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
|
/*
* 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;
// $example on$
import scala.Tuple2;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.mllib.classification.NaiveBayes;
import org.apache.spark.mllib.classification.NaiveBayesModel;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.mllib.util.MLUtils;
// $example off$
import org.apache.spark.SparkConf;
public class JavaNaiveBayesExample {
public static void main(String[] args) {
SparkConf sparkConf = new SparkConf().setAppName("JavaNaiveBayesExample");
JavaSparkContext jsc = new JavaSparkContext(sparkConf);
// $example on$
String path = "data/mllib/sample_libsvm_data.txt";
JavaRDD<LabeledPoint> inputData = MLUtils.loadLibSVMFile(jsc.sc(), path).toJavaRDD();
JavaRDD<LabeledPoint>[] tmp = inputData.randomSplit(new double[]{0.6, 0.4});
JavaRDD<LabeledPoint> training = tmp[0]; // training set
JavaRDD<LabeledPoint> test = tmp[1]; // test set
final NaiveBayesModel model = NaiveBayes.train(training.rdd(), 1.0);
JavaPairRDD<Double, Double> predictionAndLabel =
test.mapToPair(new PairFunction<LabeledPoint, Double, Double>() {
@Override
public Tuple2<Double, Double> call(LabeledPoint p) {
return new Tuple2<>(model.predict(p.features()), p.label());
}
});
double accuracy = predictionAndLabel.filter(new Function<Tuple2<Double, Double>, Boolean>() {
@Override
public Boolean call(Tuple2<Double, Double> pl) {
return pl._1().equals(pl._2());
}
}).count() / (double) test.count();
// Save and load model
model.save(jsc.sc(), "target/tmp/myNaiveBayesModel");
NaiveBayesModel sameModel = NaiveBayesModel.load(jsc.sc(), "target/tmp/myNaiveBayesModel");
// $example off$
jsc.stop();
}
}
|