025_MapReduce样例Hadoop TopKey算法
1、需求说明
2、 某个文件中某列数据的最大值。
思路：对每一个列的值依次进行比较，保存最大的值进行输出，算法的思想类似于排序算法（快速和冒泡排序）。
Mapper：因为只是在wordcount统计的基础上统计的，只是针对一个列，故可以找到最大值后，将最大值和对应的text给，cleanup中的context.write（）方法，然后输出。此时不需要Reducer。
1 package org.dragon.hadoop.mapreduce.app.topk; 2 3 import java.io.IOException; 4 5 import org.apache.hadoop.conf.Configuration; 6 import org.apache.hadoop.fs.Path; 7 import org.apache.hadoop.io.LongWritable; 8 import org.apache.hadoop.io.Text; 9 import org.apache.hadoop.mapreduce.Job; 10 import org.apache.hadoop.mapreduce.Mapper; 11 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 12 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 13 14 /** 15 * 功能：某个文件中某列数据的最大值某个文件中 16 * 17 * 针对wordcount程序输出的单词统计信息，求出单词出现频率最高的那个。 即：求给定的键值对中，value的最大值 18 * @author ZhuXY 19 * @time 2016-3-12 下午3:43:23 20 * 21 */ 22 public class TopKMapReduce { 23 24 /* 25 * ****************************************************** 26 * 这个程序很好解释了splitsize对应一个map task，而一行数据对应一个map()函数。 即一个map task对应几个map（）函数 27 * ****************************************************** 28 */ 29 30 // Mapper class 31 static class TopKMapper extends 32 Mapper<LongWritable, Text, Text, LongWritable> { 33 // map output key 34 private Text mapOutputKey = new Text();//java的变量（对象）使用前一定要先创建 35 36 // map output value 37 private LongWritable mapOutputValue = new LongWritable(); 38 39 /* 40 * ******************************** 41 * 此处创建对所有的map()函数有效 42 * ******************************* 43 */ 44 45 46 // store max value,init long.MIN_VALUE 47 private long topKValue = Long.MIN_VALUE; 48 49 @Override 50 protected void map(LongWritable key, Text value, Context context) 51 throws IOException, InterruptedException { 52 // get value 53 String lineValue =value.toString(); 54 String[] str = lineValue.split("\t"); 55 56 Long tempValue = Long.valueOf(str[1]); 57 58 // comparator 59 if (topKValue < tempValue) { 60 topKValue = tempValue; 61 // set mapout key当找到相对的最大值给topKValue时，将该单词同时赋值给输出key 62 mapOutputKey.set(str[0]); 63 } 64 65 // 此处的context不需要填写，查看源码发现context是个内部类，源码中是由cleanup负责处理 66 } 67 68 @Override 69 protected void setup(Context context) throws IOException, 70 InterruptedException { 71 super.setup(context); 72 } 73 74 @Override 75 protected void cleanup(Context context) throws IOException, 76 InterruptedException { 77 // set map output value 78 mapOutputValue.set(topKValue); 79 80 // set mapoutput context 81 context.write(mapOutputKey, mapOutputValue); 82 } 83 } 84 85 // Driver Code 86 public int run(String[] args) throws Exception, IOException, 87 InterruptedException { 88 // get conf 89 Configuration conf = new Configuration(); 90 91 // create job 92 Job job = new Job(conf, TopKMapReduce.class.getSimpleName()); 93 94 // set job 95 job.setJarByClass(TopKMapReduce.class); 96 // 1) input 97 Path inputDirPath = new Path(args[0]); 98 FileInputFormat.addInputPath(job, inputDirPath); 99 100 // 2) map 101 job.setMapperClass(TopKMapper.class); 102 job.setMapOutputKeyClass(Text.class); 103 job.setMapOutputValueClass(LongWritable.class); 104 105 // 3) reduce 106 // job.setReducerClass(DataTotalReducer.class); 107 // job.setOutputKeyClass(Text.class); 108 // job.setOutputValueClass(DataWritable.class); 109 job.setNumReduceTasks(0);// 因为本程序没有Reducer的过程，这里必须设置为0 110 111 // 4) output 112 Path outputDir = new Path(args[1]); 113 FileOutputFormat.setOutputPath(job, outputDir); 114 115 // submit job 116 boolean isSuccess = job.waitForCompletion(true); 117 118 // return status 119 return isSuccess ? 0 : 1; 120 } 121 122 // run mapreduce 123 public static void main(String[] args) throws Exception, IOException, 124 InterruptedException { 125 // set args 126 args = new String[] { "hdfs://hadoop-master:9000/wc/wcoutput", 127 "hdfs://hadoop-master:9000/wc/output" }; 128 129 // run job 130 int status = new TopKMapReduce().run(args); 131 // exit 132 System.exit(status); 133 } 134 135 }
