KMeans聚类算法Hadoop实现
来源：互联网 发布：socket多线程编程 编辑：程序博客网 时间：2024/06/06 02:00
原文地址：http://blog.csdn.net/jdplus/article/details/23960127/
Assistance.java 辅助类，功能详见注释
01.package KMeans; 02. 03.import org.apache.hadoop.conf.Configuration; 04.import org.apache.hadoop.fs.FSDataInputStream; 05.import org.apache.hadoop.fs.FSDataOutputStream; 06.import org.apache.hadoop.fs.FileSystem; 07.import org.apache.hadoop.fs.Path; 08.import org.apache.hadoop.io.Text; 09.import org.apache.hadoop.util.LineReader; 10. 11.import java.io.IOException; 12.import java.util.*; 13. 14.public class Assistance { 15. //读取聚类中心点信息：聚类中心ID、聚类中心点 16. public static List<ArrayList<Float>> getCenters(String inputpath){ 17. List<ArrayList<Float>> result = new ArrayList<ArrayList<Float>>(); 18. Configuration conf = new Configuration(); 19. try { 20. FileSystem hdfs = FileSystem.get(conf); 21. Path in = new Path(inputpath); 22. FSDataInputStream fsIn = hdfs.open(in); 23. LineReader lineIn = new LineReader(fsIn, conf); 24. Text line = new Text(); 25. while (lineIn.readLine(line) > 0){ 26. String record = line.toString(); 27. /* 28. 因为Hadoop输出键值对时会在键跟值之间添加制表符， 29. 所以用空格代替之。 30. */ 31. String[] fields = record.replace("\t", " ").split(" "); 32. List<Float> tmplist = new ArrayList<Float>(); 33. for (int i = 0; i < fields.length; ++i){ 34. tmplist.add(Float.parseFloat(fields[i])); 35. } 36. result.add((ArrayList<Float>) tmplist); 37. } 38. fsIn.close(); 39. } catch (IOException e){ 40. e.printStackTrace(); 41. } 42. return result; 43. } 44. 45. //删除上一次MapReduce作业的结果 46. public static void deleteLastResult(String path){ 47. Configuration conf = new Configuration(); 48. try { 49. FileSystem hdfs = FileSystem.get(conf); 50. Path path1 = new Path(path); 51. hdfs.delete(path1, true); 52. } catch (IOException e){ 53. e.printStackTrace(); 54. } 55. } 56. //计算相邻两次迭代结果的聚类中心的距离，判断是否满足终止条件 57. public static boolean isFinished(String oldpath, String newpath, int k, float threshold) 58. throws IOException{ 59. List<ArrayList<Float>> oldcenters = Assistance.getCenters(oldpath); 60. List<ArrayList<Float>> newcenters = Assistance.getCenters(newpath); 61. float distance = 0; 62. for (int i = 0; i < k; ++i){ 63. for (int j = 1; j < oldcenters.get(i).size(); ++j){ 64. float tmp = Math.abs(oldcenters.get(i).get(j) - newcenters.get(i).get(j)); 65. distance += Math.pow(tmp, 2); 66. } 67. } 68. System.out.println("Distance = " + distance + " Threshold = " + threshold); 69. if (distance < threshold) 70. return true; 71. /* 72. 如果不满足终止条件，则用本次迭代的聚类中心更新聚类中心 73. */ 74. Assistance.deleteLastResult(oldpath); 75. Configuration conf = new Configuration(); 76. FileSystem hdfs = FileSystem.get(conf); 77. hdfs.copyToLocalFile(new Path(newpath), new Path("/home/hadoop/class/oldcenter.data")); 78. hdfs.delete(new Path(oldpath), true); 79. hdfs.moveFromLocalFile(new Path("/home/hadoop/class/oldcenter.data"), new Path(oldpath)); 80. return false; 81. } 82.} KMeansDriver.java 作业驱动类 [java] view plain copy 在CODE上查看代码片派生到我的代码片01.package KMeans; 02. 03.import org.apache.hadoop.conf.Configuration; 04.import org.apache.hadoop.fs.FileSystem; 05.import org.apache.hadoop.fs.Path; 06.import org.apache.hadoop.io.IntWritable; 07.import org.apache.hadoop.io.Text; 08.import org.apache.hadoop.mapreduce.Job; 09.import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 10.import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 11.import org.apache.hadoop.util.GenericOptionsParser; 12. 