【Data Algorithms_Recipes for Scaling up with Hadoop and Spark】Chapter 12. K-Means Clustering_practical data science with hadoop and spark: desi-优快云博客

本文介绍了一个基于Apache Spark的K-Means聚类算法的简单实现案例，旨在帮助初学者了解如何使用Spark进行数据处理。该实现采用Scala语言，并通过具体的代码示例展示了从读取数据到迭代计算直至收敛的整个过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

:spark examples中的kmeans实现

/*
 * 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

import breeze.linalg.{ Vector, DenseVector, squaredDistance }

import org.apache.spark.{ SparkConf, SparkContext }
import org.apache.spark.SparkContext._

/**
 * K-means clustering.
 *
 * This is an example implementation for learning how to use Spark. For more conventional use,
 * please refer to org.apache.spark.mllib.clustering.KMeans
 */
object SparkKMeans {

  def parseVector(line: String): Vector[Double] = {
    DenseVector(line.split(' ').map(_.toDouble))
  }

  def closestPoint(p: Vector[Double], centers: Array[Vector[Double]]): Int = {
    var bestIndex = 0
    var closest = Double.PositiveInfinity

    for (i <- 0 until centers.length) {
      val tempDist = squaredDistance(p, centers(i))
      if (tempDist < closest) {
        closest = tempDist
        bestIndex = i
      }
    }

    bestIndex
  }

  def showWarning() {
    System.err.println(
      """WARN: This is a naive implementation of KMeans Clustering and is given as an example!
        |Please use the KMeans method found in org.apache.spark.mllib.clustering
        |for more conventional use.
      """.stripMargin)
  }

  def main(args: Array[String]) {

    if (args.length < 3) {
      System.err.println("Usage: SparkKMeans <file> <k> <convergeDist>")
      System.exit(1)
    }

    showWarning()

    val sparkConf = new SparkConf().setAppName("SparkKMeans")
    val sc = new SparkContext(sparkConf)
    val lines = sc.textFile(args(0))
    val data = lines.map(parseVector _).cache()
    val K = args(1).toInt
    val convergeDist = args(2).toDouble

    val kPoints = data.takeSample(withReplacement = false, K, 42).toArray
    var tempDist = 1.0

    while (tempDist > convergeDist) {
      val closest = data.map(p => (closestPoint(p, kPoints), (p, 1)))

      val pointStats = closest.reduceByKey { case ((p1, c1), (p2, c2)) => (p1 + p2, c1 + c2) }

      val newPoints = pointStats.map { pair =>
        (pair._1, pair._2._1 * (1.0 / pair._2._2))
      }.collectAsMap()

      tempDist = 0.0
      for (i <- 0 until K) {
        tempDist += squaredDistance(kPoints(i), newPoints(i))
      }

      for (newP <- newPoints) {
        kPoints(newP._1) = newP._2
      }
      println("Finished iteration (delta = " + tempDist + ")")
    }

    println("Final centers:")
    kPoints.foreach(println)
    sc.stop()
  }
}
// scalastyle:on println