3、 某个文件某列数据的Top Key的值（最大或者最小）
思路：用一个TreeMap保存，TreeMap可以自动根据Key排序，故将出现的次数当做Key进行hash存储。然后TreeMap.size()>NUM时,删除最小的就行了。
Mapper：在原有的基础上增加TreeMap
1 package org.dragon.hadoop.mapreduce.app.topk; 2 3 import java.io.IOException; 4 import java.util.Iterator; 5 import java.util.Set; 6 import java.util.TreeMap; 7 8 import org.apache.hadoop.conf.Configuration; 9 import org.apache.hadoop.fs.Path; 10 import org.apache.hadoop.io.LongWritable; 11 import org.apache.hadoop.io.Text; 12 import org.apache.hadoop.mapreduce.Job; 13 import org.apache.hadoop.mapreduce.Mapper; 14 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 15 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 16 17 import com.sun.org.apache.bcel.internal.generic.NEW; 18 19 /** 20 * 功能：某列的TopKey的值，即最大（小）的几个。K小值问题 21 * 22 * @author ZhuXY 23 * @time 2016-3-12 下午3:43:23 24 * 25 */ 26 public class TopKMapReduceV2 { 27 28 /* 29 * 思想：用一個集合TreeSet存儲對應的鍵值對，然後當大於三個的時候進行刪除。 30 * 该集合自动按照键进行排序，然后保留最大的三个 31 * 注意：集合 key value 32 * 真是 value key 33 */ 34 35 // Mapper class 36 static class TopKMapper extends 37 Mapper<LongWritable, Text, Text, LongWritable> { 38 39 // 用作保存TopKey的键和值 40 private TreeMap<Long, String> topKTreeMap = new TreeMap<Long, String>(); 41 42 @Override 43 protected void map(LongWritable key, Text value, Context context) 44 throws IOException, InterruptedException { 45 // get value 46 String lineValue = value.toString(); 47 String[] str = lineValue.split("\t"); 48 49 long tempKey = Long.valueOf(str[1]); 50 String tempValue = String.valueOf(str[0]); 51 52 topKTreeMap.put(tempKey, tempValue); 53 if (topKTreeMap.size() > 3) { 54 topKTreeMap.remove(topKTreeMap.firstKey()); 55 } 56 } 57 58 @Override 59 protected void setup(Context context) throws IOException, 60 InterruptedException { 61 super.setup(context); 62 } 63 64 @Override 65 protected void cleanup(Context context) throws IOException, 66 InterruptedException { 67 Set<Long> mapValueSet = topKTreeMap.keySet();// long 名字起得不好 68 69 Text mapOutputKey = new Text(); 70 LongWritable mapOutputValue = new LongWritable(); 71 72 // for (Iterator<Long> iterator = mapValueSet.iterator(); iterator 73 // .hasNext();) { 74 // 75 // long iteratorNum=iterator.next(); 76 // mapOutputValue.set(iteratorNum);// long 77 // mapOutputKey.set(topKTreeMap.get(iteratorNum)); 78 // 79 // context.write(mapOutputKey, mapOutputValue); 80 // } 81 82 for(long key:mapValueSet){ 83 mapOutputValue.set(key);// long 84 mapOutputKey.set(topKTreeMap.get(key)); 85 86 context.write(mapOutputKey, mapOutputValue); 87 } 88 } 89 } 90 91 // Driver Code 92 public int run(String[] args) throws Exception, IOException, 93 InterruptedException { 94 // get conf 95 Configuration conf = new Configuration(); 96 97 // create job 98 Job job = new Job(conf, TopKMapReduceV2.class.getSimpleName()); 99 100 // set job 101 job.setJarByClass(TopKMapReduceV2.class); 102 // 1) input 103 