第四章习题答案

答案1. 选择题(1) D解释：A，B，C都可以。(2) A解释：单词折分是通过调用类StringTokenizer实现，单词在mapper中映射为（word,one）。(3) B解释：排序发生在数据混洗阶段。(4) C解释：setInputFormat。(5) D解释：“Alice”对应Text，89.5对应Double类型，组合输出为（Text,Double）(6) A解释：自定义Mapper模块必须继承Mapper。(7) C(8) B解释：setup，reduce，cleanup。(9) B解释：输出的键值对默认按KEY的ASCII码进行排序。(10) B解释：可省略Mapper端的输出格式设置。2. 操作题(1) 使用有短句“A friend in need is a friend in deed”，画出使用MapReduce对它进行词频统计的过程，主要展示Map阶段与Reduce阶段的处理过程。如图 1所示。图 1 MapReduce词频统计过程(2) 具体实现代码如代码 1所示。代码 1 实现代码 HadoopCount.java内容package test;import java.io.IOException;import java.util.StringTokenizer;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.util.GenericOptionsParser;public class HadoopCount public static class MyMapper extends Mapper private final static IntWritable one = new IntWritable(1);private String str; private Text word=new Text(); public void map(Object key, Text value, Context context ) throws IOException, InterruptedException StringTokenizer itr = new StringTokenizer(value.toString(); while (itr.hasMoreTokens() str=itr.nextToken(); if(str.equals(Hadoop)word.set(str); context.write(word, one); public static class MyReducer extends Reducer private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable values, Context context ) throws IOException, InterruptedException int sum = 0; for (IntWritable val : values) sum += val.get(); result.set(sum); context.write(key,result); public static void main(String args) throws Exception Configuration conf = new Configuration(); String otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length 2) System.err.println(Usage: wordcount . ); System.exit(2); Job job = new Job(conf, Word Hadoop Count); job.setJarByClass(HadoopCount.class); job.setMapperClass(MyMapper.class); job.setReducerClass(MyReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); for (int i = 0; i otherArgs.length - 1; +i) FileInputFormat.addInputPath(job, new Path(otherArgsi);