13.import java.io.IOException; 14. 15.public class KMeansDriver{ 16. public static void main(String[] args) throws Exception{ 17. int repeated = 0; 18. 19. /* 20. 不断提交MapReduce作业指导相邻两次迭代聚类中心的距离小于阈值或到达设定的迭代次数 21. */ 22. do { 23. Configuration conf = new Configuration(); 24. String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); 25. if (otherArgs.length != 6){ 26. System.err.println("Usage: <int> <out> <oldcenters> <newcenters> <k> <threshold>"); 27. System.exit(2); 28. } 29. conf.set("centerpath", otherArgs[2]); 30. conf.set("kpath", otherArgs[4]); 31. Job job = new Job(conf, "KMeansCluster");//新建MapReduce作业 32. job.setJarByClass(KMeansDriver.class);//设置作业启动类 33. 34. Path in = new Path(otherArgs[0]); 35. Path out = new Path(otherArgs[1]); 36. FileInputFormat.addInputPath(job, in);//设置输入路径 37. FileSystem fs = FileSystem.get(conf); 38. if (fs.exists(out)){//如果输出路径存在，则先删除之 39. fs.delete(out, true); 40. } 41. FileOutputFormat.setOutputPath(job, out);//设置输出路径 42. 43. job.setMapperClass(KMeansMapper.class);//设置Map类 44. job.setReducerClass(KMeansReducer.class);//设置Reduce类 45. 46. job.setOutputKeyClass(IntWritable.class);//设置输出键的类 47. job.setOutputValueClass(Text.class);//设置输出值的类 48. 49. job.waitForCompletion(true);//启动作业 50. 51. ++repeated; 52. System.out.println("We have repeated " + repeated + " times."); 53. } while (repeated < 10 && (Assistance.isFinished(args[2], args[3], Integer.parseInt(args[4]), Float.parseFloat(args[5])) == false)); 54. //根据最终得到的聚类中心对数据集进行聚类 55. Cluster(args); 56. } 57. public static void Cluster(String[] args) 58. throws IOException, InterruptedException, ClassNotFoundException{ 59. Configuration conf = new Configuration(); 60. String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); 61. if (otherArgs.length != 6){ 62. System.err.println("Usage: <int> <out> <oldcenters> <newcenters> <k> <threshold>"); 63. System.exit(2); 64. } 65. conf.set("centerpath", otherArgs[2]); 66. conf.set("kpath", otherArgs[4]); 67. Job job = new Job(conf, "KMeansCluster"); 68. job.setJarByClass(KMeansDriver.class); 69. 70. Path in = new Path(otherArgs[0]); 71. Path out = new Path(otherArgs[1]); 72. FileInputFormat.addInputPath(job, in); 73. FileSystem fs = FileSystem.get(conf); 74. if (fs.exists(out)){ 75. fs.delete(out, true); 76. } 77. FileOutputFormat.setOutputPath(job, out); 78. 79. //因为只是将样本点聚类，不需要reduce操作，故不设置Reduce类 80. job.setMapperClass(KMeansMapper.class); 81. 82. job.setOutputKeyClass(IntWritable.class); 83. job.setOutputValueClass(Text.class); 84. 85. job.waitForCompletion(true); 86. } 87.} KMeansMapper.java [java] view plain copy 在CODE上查看代码片派生到我的代码片01.package KMeans; 02. 03.import org.apache.hadoop.io.IntWritable; 04.import org.apache.hadoop.io.LongWritable; 05.import org.apache.hadoop.io.Text; 06.import org.apache.hadoop.mapreduce.Mapper; 07. 08.import java.io.IOException; 09.import java.util.ArrayList; 10.import java.util.List; 11. 