forked from ze2o/golearn
/
util.go
83 lines (75 loc) · 2.2 KB
/
util.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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
package linear_models
import (
"fmt"
"github.com/rdbell/golearn/base"
)
func generateClassWeightVectorFromDist(X base.FixedDataGrid) []float64 {
classDist := base.GetClassDistributionByBinaryFloatValue(X)
ret := make([]float64, len(classDist))
for i, c := range classDist {
if c == 0 {
ret[i] = 1.0
} else {
ret[i] = 1.0 / float64(c)
}
}
return ret
}
func generateClassWeightVectorFromFixed(X base.FixedDataGrid) []float64 {
classAttrs := X.AllClassAttributes()
if len(classAttrs) != 1 {
panic("Wrong number of class Attributes")
}
if _, ok := classAttrs[0].(*base.FloatAttribute); ok {
ret := make([]float64, 2)
for i := range ret {
ret[i] = 1.0
}
return ret
} else {
panic("Must be a FloatAttribute")
}
}
func convertInstancesToProblemVec(X base.FixedDataGrid) [][]float64 {
// Allocate problem array
_, rows := X.Size()
problemVec := make([][]float64, rows)
// Retrieve numeric non-class Attributes
numericAttrs := base.NonClassFloatAttributes(X)
numericAttrSpecs := base.ResolveAttributes(X, numericAttrs)
// Convert each row
X.MapOverRows(numericAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
// Allocate a new row
probRow := make([]float64, len(numericAttrSpecs))
// Read out the row
for i, _ := range numericAttrSpecs {
probRow[i] = base.UnpackBytesToFloat(row[i])
}
// Add the row
problemVec[rowNo] = probRow
return true, nil
})
return problemVec
}
func convertInstancesToLabelVec(X base.FixedDataGrid) []float64 {
// Get the class Attributes
classAttrs := X.AllClassAttributes()
// Only support 1 class Attribute
if len(classAttrs) != 1 {
panic(fmt.Sprintf("%d ClassAttributes (1 expected)", len(classAttrs)))
}
// ClassAttribute must be numeric
if _, ok := classAttrs[0].(*base.FloatAttribute); !ok {
panic(fmt.Sprintf("%s: ClassAttribute must be a FloatAttribute", classAttrs[0]))
}
// Allocate return structure
_, rows := X.Size()
labelVec := make([]float64, rows)
// Resolve class Attribute specification
classAttrSpecs := base.ResolveAttributes(X, classAttrs)
X.MapOverRows(classAttrSpecs, func(row [][]byte, rowNo int) (bool, error) {
labelVec[rowNo] = base.UnpackBytesToFloat(row[0])
return true, nil
})
return labelVec
}