examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeansExample.java


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.spark.examples.mllib;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;

// $example on$
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.clustering.KMeans;
import org.apache.spark.mllib.clustering.KMeansModel;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;
// $example off$

public class JavaKMeansExample {
  public static void main(String[] args) {

    SparkConf conf = new SparkConf().setAppName("JavaKMeansExample");
    JavaSparkContext jsc = new JavaSparkContext(conf);

    // $example on$
    // Load and parse data
    String path = "data/mllib/kmeans_data.txt";
    JavaRDD<String> data = jsc.textFile(path);
    JavaRDD<Vector> parsedData = data.map(s -> {
      String[] sarray = s.split(" ");
      double[] values = new double[sarray.length];
      for (int i = 0; i < sarray.length; i++) {
        values[i] = Double.parseDouble(sarray[i]);
      }
      return Vectors.dense(values);
    });
    parsedData.cache();

    // Cluster the data into two classes using KMeans
    int numClusters = 2;
    int numIterations = 20;
    KMeansModel clusters = KMeans.train(parsedData.rdd(), numClusters, numIterations);

    System.out.println("Cluster centers:");
    for (Vector center: clusters.clusterCenters()) {
      System.out.println(" " + center);
    }
    double cost = clusters.computeCost(parsedData.rdd());
    System.out.println("Cost: " + cost);

    // Evaluate clustering by computing Within Set Sum of Squared Errors
    double WSSSE = clusters.computeCost(parsedData.rdd());
    System.out.println("Within Set Sum of Squared Errors = " + WSSSE);

    // Save and load model
    clusters.save(jsc.sc(), "target/org/apache/spark/JavaKMeansExample/KMeansModel");
    KMeansModel sameModel = KMeansModel.load(jsc.sc(),
      "target/org/apache/spark/JavaKMeansExample/KMeansModel");
    // $example off$

    jsc.stop();
  }
}