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
|
/*
* 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.ml
// scalastyle:off println
import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.ml.clustering.KMeans
import org.apache.spark.mllib.linalg.Vectors
// $example off$
import org.apache.spark.sql.{DataFrame, SQLContext}
/**
* An example demonstrating a k-means clustering.
* Run with
* {{{
* bin/run-example ml.KMeansExample
* }}}
*/
object KMeansExample {
def main(args: Array[String]): Unit = {
// Creates a Spark context and a SQL context
val conf = new SparkConf().setAppName(s"${this.getClass.getSimpleName}")
val sc = new SparkContext(conf)
val sqlContext = new SQLContext(sc)
// $example on$
// Crates a DataFrame
val dataset: DataFrame = sqlContext.createDataFrame(Seq(
(1, Vectors.dense(0.0, 0.0, 0.0)),
(2, Vectors.dense(0.1, 0.1, 0.1)),
(3, Vectors.dense(0.2, 0.2, 0.2)),
(4, Vectors.dense(9.0, 9.0, 9.0)),
(5, Vectors.dense(9.1, 9.1, 9.1)),
(6, Vectors.dense(9.2, 9.2, 9.2))
)).toDF("id", "features")
// Trains a k-means model
val kmeans = new KMeans()
.setK(2)
.setFeaturesCol("features")
.setPredictionCol("prediction")
val model = kmeans.fit(dataset)
// Shows the result
println("Final Centers: ")
model.clusterCenters.foreach(println)
// $example off$
sc.stop()
}
}
// scalastyle:on println
|