Path inputDirPath = new Path(args[0]); 104 FileInputFormat.addInputPath(job, inputDirPath); 105 106 // 2) map 107 job.setMapperClass(TopKMapper.class); 108 job.setMapOutputKeyClass(Text.class); 109 job.setMapOutputValueClass(LongWritable.class); 110 111 // 3) reduce 112 // job.setReducerClass(DataTotalReducer.class); 113 // job.setOutputKeyClass(Text.class); 114 // job.setOutputValueClass(DataWritable.class); 115 job.setNumReduceTasks(0);// 因为本程序没有Reducer的过程，这里必须设置为0 116 117 // 4) output 118 Path outputDir = new Path(args[1]); 119 FileOutputFormat.setOutputPath(job, outputDir); 120 121 // submit job 122 boolean isSuccess = job.waitForCompletion(true); 123 124 // return status 125 return isSuccess ? 0 : 1; 126 } 127 128 // run mapreduce 129 public static void main(String[] args) throws Exception, IOException, 130 InterruptedException { 131 // set args 132 args = new String[] { "hdfs://hadoop-master:9000/wc/wcoutput", 133 "hdfs://hadoop-master:9000/wc/output1" }; 134 135 // run job 136 int status = new TopKMapReduceV2().run(args); 137 // exit 138 System.exit(status); 139 } 140 141 }
4、 多个文件中某列数据的Top Key的值（最大或者最小）
思路：此处因为是多个文件，故Reducer至少且只能为1个，即default也就是1个。将TreeMap放在Reducer内部的reduce函数进行处理。
1 package org.dragon.hadoop.mapreduce.app.topk; 2 3 import java.io.IOException; 4 import java.util.Iterator; 5 import java.util.Set; 6 import java.util.TreeMap; 7 8 import org.apache.hadoop.conf.Configuration; 9 import org.apache.hadoop.fs.Path; 10 import org.apache.hadoop.io.IntWritable; 11 import org.apache.hadoop.io.LongWritable; 12 import org.apache.hadoop.io.Text; 13 import org.apache.hadoop.mapreduce.Job; 14 import org.apache.hadoop.mapreduce.Mapper; 15 import org.apache.hadoop.mapreduce.Mapper.Context; 16 import org.apache.hadoop.mapreduce.Reducer; 17 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 18 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 19 import org.eclipse.core.internal.filesystem.local.Convert; 20 21 import com.sun.org.apache.bcel.internal.generic.NEW; 22 23 /** 24 * 功能：多个文件中某列数据和的最大值 25 * 26 * 思想：类似wordcount，把每行数据统计好，context出去---mapper 27 * 接收到经过shuffle和merge形成<key,list<1,2,3,4…>>----透明 28 * 在cleanup中，收集reduce中的TreeMap集合，进行排序删除-------reduce、cleanup 29 * 30 * @author ZhuXY 31 * @time 2016-3-12 下午3:43:23 32 * 33 */ 34 public class TopKMapReduceV3 { 35 36 /* 37 * 思想：用一個集合TreeSet存儲對應的鍵值對，然後當大於三個的時候進行刪除。 38 * 该集合自动按照键进行排序，然后保留最大的三个 39 * 注意：集合 key value 40 * 真是 value key 41 */ 42 43 // Mapper class 44 static class TopKMapper extends 45 Mapper<LongWritable, Text, Text, LongWritable> { 46 47 Text mapOutputKey=new Text(); //key 48 LongWritable mapOutputValue=new LongWritable();//value 49 50 @Override 51 protected void map(LongWritable key, Text value, Context context) 52 throws IOException, InterruptedException { 53 // get value 54 String lineValue = value.toString(); 55 String[] str = lineValue.split("\t"); 56 57 mapOutputKey.set(str[0]); 58 59 mapOutputValue.set(Long.parseLong(str[1])); 60 61 context.write(mapOutputKey, mapOutputValue); 62 63 } 64 } 65 66 static class TopKReducer extends 67 Reducer<Text, LongWritable, Text, LongWritable>{ 68 69 70 71 // 用作保存TopKey的键和值 72 private TreeMap<Long, String> topKTreeMap = new TreeMap<Long, String>(); 73 74 @Override 75 protected void reduce(Text key, Iterable<LongWritable> values,Context context) 76 throws IOException, InterruptedException { 77 int sum=0; 78 //循环遍历Interable 