forked from xlvector/hector
/
hector-cv.go
61 lines (53 loc) · 1.3 KB
/
hector-cv.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
package main
import (
"fmt"
"github.com/xlvector/hector"
"github.com/xlvector/hector/core"
"log"
"os"
"runtime/pprof"
"strconv"
)
func SplitFile(dataset *core.DataSet, total, part int) (*core.DataSet, *core.DataSet) {
train := core.NewDataSet()
test := core.NewDataSet()
for i, sample := range dataset.Samples {
if i%total == part {
test.AddSample(sample)
} else {
train.AddSample(sample)
}
}
return train, test
}
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))
}