package main

import (
	"bufio"
	"fmt"
	"log"
	"os"
	"strconv"
	"strings"

	mat "gonum.org/v1/gonum/mat"
)

func readData(filename string) (dataSet, result []*mat.Dense) {
	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
		}
		dataSet = append(dataSet, mat.NewDense(4, 1, dataRaw))

		switch data[4] {
		case "Iris-setosa":
			result = append(result, mat.NewDense(3, 1, []float64{1.0, 0.0, 0.0}))
		case "Iris-versicolor":
			result = append(result, mat.NewDense(3, 1, []float64{0.0, 1.0, 0.0}))
		case "Iris-virginica":
			result = append(result, mat.NewDense(3, 1, []float64{0.0, 0.0, 1.0}))
		}
	}

	//normalize
	for i := 0; i < len(dataSet); i++ {
		dataSet[i].Apply(func(r, _ int, val float64) float64 {
			return val / max[r]
		}, dataSet[i])
	}

	return
}