blob: d1fe5d138d31cf221e9cdfd1bd4818f3eb837d51 (
plain) (
blame)
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
|
/*
* 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 org.apache.spark.RDD
import org.apache.spark.SparkContext._
import org.apache.spark.mllib.util.MLUtils
/**
* A clustering model for K-means. Each point belongs to the cluster with the closest center.
*/
class KMeansModel(val clusterCenters: Array[Array[Double]]) extends Serializable {
/** Total number of clusters. */
def k: Int = clusterCenters.length
/** Return the cluster index that a given point belongs to. */
def predict(point: Array[Double]): Int = {
KMeans.findClosest(clusterCenters, point)._1
}
/**
* Return the K-means cost (sum of squared distances of points to their nearest center) for this
* model on the given data.
*/
def computeCost(data: RDD[Array[Double]]): Double = {
data.map(p => KMeans.pointCost(clusterCenters, p)).sum
}
}
|