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
76
77
78
79
80
81
82
|
/*
* 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.mllib.clustering;
import java.io.Serializable;
import java.util.Arrays;
import java.util.List;
import scala.Tuple2;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import static org.apache.spark.streaming.JavaTestUtils.*;
import org.apache.spark.SparkConf;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;
import org.apache.spark.streaming.Duration;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
public class JavaStreamingKMeansSuite implements Serializable {
protected transient JavaStreamingContext ssc;
@Before
public void setUp() {
SparkConf conf = new SparkConf()
.setMaster("local[2]")
.setAppName("test")
.set("spark.streaming.clock", "org.apache.spark.util.ManualClock");
ssc = new JavaStreamingContext(conf, new Duration(1000));
ssc.checkpoint("checkpoint");
}
@After
public void tearDown() {
ssc.stop();
ssc = null;
}
@Test
@SuppressWarnings("unchecked")
public void javaAPI() {
List<Vector> trainingBatch = Arrays.asList(
Vectors.dense(1.0),
Vectors.dense(0.0));
JavaDStream<Vector> training =
attachTestInputStream(ssc, Arrays.asList(trainingBatch, trainingBatch), 2);
List<Tuple2<Integer, Vector>> testBatch = Arrays.asList(
new Tuple2<>(10, Vectors.dense(1.0)),
new Tuple2<>(11, Vectors.dense(0.0)));
JavaPairDStream<Integer, Vector> test = JavaPairDStream.fromJavaDStream(
attachTestInputStream(ssc, Arrays.asList(testBatch, testBatch), 2));
StreamingKMeans skmeans = new StreamingKMeans()
.setK(1)
.setDecayFactor(1.0)
.setInitialCenters(new Vector[]{Vectors.dense(1.0)}, new double[]{0.0});
skmeans.trainOn(training);
JavaPairDStream<Integer, Integer> prediction = skmeans.predictOnValues(test);
attachTestOutputStream(prediction.count());
runStreams(ssc, 2, 2);
}
}
|