12.public class KMeansMapper extends Mapper<Object, Text, IntWritable, Text> { 13. public void map(Object key, Text value, Context context) 14. throws IOException, InterruptedException{ 15. String line = value.toString(); 16. String[] fields = line.split(" "); 17. List<ArrayList<Float>> centers = Assistance.getCenters(context.getConfiguration().get("centerpath")); 18. int k = Integer.parseInt(context.getConfiguration().get("kpath")); 19. float minDist = Float.MAX_VALUE; 20. int centerIndex = k; 21. //计算样本点到各个中心的距离，并把样本聚类到距离最近的中心点所属的类 22. for (int i = 0; i < k; ++i){ 23. float currentDist = 0; 24. for (int j = 0; j < fields.length; ++j){ 25. float tmp = Math.abs(centers.get(i).get(j + 1) - Float.parseFloat(fields[j])); 26. currentDist += Math.pow(tmp, 2); 27. } 28. if (minDist > currentDist){ 29. minDist = currentDist; 30. centerIndex = i; 31. } 32. } 33. context.write(new IntWritable(centerIndex), new Text(value)); 34. } 35.} KMeansReducer.java[java] view plain copy 在CODE上查看代码片派生到我的代码片01.package KMeans; 02. 03.import org.apache.hadoop.io.IntWritable; 04.import org.apache.hadoop.io.Text; 05.import org.apache.hadoop.mapreduce.Reducer; 06. 07.import java.io.IOException; 08.import java.util.ArrayList; 09.import java.util.List; 10. 11.public class KMeansReducer extends Reducer<IntWritable, Text, IntWritable, Text> { 12. public void reduce(IntWritable key, Iterable<Text> value, Context context) 13. throws IOException, InterruptedException{ 14. List<ArrayList<Float>> assistList = new ArrayList<ArrayList<Float>>(); 15. String tmpResult = ""; 16. for (Text val : value){ 17. String line = val.toString(); 18. String[] fields = line.split(" "); 19. List<Float> tmpList = new ArrayList<Float>(); 20. for (int i = 0; i < fields.length; ++i){ 21. tmpList.add(Float.parseFloat(fields[i])); 22. } 23. assistList.add((ArrayList<Float>) tmpList); 24. } 25. //计算新的聚类中心 26. for (int i = 0; i < assistList.get(0).size(); ++i){ 27. float sum = 0; 28. for (int j = 0; j < assistList.size(); ++j){ 29. sum += assistList.get(j).get(i); 30. } 31. float tmp = sum / assistList.size(); 32. if (i == 0){ 33. tmpResult += tmp; 34. } 35. else{ 36. tmpResult += " " + tmp; 37. } 38. } 39. Text result = new Text(tmpResult); 40. context.write(key, result); 41. } 42.} 作业运行情况：[plain] view plain copy 在CODE上查看代码片派生到我的代码片01.hadoop@shaobo-ThinkPad-E420:~/class$ hadoop jar KMeans.jar KMeans.KMeansDriver input/iris.data output input/oldcenter.data output/part-r-00000 3 0.0001 02.14/04/17 16:15:50 INFO input.FileInputFormat: Total input paths to process : 1 03.14/04/17 16:15:51 INFO mapred.JobClient: Running job: job_201404171511_0012 04.14/04/17 16:15:52 INFO mapred.JobClient: map 0% reduce 0% 05.14/04/17 16:16:07 INFO mapred.JobClient: map 100% reduce 0% 06.14/04/17 16:16:19 INFO mapred.JobClient: map 100% reduce 100% 07.14/04/17 16:16:24 INFO mapred.JobClient: Job complete: job_201404171511_0012 08.14/04/17 16:16:24 INFO mapred.JobClient: Counters: 25 09.14/04/17 16:16:24 INFO mapred.JobClient: Job Counters 10.14/04/17 16:16:24 INFO mapred.JobClient: Launched reduce tasks=1 11.14/04/17 16:16:24 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=12041 12.14/04/17 16:16:24 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0 13.14/04/17 16:16:24 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0 14.14/04/17 16:16:24 INFO mapred.JobClient: Launched map tasks=1 15.14/04/17 16:16:24 INFO mapred.JobClient: Data-local map tasks=1 16.14/04/17 16:16:24 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=10030 17.14/04/17 16:16:24 INFO mapred.JobClient: File Output Format Counters 18.14/04/17 16:16:24 INFO mapred.JobClient: Bytes Written=125 19.14/04/17 