load(train_path, global)
cv, _ := strconv.ParseInt(params["cv"], 10, 32)
total := int(cv)
if profile != "" {
fmt.Println(profile)
f, err := os.Create(profile)
if err != nil {
fmt.Println("%v", err)
log.Fatal(err)
}
pprof.StartCPUProfile(f)
defer pprof.StopCPUProfile()
}
average_auc := 0.0
for part := 0; part < total; part++ {
train, test := SplitFile(dataset, total, part)
classifier := hector.GetClassifier(method)
classifier.Init(params)
auc, _ := hector.AlgorithmRunOnDataSet(classifier, train, test, "", params)
fmt.Println("AUC:")
fmt.Println(auc)
average_auc += auc
classifier = nil
}
fmt.Println(average_auc / float64(total))
}
func main() {
train_path, _, _, method, params := hector.PrepareParams()
global, _ := strconv.ParseInt(params["global"], 10, 64)
profile, _ := params["profile"]
dataset := core.NewDataSet()
dataset.Load(train_path, global)
cv, _ := strconv.ParseInt(params["cv"], 10, 32)
total := int(cv)
if profile != "" {
f, err := os.Create(profile)
if err != nil {
log.Fatal(err)
}
pprof.StartCPUProfile(f)
defer pprof.StopCPUProfile()
}
average_accuracy := 0.0
for part := 0; part < total; part++ {
train, test := SplitFile(dataset, total, part)
classifier := hector.GetMutliClassClassifier(method)
classifier.Init(params)
accuracy := hector.MultiClassRunOnDataSet(classifier, train, test, "", params)
fmt.Println("accuracy : ", accuracy)
average_accuracy += accuracy
classifier = nil
train = nil
test = nil
runtime.GC()
}
fmt.Println(average_accuracy / float64(total))
}
func main() {
train, test, _, _, params := hector.PrepareParams()
action, _ := params["action"]
if action == "encodelabel" {
fmt.Println("encoded dataset label ..." + train)
e := core.NewLabelEncoder()
EncodeLabelAction(e, train)
fmt.Println("encoded dataset label ..." + test)
EncodeLabelAction(e, test)
}
}
func main() {
_, _, _, method, params := hector.PrepareParams()
ch := &ClassifierHandler{
classifier: hector.GetClassifier(method),
}
model, ok := params["model"]
if !ok {
log.Fatalln("please input model file")
}
ch.classifier.LoadModel(model)
http.Handle("/predict", ch)
err := http.ListenAndServe(":"+params["port"], nil)
if err != nil {
log.Fatal(err)
}
}
func main() {
train, test, pred, method, params := hector.PrepareParams()
action, _ := params["action"]
classifier := hector.GetClassifier(method)
if action == "" {
auc, _, _ := hector.AlgorithmRun(classifier, train, test, pred, params)
fmt.Println("AUC:")
fmt.Println(auc)
} else if action == "train" {
hector.AlgorithmTrain(classifier, train, params)
} else if action == "test" {
auc, _, _ := hector.AlgorithmTest(classifier, test, pred, params)
fmt.Println("AUC:")
fmt.Println(auc)
}
}
func main() {
train, _, _, _, params := hector.PrepareParams()
feature_combination := combine.CategoryFeatureCombination{}
feature_combination.Init(params)
dataset := core.NewRawDataSet()
dataset.Load(train)
combinations := feature_combination.FindCombination(dataset)
output := params["output"]
file, _ := os.Create(output)
defer file.Close()
for _, combination := range combinations {
file.WriteString(strings.Join(combination, "\t") + "\n")
}
}
func main() {
train_path, test_path, pred_path, _, params := hector.PrepareParams()
total := 5
methods := []string{"ftrl", "fm"}
all_methods_predictions := [][]*eval.LabelPrediction{}
all_methods_test_predictions := [][]*eval.LabelPrediction{}
for _, method := range methods {
fmt.Println(method)
average_auc := 0.0
all_predictions := []*eval.LabelPrediction{}
for part := 0; part < total; part++ {
train, test, _ := SplitFile(train_path, total, part)
classifier := hector.GetClassifier(method)
auc, predictions, _ := hector.AlgorithmRun(classifier, train, test, "", params)
fmt.Println("AUC:")
fmt.Println(auc)
average_auc += auc
os.Remove(train)
os.Remove(test)
classifier = nil
for _, pred := range predictions {
all_predictions = append(all_predictions, pred)
}
}
all_methods_predictions = append(all_methods_predictions, all_predictions)
fmt.Println(average_auc / float64(total))
classifier := hector.GetClassifier(method)
fmt.Println(test_path)
_, test_predictions, _ := hector.AlgorithmRun(classifier, train_path, test_path, "", params)
all_methods_test_predictions = append(all_methods_test_predictions, test_predictions)
}
var wait sync.WaitGroup
wait.Add(2)
dataset := core.NewDataSet()
go func() {
for i, _ := range all_methods_predictions[0] {
sample := core.NewSample()
sample.Label = all_methods_predictions[0][i].Label
for j, _ := range all_methods_predictions {
feature := core.Feature{Id: int64(j), Value: all_methods_predictions[j][i].Prediction}
sample.AddFeature(feature)
}
dataset.Samples <- sample
}
close(dataset.Samples)
wait.Done()
}()
ensembler := lr.LinearRegression{}
go func() {
ensembler.Init(params)
ensembler.Train(dataset)
wait.Done()
}()
wait.Wait()
fmt.Println(ensembler.Model)
wait.Add(2)
test_dataset := hector.NewDataSet()
go func() {
for i, _ := range all_methods_test_predictions[0] {
sample := hector.NewSample()
sample.Label = all_methods_test_predictions[0][i].Prediction
for j, _ := range all_methods_test_predictions {
feature := hector.Feature{Id: int64(j), Value: all_methods_test_predictions[j][i].Prediction}
sample.AddFeature(feature)
}
test_dataset.Samples <- sample
}
close(test_dataset.Samples)
wait.Done()
}()
go func() {
pred_file, _ := os.Create(test_path + ".out")
for sample := range test_dataset.Samples {
prediction := sample.Label //ensembler.Predict(sample)
pred_file.WriteString(strconv.FormatFloat(prediction, 'g', 5, 64) + "\n")
}
defer pred_file.Close()
wait.Done()
}()
wait.Wait()
}