79 for(LongWritable value:values) 80 { 81 //累加 82 sum+=value.get(); 83 } 84 85 long tempKey = Long.valueOf(sum); 86 String tempValue = String.valueOf(key); 87 88 topKTreeMap.put(tempKey, tempValue); 89 if (topKTreeMap.size() > 3) { 90 topKTreeMap.remove(topKTreeMap.firstKey()); 91 } 92 } 93 94 @Override 95 protected void cleanup(Context context) 96 throws IOException, InterruptedException { 97 98 //TreeMap键的集合 99 Set<Long> mapValueSet = topKTreeMap.keySet();// long 名字起得不好 100 101 Text mapOutputKey = new Text(); 102 LongWritable mapOutputValue = new LongWritable(); 103 104 //根据键，获取值，并交叉赋予context中参数 105 for(long key:mapValueSet){ 106 mapOutputValue.set(key);// long 107 mapOutputKey.set(topKTreeMap.get(key)); 108 109 context.write(mapOutputKey, mapOutputValue); 110 } 111 } 112 113 } 114 115 // Driver Code 116 public int run(String[] args) throws Exception, IOException, 117 InterruptedException { 118 // get conf 119 Configuration conf = new Configuration(); 120 121 // create job 122 Job job = new Job(conf, TopKMapReduceV3.class.getSimpleName()); 123 124 // set job 125 job.setJarByClass(TopKMapReduceV3.class); 126 // 1) input 127 Path inputDirPath = new Path(args[0]); 128 FileInputFormat.addInputPath(job, inputDirPath); 129 130 // 2) map 131 job.setMapperClass(TopKMapper.class); 132 job.setMapOutputKeyClass(Text.class); 133 job.setMapOutputValueClass(LongWritable.class); 134 135 // 3) reduce 136 job.setReducerClass(TopKReducer.class); 137 job.setOutputKeyClass(Text.class); 138 job.setOutputValueClass(LongWritable.class); 139 //job.setNumReduceTasks(0);// default 1 140 141 // 4) output 142 Path outputDir = new Path(args[1]); 143 FileOutputFormat.setOutputPath(job, outputDir); 144 145 // submit job 146 boolean isSuccess = job.waitForCompletion(true); 147 148 // return status 149 return isSuccess ? 0 : 1; 150 } 151 152 // run mapreduce 153 public static void main(String[] args) throws Exception, IOException, 154 InterruptedException { 155 // set args 156 args = new String[] { "hdfs://hadoop-master:9000/wc/wcinput", 157 "hdfs://hadoop-master:9000/wc/output2" }; 158 159 // run job 160 int status = new TopKMapReduceV3().run(args); 161 // exit 162 System.exit(status); 163 } 164 165 }
5、 统计和Top Key
思路：这个比较难。没有在统计好的基础上进行操作，而是直接统计，然后进行比较。具体看下面应用
数据格式：
语言类别 歌曲名称 收藏次数 播放次数 歌手名称
需求：
统计前十首播放次数最多的歌曲名称和次数。
测试数据：
经典老歌 我只在乎你 1234 34535 邓丽君
流行歌曲 流着泪说分手 125 2342 金志文
流行歌曲 菠萝菠萝蜜 543 536 谢娜
经典老歌 大花轿 123 3465 火风
流行歌曲 无所谓 3453 87654 杨坤
定义一个数据类型TopKWritable：
1 package org.dragon.hadoop.mapreduce.app.topk; 2 3 import java.io.DataInput; 4 import java.io.DataOutput; 5 import java.io.IOException; 6 7 import org.apache.hadoop.io.WritableComparable; 8 9 /** 10 * 11 * @author ZhuXY 12 * @time 2016-3-13 下午7:30:21 13 * 14 */ 15 16 /** 17 * 18 * 数据格式： 19 * 语言类别 歌曲名称 收藏次数 播放次数 歌手名称 20 * 需求： 21 * 统计前十首播放次数最多的歌曲名称和次数。 22 */ 23 public class TopKWritable implements WritableComparable<TopKWritable>{ 24 private String languageType=null; 25 private String songName=null; 26 private long playNum=0; 27 28 public TopKWritable(){ 29 30 } 31 public TopKWritable(String languageType,String songName,long playNum){ 32 set(languageType, songName, playNum); 33 } 34 public void set(String languageType,String songName,Long playNum){ 35 this.languageType=languageType; 36 this.songName=songName; 37 this.playNum=playNum; 38 } 39 40 public String getLanguageType() { 41 return