16:16:24 INFO mapred.JobClient: FileSystemCounters 20.14/04/17 16:16:24 INFO mapred.JobClient: FILE_BYTES_READ=3306 21.14/04/17 16:16:24 INFO mapred.JobClient: HDFS_BYTES_READ=11214 22.14/04/17 16:16:24 INFO mapred.JobClient: FILE_BYTES_WRITTEN=48901 23.14/04/17 16:16:24 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=125 24.14/04/17 16:16:24 INFO mapred.JobClient: File Input Format Counters 25.14/04/17 16:16:24 INFO mapred.JobClient: Bytes Read=2550 26.14/04/17 16:16:24 INFO mapred.JobClient: Map-Reduce Framework 27.14/04/17 16:16:24 INFO mapred.JobClient: Reduce input groups=3 28.14/04/17 16:16:24 INFO mapred.JobClient: Map output materialized bytes=3306 29.14/04/17 16:16:24 INFO mapred.JobClient: Combine output records=0 30.14/04/17 16:16:24 INFO mapred.JobClient: Map input records=150 31.14/04/17 16:16:24 INFO mapred.JobClient: Reduce shuffle bytes=0 32.14/04/17 16:16:24 INFO mapred.JobClient: Reduce output records=3 33.14/04/17 16:16:24 INFO mapred.JobClient: Spilled Records=300 34.14/04/17 16:16:24 INFO mapred.JobClient: Map output bytes=3000 35.14/04/17 16:16:24 INFO mapred.JobClient: Combine input records=0 36.14/04/17 16:16:24 INFO mapred.JobClient: Map output records=150 37.14/04/17 16:16:24 INFO mapred.JobClient: SPLIT_RAW_BYTES=114 38.14/04/17 16:16:24 INFO mapred.JobClient: Reduce input records=150 39.We have repeated 1 times. 40.Distance = 0.35025704 Threshold = 1.0E-4 41.14/04/17 16:16:24 INFO input.FileInputFormat: Total input paths to process : 1 42.14/04/17 16:16:25 INFO mapred.JobClient: Running job: job_201404171511_0013 43.14/04/17 16:16:26 INFO mapred.JobClient: map 0% reduce 0% 44.14/04/17 16:16:40 INFO mapred.JobClient: map 100% reduce 0% 45.14/04/17 16:16:52 INFO mapred.JobClient: map 100% reduce 100% 46.14/04/17 16:16:57 INFO mapred.JobClient: Job complete: job_201404171511_0013 47.14/04/17 16:16:57 INFO mapred.JobClient: Counters: 25 48.14/04/17 16:16:57 INFO mapred.JobClient: Job Counters 49.14/04/17 16:16:57 INFO mapred.JobClient: Launched reduce tasks=1 50.14/04/17 16:16:57 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=12077 51.14/04/17 16:16:57 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0 52.14/04/17 16:16:57 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0 53.14/04/17 16:16:57 INFO mapred.JobClient: Launched map tasks=1 54.14/04/17 16:16:57 INFO mapred.JobClient: Data-local map tasks=1 55.14/04/17 16:16:57 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=10048 56.14/04/17 16:16:57 INFO mapred.JobClient: File Output Format Counters 57.14/04/17 16:16:57 INFO mapred.JobClient: Bytes Written=116 58.14/04/17 16:16:57 INFO mapred.JobClient: FileSystemCounters 59.14/04/17 16:16:57 INFO mapred.JobClient: FILE_BYTES_READ=3306 60.14/04/17 16:16:57 INFO mapred.JobClient: HDFS_BYTES_READ=21414 61.14/04/17 16:16:57 INFO mapred.JobClient: FILE_BYTES_WRITTEN=48901 62.14/04/17 16:16:57 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=116 63.14/04/17 16:16:57 INFO mapred.JobClient: File Input Format Counters 64.14/04/17 16:16:57 INFO mapred.JobClient: Bytes Read=2550 65.14/04/17 16:16:57 INFO mapred.JobClient: Map-Reduce Framework 66.14/04/17 16:16:57 INFO mapred.JobClient: Reduce input groups=3 67.14/04/17 16:16:57 INFO mapred.JobClient: Map output materialized bytes=3306 68.14/04/17 16:16:57 INFO mapred.JobClient: