123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110 |
- package teach
- import (
- "bufio"
- "fmt"
- "log"
- "os"
- "strconv"
- "strings"
- mat "gonum.org/v1/gonum/mat"
- )
- type TextDataReader struct {
- dataSet []*mat.Dense
- result []*mat.Dense
- index int
- }
- func NewTextDataReader(filename string) *TextDataReader {
- r := &TextDataReader{
- index: 0,
- }
- r.readData(filename)
- return r
- }
- func (r *TextDataReader) readData(filename string) {
- inputFile, err := os.Open(filename)
- if err != nil {
- log.Fatal(err)
- }
- defer inputFile.Close()
- scanner := bufio.NewScanner(inputFile)
- scanner.Split(bufio.ScanLines)
- max := []float64{0.0, 0.0, 0.0, 0.0}
- for scanner.Scan() {
- dataLine := scanner.Text()
- data := strings.Split(dataLine, ",")
- if len(data) < 5 {
- fmt.Printf("Garbage record: %s\n", dataLine)
- continue
- }
- var dataRaw []float64
- for i := 0; i < 4; i++ {
- val, err := strconv.ParseFloat(data[i], 64)
- if err != nil {
- break
- }
- dataRaw = append(dataRaw, val)
- if max[i] < val {
- max[i] = val
- }
- }
- if len(dataRaw) < 4 {
- fmt.Printf("Garbage record: %s\n", dataLine)
- continue
- }
- r.dataSet = append(r.dataSet, mat.NewDense(4, 1, dataRaw))
- switch data[4] {
- case "Iris-setosa":
- r.result = append(r.result, mat.NewDense(3, 1, []float64{1.0, 0.0, 0.0}))
- case "Iris-versicolor":
- r.result = append(r.result, mat.NewDense(3, 1, []float64{0.0, 1.0, 0.0}))
- case "Iris-virginica":
- r.result = append(r.result, mat.NewDense(3, 1, []float64{0.0, 0.0, 1.0}))
- }
- }
-
- for i := 0; i < len(r.dataSet); i++ {
- r.dataSet[i].Apply(func(r, _ int, val float64) float64 {
- return val / max[r]
- }, r.dataSet[i])
- }
- }
- func (r *TextDataReader) GetData() *mat.Dense {
- return r.dataSet[r.index]
- }
- func (r *TextDataReader) GetExpect() *mat.Dense {
- return r.result[r.index]
- }
- func (r *TextDataReader) Next() bool {
- r.index++
- if r.index >= len(r.result) {
- r.index = 0
- return false
- }
- return true
- }
- func (r *TextDataReader) Reset() {
- r.index = 0
- }
- func (r *TextDataReader) Index() int {
- return r.index
- }
|