languageType; 42 } 43 public String getSongName() { 44 return songName; 45 } 46 public Long getPlayNum() { 47 return playNum; 48 } 49 50 @Override 51 public void write(DataOutput out) throws IOException { 52 out.writeUTF(languageType); 53 out.writeUTF(songName); 54 out.writeLong(playNum); 55 } 56 57 @Override 58 public void readFields(DataInput in) throws IOException { 59 this.languageType=in.readUTF(); 60 this.songName=in.readUTF(); 61 this.playNum=in.readLong(); 62 } 63 64 @Override 65 public int compareTo(TopKWritable o) { 66 67 //此处-1是为了在输出的时候是按照从大到小的次序输出 68 return -this.getPlayNum().compareTo(o.getPlayNum()); 69 } 70 71 @Override 72 public String toString() { 73 return languageType + "\t" 74 + songName + "\t" 75 + playNum; 76 } 77 78 @Override 79 public int hashCode() { 80 final int prime = 31; 81 int result = 1; 82 result = prime * result 83 + ((languageType == null) ? 0 : languageType.hashCode()); 84 result = prime * result + (int) (playNum ^ (playNum >>> 32)); 85 result = prime * result 86 + ((songName == null) ? 0 : songName.hashCode()); 87 return result; 88 } 89 90 @Override 91 public boolean equals(Object obj) { 92 if (this == obj) 93 return true; 94 if (obj == null) 95 return false; 96 if (getClass() != obj.getClass()) 97 return false; 98 TopKWritable other = (TopKWritable) obj; 99 if (languageType == null) { 100 if (other.languageType != null) 101 return false; 102 } else if (!languageType.equals(other.languageType)) 103 return false; 104 if (playNum != other.playNum) 105 return false; 106 if (songName == null) { 107 if (other.songName != null) 108 return false; 109 } else if (!songName.equals(other.songName)) 110 return false; 111 return true; 112 } 113 }
正式的Mapper和Reducer类;
1 package org.dragon.hadoop.mapreduce.app.topk; 2 3 import java.io.IOException; 4 import java.util.Iterator; 5 import java.util.TreeMap; 6 import java.util.TreeSet; 7 8 import javax.security.auth.callback.LanguageCallback; 9 10 import org.apache.hadoop.classification.InterfaceAudience.Private; 11 import org.apache.hadoop.conf.Configuration; 12 import org.apache.hadoop.fs.Path; 13 import org.apache.hadoop.io.LongWritable; 14 import org.apache.hadoop.io.NullWritable; 15 import org.apache.hadoop.io.Text; 16 import org.apache.hadoop.mapreduce.Job; 17 import org.apache.hadoop.mapreduce.Mapper; 18 import org.apache.hadoop.mapreduce.Reducer; 19 import org.apache.hadoop.mapreduce.Mapper.Context; 20 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 21 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 22 import org.dragon.hadoop.mapreduce.app.topk.TopKMapReduceV3.TopKReducer; 23 24 import com.sun.jersey.core.header.LanguageTag; 25 26 import sun.reflect.LangReflectAccess; 27 28 /** 29 * 30 * @author ZhuXY 31 * @time 2016-3-13 下午12:57:26 32 * 33 */ 34 35 /** 36 * 统计 & TopKey 37 * 38 * 数据格式： 语言类别 歌曲名称 收藏次数 播放次数 歌手名称 需求： 统计前十首播放次数最多的歌曲名称和次数。 39 * 40 * 思想:在Mapper中输出：key---歌曲类型+歌曲名称 41 * value---播放次数 42 * Reducer中：key----封装成TopKWritable对象 43 * value---nullwritable 44 * reduce方法中进行集合存储，然后删除多余的 45 * 46 */ 47 public class TopKMapReduceV4 { 48 private static final int KEY = 4; 49 50 // Mapper class 51 public static class TopKMapper extends 52 Mapper<LongWritable, Text, Text, LongWritable> { 53 54 @Override 55 protected void cleanup(Context context) throws IOException, 56 InterruptedException { 57 super.cleanup(context); 58 } 59 60 @Override 61 protected