Combine output records=0 69.14/04/17 16:16:57 INFO mapred.JobClient: Map input records=150 70.14/04/17 16:16:57 INFO mapred.JobClient: Reduce shuffle bytes=3306 71.14/04/17 16:16:57 INFO mapred.JobClient: Reduce output records=3 72.14/04/17 16:16:57 INFO mapred.JobClient: Spilled Records=300 73.14/04/17 16:16:57 INFO mapred.JobClient: Map output bytes=3000 74.14/04/17 16:16:57 INFO mapred.JobClient: Combine input records=0 75.14/04/17 16:16:57 INFO mapred.JobClient: Map output records=150 76.14/04/17 16:16:57 INFO mapred.JobClient: SPLIT_RAW_BYTES=114 77.14/04/17 16:16:57 INFO mapred.JobClient: Reduce input records=150 78.We have repeated 2 times. 79.Distance = 0.006297064 Threshold = 1.0E-4 80.14/04/17 16:16:57 INFO input.FileInputFormat: Total input paths to process : 1 81.14/04/17 16:16:58 INFO mapred.JobClient: Running job: job_201404171511_0014 82.14/04/17 16:16:59 INFO mapred.JobClient: map 0% reduce 0% 83.14/04/17 16:17:14 INFO mapred.JobClient: map 100% reduce 0% 84.14/04/17 16:17:25 INFO mapred.JobClient: map 100% reduce 100% 85.14/04/17 16:17:30 INFO mapred.JobClient: Job complete: job_201404171511_0014 86.14/04/17 16:17:30 INFO mapred.JobClient: Counters: 25 87.14/04/17 16:17:30 INFO mapred.JobClient: Job Counters 88.14/04/17 16:17:30 INFO mapred.JobClient: Launched reduce tasks=1 89.14/04/17 16:17:30 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=12046 90.14/04/17 16:17:30 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0 91.14/04/17 16:17:30 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0 92.14/04/17 16:17:30 INFO mapred.JobClient: Launched map tasks=1 93.14/04/17 16:17:30 INFO mapred.JobClient: Data-local map tasks=1 94.14/04/17 16:17:30 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=10051 95.14/04/17 16:17:30 INFO mapred.JobClient: File Output Format Counters 96.14/04/17 16:17:30 INFO mapred.JobClient: Bytes Written=116 97.14/04/17 16:17:30 INFO mapred.JobClient: FileSystemCounters 98.14/04/17 16:17:30 INFO mapred.JobClient: FILE_BYTES_READ=3306 99.14/04/17 16:17:30 INFO mapred.JobClient: HDFS_BYTES_READ=20064 100.14/04/17 16:17:30 INFO mapred.JobClient: FILE_BYTES_WRITTEN=48901 101.14/04/17 16:17:30 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=116 102.14/04/17 16:17:30 INFO mapred.JobClient: File Input Format Counters 103.14/04/17 16:17:30 INFO mapred.JobClient: Bytes Read=2550 104.14/04/17 16:17:30 INFO mapred.JobClient: Map-Reduce Framework 105.14/04/17 16:17:30 INFO mapred.JobClient: Reduce input groups=3 106.14/04/17 16:17:30 INFO mapred.JobClient: Map output materialized bytes=3306 107.14/04/17 16:17:30 INFO mapred.JobClient: Combine output records=0 108.14/04/17 16:17:30 INFO mapred.JobClient: Map input records=150 109.14/04/17 16:17:30 INFO mapred.JobClient: Reduce shuffle bytes=0 110.14/04/17 16:17:30 INFO mapred.JobClient: Reduce output records=3 111.14/04/17 16:17:30 INFO mapred.JobClient: Spilled Records=300 112.14/04/17 16:17:30 INFO mapred.JobClient: Map output bytes=3000 113.14/04/17 16:17:30 INFO mapred.JobClient: Combine input records=0 114.14/04/17 16:17:30 INFO mapred.JobClient: Map output records=150 115.14/04/17 16:17:30 INFO mapred.JobClient: SPLIT_RAW_BYTES=114 116.14/04/17 16:17:30 INFO mapred.JobClient: Reduce input records=150 117.We have repeated 3 times. 