下面的Go代码读入10,000记录CSV(时间戳times和浮点数values),对数据运行一些操作,然后将原始值写入另一个CSV以及另外一列score.然而它非常慢(即几小时,但大部分都是这样calculateStuff())而且我很好奇,如果我可以处理的CSV读/写有任何低效率.
package main
import (
"encoding/csv"
"log"
"os"
"strconv"
)
func ReadCSV(filepath string) ([][]string, error) {
csvfile, err := os.Open(filepath)
if err != nil {
return nil, err
}
defer csvfile.Close()
reader := csv.NewReader(csvfile)
fields, err := reader.ReadAll()
return fields, nil
}
func main() {
// load data csv
records, err := ReadCSV("./path/to/datafile.csv")
if err != nil {
log.Fatal(err)
}
// write results to a new csv
outfile, err := os.Create("./where/to/write/resultsfile.csv"))
if err != nil {
log.Fatal("Unable to open output")
}
defer outfile.Close()
writer := csv.NewWriter(outfile)
for i, record := range records {
time := record[0]
value := record[1]
// skip header row
if i == 0 {
writer.Write([]string{time, value, "score"})
continue
}
// get float values
floatValue, err := strconv.ParseFloat(value, 64)
if err != nil {
log.Fatal("Record: %v, Error: %v", floatValue, err)
}
// calculate scores; THIS EXTERNAL METHOD CANNOT BE CHANGED
score := calculateStuff(floatValue)
valueString := strconv.FormatFloat(floatValue, 'f', 8, 64)
scoreString := strconv.FormatFloat(prob, 'f', 8, 64)
//fmt.Printf("Result: %v\n", []string{time, valueString, scoreString})
writer.Write([]string{time, valueString, scoreString})
}
writer.Flush()
}
Run Code Online (Sandbox Code Playgroud)
我正在寻找帮助尽快制作这个CSV读/写模板代码.对于这个问题的范围,我们不必担心该calculateStuff方法.
One*_*One 15
您首先将文件加载到内存中然后处理它,这对于大文件来说可能很慢.
您需要一次循环并调用.Read和处理一行.
func processCSV(rc io.Reader) (ch chan []string) {
ch = make(chan []string, 10)
go func() {
r := csv.NewReader(rc)
if _, err := r.Read(); err != nil { //read header
log.Fatal(err)
}
defer close(ch)
for {
rec, err := r.Read()
if err != nil {
if err == io.EOF {
break
}
log.Fatal(err)
}
ch <- rec
}
}()
return
}
Run Code Online (Sandbox Code Playgroud)
//注意它大致基于DaveC的评论.
这基本上是Dave C在评论部分的回答:
package main
import (
"encoding/csv"
"log"
"os"
"strconv"
)
func main() {
// setup reader
csvIn, err := os.Open("./path/to/datafile.csv")
if err != nil {
log.Fatal(err)
}
r := csv.NewReader(csvIn)
// setup writer
csvOut, err := os.Create("./where/to/write/resultsfile.csv"))
if err != nil {
log.Fatal("Unable to open output")
}
w := csv.NewWriter(csvOut)
defer csvOut.Close()
// handle header
rec, err := r.Read()
if err != nil {
log.Fatal(err)
}
rec = append(rec, "score")
if err = w.Write(rec); err != nil {
log.Fatal(err)
}
for {
rec, err = r.Read()
if err != nil {
if err == io.EOF {
break
}
log.Fatal(err)
}
// get float value
value := rec[1]
floatValue, err := strconv.ParseFloat(value, 64)
if err != nil {
log.Fatal("Record, error: %v, %v", value, err)
}
// calculate scores; THIS EXTERNAL METHOD CANNOT BE CHANGED
score := calculateStuff(floatValue)
scoreString := strconv.FormatFloat(score, 'f', 8, 64)
rec = append(rec, scoreString)
if err = w.Write(rec); err != nil {
log.Fatal(err)
}
w.Flush()
}
}
Run Code Online (Sandbox Code Playgroud)
当然注意逻辑是全部卡住的main(),更好的是将它分成几个函数,但这超出了这个问题的范围.
| 归档时间: |
|
| 查看次数: |
18462 次 |
| 最近记录: |