[Case Study]K-Means Clustering using Java

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

1. package org.apache.spark.examples.ml;
   
2. 
   
3. import java.util.regex.Pattern;
   
4. 
   
5. import org.apache.spark.SparkConf;
   
6. import org.apache.spark.api.java.JavaRDD;
   
7. import org.apache.spark.api.java.JavaSparkContext;
   
8. import org.apache.spark.api.java.function.Function;
   
9. import org.apache.spark.ml.clustering.KMeansModel;
   
10. import org.apache.spark.ml.clustering.KMeans;
    
11. import org.apache.spark.mllib.linalg.Vector;
    
12. import org.apache.spark.mllib.linalg.VectorUDT;
    
13. import org.apache.spark.mllib.linalg.Vectors;
    
14. import org.apache.spark.sql.DataFrame;
    
15. import org.apache.spark.sql.Row;
    
16. import org.apache.spark.sql.SQLContext;
    
17. import org.apache.spark.sql.catalyst.expressions.GenericRow;
    
18. import org.apache.spark.sql.types.Metadata;
    
19. import org.apache.spark.sql.types.StructField;
    
20. import org.apache.spark.sql.types.StructType;
    
21. 
    
22. 
    
23. /**
    
24. * An example demonstrating a k-means clustering.
    
25. * Run with
    
26. * <pre>
    
27. * bin/run-example ml.JavaSimpleParamsExample <file> <k>
    
28. * </pre>
    
29. */
    
30. public class JavaKMeansExample {
    
31. 
    
32.   private static class ParsePoint implements Function<String, Row> {
    
33.     private static final Pattern separator = Pattern.compile(" ");
    
34. 
    
35.     @Override
    
36.     public Row call(String line) {
    
37.       String[] tok = separator.split(line);
    
38.       double[] point = new double[tok.length];
    
39.       for (int i = 0; i < tok.length; ++i) {
    
40.         point[i] = Double.parseDouble(tok[i]);
    
41.       }
    
42.       Vector[] points = {Vectors.dense(point)};
    
43.       return new GenericRow(points);
    
44.     }
    
45.   }
    
46. 
    
47.   public static void main(String[] args) {
    
48.     if (args.length != 2) {
    
49.       System.err.println("Usage: ml.JavaKMeansExample <file> <k>");
    
50.       System.exit(1);
    
51.     }
    
52.     String inputFile = args[0];
    
53.     int k = Integer.parseInt(args[1]);
    
54. 
    
55.     // Parses the arguments
    
56.     SparkConf conf = new SparkConf().setAppName("JavaKMeansExample");
    
57.     JavaSparkContext jsc = new JavaSparkContext(conf);
    
58.     SQLContext sqlContext = new SQLContext(jsc);
    
59. 
    
60.     // Loads data
    
61.     JavaRDD<Row> points = jsc.textFile(inputFile).map(new ParsePoint());
    
62.     StructField[] fields = {new StructField("features", new VectorUDT(), false, Metadata.empty())};
    
63.     StructType schema = new StructType(fields);
    
64.     DataFrame dataset = sqlContext.createDataFrame(points, schema);
    
65. 
    
66.     // Trains a k-means model
    
67.     KMeans kmeans = new KMeans()
    
68.       .setK(k);
    
69.     KMeansModel model = kmeans.fit(dataset);
    
70. 
    
71.     // Shows the result
    
72.     Vector[] centers = model.clusterCenters();
    
73.     System.out.println("Cluster Centers: ");
    
74.     for (Vector center: centers) {
    
75.       System.out.println(center);
    
76.     }
    
77. 
    
78.     jsc.stop();
    
79.   }
    
80. }

复制代码

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Clustering Case study k-means Cluster means package import Java