0
我有大约1 GB的大数据集,需要将其从.txt
转换为.arff
格式。所有来源从.txt
转换为.csv
,然后转换为.arff
,但使用在线转换器时,最大大小为100 MB。任何人都可以帮助我如何转换这1 GB的数据?将.txt中的大数据集转换为.arff格式
我有大约1 GB的大数据集,需要将其从.txt
转换为.arff
格式。所有来源从.txt
转换为.csv
,然后转换为.arff
,但使用在线转换器时,最大大小为100 MB。任何人都可以帮助我如何转换这1 GB的数据?将.txt中的大数据集转换为.arff格式
您可以使用此代码段将txt文件转换为csv。
import java.io.*;
public class Convert {
public static void main(String[] args) {
System.out.println("Initialize ...");
Read read = new Read("soal01.txt");
Print print = new Print();
for (int i = 1; i <= 3; i++) {
try{
print.setFileName("jawaban"+i+".csv");
read.setPrint(print);
read.exec(i);
} catch(IOException ex){
ex.printStackTrace();
}
}
System.out.println("Finished");
}
}
class Print {
protected String fileName;
protected FileWriter writer;
public Print() {}
public Print(String fileName) throws IOException {
this.fileName = fileName;
this.writer = new FileWriter(this.fileName);
}
public String getFileName() {
return this.fileName;
}
public void setFileName(String fileName) throws IOException {
this.fileName = fileName;
this.writer = new FileWriter(this.fileName);
}
public void close() throws IOException {
this.writer.flush();
this.writer.close();
}
public void addRow(String[] c) throws IOException {
int l = c.length;
for(int i = 0; i < l; i++) {
this.writer.append(c[i]);
if(i != (l - 1)) {
this.writer.append(",");
}
}
this.writer.append('\n');
}
}
class Read {
protected String fileName;
protected BufferedReader bufferedReader;
protected Print print;
public Read(String fileName) {
this.fileName = fileName;
}
public Read(Print print, String fileName) {
this.print = print;
this.fileName = fileName;
}
public void setPrint(Print print) {
this.print = print;
}
public Print getPrint() {
return this.print;
}
public void exec(Integer type) {
String sCurrentLine = "";
try{
this.bufferedReader = new BufferedReader(
new FileReader(this.fileName));
while((sCurrentLine = this.bufferedReader.readLine()) != null) {
String[] columns = sCurrentLine.split("\t");
int length = columns.length;
if(type == 1) {
this.print.addRow(columns);
} else if(length >= 2){
double col1 = Double.parseDouble(columns[1]);
if(col1 > 20){
if(type == 2){
this.print.addRow(columns);
} else if(type == 3 && length >= 3 && columns[2] != null){
this.print.addRow(columns);
}
}
}
}
this.print.close();
} catch(IOException ex) {
ex.printStackTrace();
} finally {
try{
if(this.bufferedReader != null) {
this.bufferedReader.close();
}
} catch(IOException ex) {
ex.printStackTrace();
}
}
}
}
谢谢你的帮助,但我运行的代码,并出现以下错误。 异常线程“main” java.lang.NumberFormatException:对于输入字符串:“青少年分享如何基督教影响到他们生活” \t在sun.misc.FloatingDecimal.readJavaFormatString(FloatingDecimal.java:2043) \t在阳光下.misc.FloatingDecimal.parseDouble(FloatingDecimal.java:110) \t在java.lang.Double.parseDouble(Double.java:538) \t在Read.exec(Convert.java:97) \t在Convert.main( Convert.java:12) – medooSa