118.Distance = 0.0 Threshold = 1.0E-4 119.14/04/17 16:17:30 INFO input.FileInputFormat: Total input paths to process : 1 120.14/04/17 16:17:30 INFO mapred.JobClient: Running job: job_201404171511_0015 121.14/04/17 16:17:31 INFO mapred.JobClient: map 0% reduce 0% 122.14/04/17 16:17:47 INFO mapred.JobClient: map 100% reduce 0% 123.14/04/17 16:17:59 INFO mapred.JobClient: map 100% reduce 100% 124.14/04/17 16:18:04 INFO mapred.JobClient: Job complete: job_201404171511_0015 125.14/04/17 16:18:04 INFO mapred.JobClient: Counters: 25 126.14/04/17 16:18:04 INFO mapred.JobClient: Job Counters 127.14/04/17 16:18:04 INFO mapred.JobClient: Launched reduce tasks=1 128.14/04/17 16:18:04 INFO mapred.JobClient: SLOTS_MILLIS_MAPS=12036 129.14/04/17 16:18:04 INFO mapred.JobClient: Total time spent by all reduces waiting after reserving slots (ms)=0 130.14/04/17 16:18:04 INFO mapred.JobClient: Total time spent by all maps waiting after reserving slots (ms)=0 131.14/04/17 16:18:04 INFO mapred.JobClient: Launched map tasks=1 132.14/04/17 16:18:04 INFO mapred.JobClient: Data-local map tasks=1 133.14/04/17 16:18:04 INFO mapred.JobClient: SLOTS_MILLIS_REDUCES=10050 134.14/04/17 16:18:04 INFO mapred.JobClient: File Output Format Counters 135.14/04/17 16:18:04 INFO mapred.JobClient: Bytes Written=2700 136.14/04/17 16:18:04 INFO mapred.JobClient: FileSystemCounters 137.14/04/17 16:18:04 INFO mapred.JobClient: FILE_BYTES_READ=3306 138.14/04/17 16:18:04 INFO mapred.JobClient: HDFS_BYTES_READ=20064 139.14/04/17 16:18:04 INFO mapred.JobClient: FILE_BYTES_WRITTEN=48717 140.14/04/17 16:18:04 INFO mapred.JobClient: HDFS_BYTES_WRITTEN=2700 141.14/04/17 16:18:04 INFO mapred.JobClient: File Input Format Counters 142.14/04/17 16:18:04 INFO mapred.JobClient: Bytes Read=2550 143.14/04/17 16:18:04 INFO mapred.JobClient: Map-Reduce Framework 144.14/04/17 16:18:04 INFO mapred.JobClient: Reduce input groups=3 145.14/04/17 16:18:04 INFO mapred.JobClient: Map output materialized bytes=3306 146.14/04/17 16:18:04 INFO mapred.JobClient: Combine output records=0 147.14/04/17 16:18:04 INFO mapred.JobClient: Map input records=150 148.14/04/17 16:18:04 INFO mapred.JobClient: Reduce shuffle bytes=0 149.14/04/17 16:18:04 INFO mapred.JobClient: Reduce output records=150 150.14/04/17 16:18:04 INFO mapred.JobClient: Spilled Records=300 151.14/04/17 16:18:04 INFO mapred.JobClient: Map output bytes=3000 152.14/04/17 16:18:04 INFO mapred.JobClient: Combine input records=0 153.14/04/17 16:18:04 INFO mapred.JobClient: Map output records=150 154.14/04/17 16:18:04 INFO mapred.JobClient: SPLIT_RAW_BYTES=114 155.14/04/17 16:18:04 INFO mapred.JobClient: Reduce input records=150 . 0 0
- KMeans聚类算法Hadoop实现
- KMeans聚类算法Hadoop实现
- KMeans聚类算法Hadoop实现
- KMeans聚类算法Hadoop实现
- Hadoop 实现kmeans 算法
- Hadoop/MapReduce 及 Spark KMeans聚类算法实现
- 用Hadoop实现KMeans算法
- hadoop下的Kmeans算法实现一
- hadoop下的Kmeans算法实现二
- hadoop下的Kmeans算法实现三
- hadoop下kmeans算法实现四
- hadoop下的Kmeans算法实现
- hadoop下kmeans算法实现四
- hadoop下的Kmeans算法实现三
- hadoop下的Kmeans算法实现一
- hadoop下的Kmeans算法实现
- 基于Hadoop的Kmeans算法实现
- hadoop之Kmeans数据挖掘算法实现
- 用UIWebView打开文档（doc、xls、pdf等）
- CSU 1765 简单shell 模拟
- 小练习——输出9*9乘法表，判断闰年
- Codeforces546B Soldier and Badges
- Java线程安全和线程不安全理解
- KMeans聚类算法Hadoop实现
- 安装mysql
- poj 1573 Robot Motion
- Backbone.js-入门教程
- 进程查看管理
- 阐述问答题（C语言）
- Python 列表(List)操作方法详解
- 网络流 ( ISAP+建图 )——A Plug for UNIX ( POJ 1087 )
- JAVA面向对象——对象数组概念与举例
