examples/src/main/scala/org/apache/spark/examples/ml/NaiveBayesExample.scala


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

/*
 * 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.
 */

// scalastyle:off println
package org.apache.spark.examples.ml

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.ml.classification.{NaiveBayes}
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
// $example off$
import org.apache.spark.sql.SQLContext

object NaiveBayesExample {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("NaiveBayesExample")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
    // $example on$
    // Load the data stored in LIBSVM format as a DataFrame.
    val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")

    // Split the data into training and test sets (30% held out for testing)
    val Array(trainingData, testData) = data.randomSplit(Array(0.7, 0.3))

    // Train a NaiveBayes model.
    val model = new NaiveBayes()
      .fit(trainingData)

    // Select example rows to display.
    val predictions = model.transform(testData)
    predictions.show()

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("precision")
    val precision = evaluator.evaluate(predictions)
    println("Precision:" + precision)
    // $example off$
  }
}
// scalastyle:on println