topk代码

1、生成随机数代码：

[java] view plain copy print?

1. package test;  
2.   
3.   
4. import java.util.Random;  
5.   
6.   
7. public class RandomTest {  
8.      public static void main(String[] args){          
9.          int number=0;  
10.          for (int i = 0; i < 100000; i++) {  
11.               number = new Random().nextInt(100000) + 1;  
12.              System.out.println(number);  
13.         }  
14.     }  
15. }  

2、生成部分数据如下所示：

[java] view plain copy print?

1. [hadoop@hadoop ~]$ tail -10 top_k.txt  
2. 16287  
3. 86786  
4. 63942  
5. 5960  
6. 87524  
7. 53898  
8. 81409  
9. 92020  
10. 68327  
11. 92706  
12. [hadoop@hadoop ~]$  

3、代码：

[java] view plain copy print?

1. package test;  
2.   
3.   
4. import java.io.IOException;  
5. import java.util.TreeMap;  
6. import org.apache.hadoop.conf.Configuration;  
7. import org.apache.hadoop.fs.Path;  
8. import org.apache.hadoop.io.LongWritable;  
9. import org.apache.hadoop.io.NullWritable;  
10. import org.apache.hadoop.io.Text;  
11. import org.apache.hadoop.mapreduce.Job;  
12. import org.apache.hadoop.mapreduce.Mapper;  
13. import org.apache.hadoop.mapreduce.Reducer;  
14. import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;  
15. import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;  
16. import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;  
17. import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;  
18.   
19.   
20. public class Topk {  
21. /** 
22. * map方法 
23. */  
24. private static final int k=10;  
25. public static class MyMapper extends Mapper<LongWritable, Text, LongWritable, Text>{   
26. LongWritable lw=new LongWritable();  
27. Text text=new Text();  
28. TreeMap<Long, String > treemap_mapper=new TreeMap<Long, String>();  
29. @Override  
30. protected void map(LongWritable key, Text value,Context context)  
31. throws IOException, InterruptedException {  
32. String line=value.toString();  
33. String[] splited=line.split("\t");  
34.   
35. treemap_mapper.put(Long.parseLong(splited[0]), line);  
36.   
37. if(treemap_mapper.size()>k){  
38. treemap_mapper.remove(treemap_mapper.firstKey());  
39. }  
40.   
41. }  
42.   
43. @Override  
44. protected void cleanup(Context context)  
45. throws IOException, InterruptedException {  
46.   
47. for (Long numLong : treemap_mapper.keySet()) {  
48. context.write(new LongWritable(numLong), new Text(treemap_mapper.get(numLong)));  
49. }  
50. }  
51.   
52. }  
53.   
54. /** 
55. * reducer方法 
56. * @author Administrator 
57. * 
58. */  
59. public static class MyReducer extends Reducer<LongWritable, Text, LongWritable, NullWritable>{  
60. TreeMap<Long, String> treemap_reducer=new TreeMap<Long, String>();  
61. @Override  
62. protected void reduce(LongWritable k2,Iterable<Text> v2s,Context context)  
63. throws IOException, InterruptedException {  
64. treemap_reducer.put(k2.get(), v2s.iterator().next().toString());  
65.   
66. if(treemap_reducer.size()>k){   
67. treemap_reducer.remove(treemap_reducer.firstKey());  
68. }  
69. }  
70.   
71. @Override  
72. protected void cleanup(Context context)  
73. throws IOException, InterruptedException {  
74. Long[] outLong=new Long[10];  
75. int flag=0;  
76. for (Long numLong : treemap_reducer.keySet()) {  
77. outLong[flag]=numLong;  
78. flag++;  
79. }  
80.   
81. for (int i=k-1;i>=0;i--) {  
82. context.write(new LongWritable(outLong[i]),NullWritable.get());  
83. }  
84. }  
85.   
86. }  
87. /** 
88. * 主方法 
89. * @param args 
90. * @throws Exception 
91. */  
92. public static void main(String[] args) throws Exception {  
93. Configuration conf = new Configuration();  
94. Job job=Job.getInstance(conf, Topk.class.getSimpleName());  
95. job.setJarByClass(Topk.class);  
96.   
97. job.setNumReduceTasks(1);  
98.   
99. job.setMapperClass(MyMapper.class);  
100. job.setReducerClass(MyReducer.class);  
101.   
102. job.setMapOutputKeyClass(LongWritable.class);  
103. job.setMapOutputValueClass(Text.class);  
104.   
105. job.setOutputKeyClass(LongWritable.class);  
106. job.setOutputValueClass(NullWritable.class);  
107.   
108. job.setInputFormatClass(TextInputFormat.class);  
109. job.setOutputFormatClass(TextOutputFormat.class);  
110.   
111. FileInputFormat.setInputPaths(job, args[0]);  
112. FileOutputFormat.setOutputPath(job, new Path(args[1]));  
113.   
114. job.waitForCompletion(true);  
115.   
116. }  
117. }  

4、代码运行后输出在HDFS上面的目录：

[java] view plain copy print?

1. [hadoop@hadoop ~]$ hdfs dfs -ls /user/hadoop/output_topk/output3  
2. Found 2 items  
3. -rw-r--r--   3 hadoop supergroup          0 2015-08-30 21:09 /user/hadoop/output_topk/output3/_SUCCESS  
4. -rw-r--r--   3 hadoop supergroup         80 2015-08-30 21:09 /user/hadoop/output_topk/output3/part-r-00000  

5、查看top10的数据：

[java] view plain copy print?

1. [hadoop@hadoop ~]$ hdfs dfs -text /user/hadoop/output_topk/output3/part-r-00000  
2. 9999706  
3. 9999594  
4. 9999424  
5. 9999199  
6. 9997208  
7. 9996513  
8. 9995640  
9. 9995515  
10. 9993977  
11. 9991946