void map(LongWritable key, Text value, Context context) 62 throws IOException, InterruptedException { 63 //文件的输入类型为TextInputFormat，默认到map中的为<Longwritable,Text> 64 String lineValue = value.toString(); 65 66 if (null == lineValue) { 67 return; 68 } 69 70 //split 71 String[] splitValue = lineValue.split("\t"); 72 73 if (splitValue != null && splitValue.length == 5) { 74 String languageType = splitValue[0]; 75 String songName = splitValue[1]; 76 Long playNum = Long.parseLong(splitValue[3]); 77 78 context.write(new Text(languageType + "\t" + songName), 79 new LongWritable(playNum)); 80 } 81 } 82 83 @Override 84 protected void setup(Context context) throws IOException, 85 InterruptedException { 86 // TODO Auto-generated method stub 87 super.setup(context); 88 } 89 } 90 91 // Reducer class 92 public static class TopKReducer extends 93 Reducer<Text, LongWritable, TopKWritable, NullWritable> { 94 95 //此集合的排序规则即为TopKWritable中comparaTo的排序规则 96 TreeSet<TopKWritable> treeSet=new TreeSet<TopKWritable>(); 97 98 @Override 99 protected void setup(Context context) 100 throws IOException, InterruptedException { 101 // TODO Auto-generated method stub 102 super.setup(context); 103 } 104 105 @Override 106 protected void reduce(Text key, Iterable<LongWritable> values, 107 Context context) throws IOException, InterruptedException { 108 109 Long palyNum=(long) 0; 110 if (key==null) { 111 return; 112 } 113 114 //get key 115 String[] keyArr=key.toString().split("\t"); 116 String languageType=keyArr[0]; 117 String songName=keyArr[1]; 118 119 //sum 120 for(LongWritable value:values){ 121 palyNum+=value.get(); 122 } 123 124 //歌曲类型、歌曲名称、歌曲播放次数封装成TopKWritable对象，保存在treeSet集合中，此集合自动排序 125 treeSet.add(new TopKWritable( 126 languageType,songName,palyNum 127 )); 128 129 if (treeSet.size()>KEY) { 130 treeSet.remove(treeSet.last());//remove the current small longNum 131 } 132 } 133 134 @Override 135 protected void cleanup(Context context) 136 throws IOException, InterruptedException { 137 for (TopKWritable topKWritable : treeSet) { 138 context.write(topKWritable,NullWritable.get()); 139 } 140 } 141 142 143 } 144 // Driver Code 145 public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException { 146 // get conf 147 Configuration conf=new Configuration(); 148 149 // create job 150 Job job =new Job(conf, TopKMapReduceV4.class.getSimpleName());//Job name 151 152 // set job 153 job.setJarByClass(TopKMapReduceV4.class); 154 155 // 1)set inputPath 156 FileInputFormat.addInputPath(job, new Path(args[0])); 157 158 // 2)set map 159 job.setMapperClass(TopKMapper.class); 160 job.setMapOutputKeyClass(Text.class); 161 job.setMapOutputValueClass(LongWritable.class); 162 163 // 3)set outputPath 164 FileOutputFormat.setOutputPath(job, new Path(args[1])); 165 166 // 4)set reduce 167 job.setReducerClass(TopKReducer.class); 168 job.setOutputKeyClass(TopKWritable.class); 169 job.setOutputValueClass(NullWritable.class); 170 171 // submit job 172 boolean isSuccess=job.waitForCompletion(true); 173 174 //return status 175 return isSuccess?0:1; 176 } 177 178 public static void main(String[] args) throws IOException, InterruptedException, Exception { 179 180 args=new String[]{ 181 "hdfs://hadoop-master.dragon.org:9000/wc/wcinput/", 182 "hdfs://hadoop-master.dragon.org:9000/wc/wcoutput" 183 }; 184 int status =new TopKMapReduceV4().run(args); 185 System.exit(status); 186 } 187 }