package com.delhi;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class UppercaseDriver extends Configured implements Tool {
public int run(String[] args) throws Exception{
if(args.length !=2){
System.out.printf("Two parameters are required- <input dir> <output dir>n");
return -1;}
Configuration conf = new Configuration();
Job job=Job.getInstance(conf);
job.setJobName("uppercase");
job.setJarByClass(UppercaseDriver.class);
job.setMapperClass(UpperCaseMapper.class);
job.setReducerClass(UpperCaseReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job,new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
//job.setNumReduceTasks(1);
boolean success = job.waitForCompletion(true);
return success ?0:1;
}
public static void main(String[] args) throws Exception {
int exitcode = ToolRunner.run(new UppercaseDriver(), args);
System.exit(exitcode);
}
}
這是驅動程序。減速器在mapreduce wordcount程序中沒有被驅動程序調用
接下來就是減速程序:
package com.delhi;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class UpperCaseReduce extends Reducer< Text,LongWritable, Text, LongWritable>{
public void reduce(Text key, Iterable<LongWritable> value,
org.apache.hadoop.mapreduce.Reducer.Context context)
throws IOException, InterruptedException {
int sum=0;
System.out.println("how +++++++++++++++++" + key);
for(LongWritable st: value){
sum = (int) (sum + st.get());
}
System.out.println("how +++++++++++++++++" + key);
context.write(key, new LongWritable(sum));
}
}
接下來就是映射器程序:
package com.delhi;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class UpperCaseMapper extends Mapper<Object, Text, Text, LongWritable>{
@Override
protected void map(Object key, Text value,
org.apache.hadoop.mapreduce.Mapper.Context context)
throws IOException, InterruptedException {
String line = value.toString();
String arr[] = line.split(" ");
System.out.println("hello++++++++++++++++++++++++++++");
for(String st: arr){
//context.write(new Text(st.toUpperCase().trim()),new LongWritable(1));
context.write(new Text(st),new LongWritable(1));
}
}
}
從已經存在的解決方案,我發現了,在這類問題outputkeyclass和outputvalueclass的應與減速機。我認爲我採取妥善妥善的部分。我的情況@Override for reduce不起作用。我正在使用hadoop 7.2.3。我也嘗試使用修剪功能。問題是wordcount不會發生。我只給我「單詞1」,輸出文件中的任何單詞。 我從不同的問題開始,我就這樣結束了。請幫助我。 謝謝。
確實很難設法解決你的問題。你有錯誤嗎?減速機是否在運轉?問一個問題,並明確你遇到的問題。 –
感謝您的回覆。我得到這樣的輸出:1 1個 文件1個 文件1 文件1 1 是1 爲1 爲1 所以,簡單的字計數不working.My問題是爲什麼?我認爲減速機不工作。 – Angshusuri
請編輯問題以使其更具可讀性。從問題開始,然後發佈代碼,然後添加您希望的任何細節。添加您以前的評論作爲問題的一部分。 – vefthym