spark SparkKMeans 源码

spark SparkKMeans 代码

文件路径：/examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala

/*
 * 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.{squaredDistance, DenseVector, Vector}

import org.apache.spark.sql.SparkSession

/**
 * K-means clustering.
 *
 * This is an example implementation for learning how to use Spark. For more conventional use,
 * please refer to org.apache.spark.ml.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 <- centers.indices) {
      val tempDist = squaredDistance(p, centers(i))
      if (tempDist < closest) {
        closest = tempDist
        bestIndex = i
      }
    }

    bestIndex
  }

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

  def main(args: Array[String]): Unit = {

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

    showWarning()

    val spark = SparkSession
      .builder
      .appName("SparkKMeans")
      .getOrCreate()

    val lines = spark.read.textFile(args(0)).rdd
    val data = lines.map(parseVector _).cache()
    val K = args(1).toInt
    val convergeDist = args(2).toDouble

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

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

      val pointStats = closest.reduceByKey(mergeResults)

      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(s"Finished iteration (delta = $tempDist)")
    }

    println("Final centers:")
    kPoints.foreach(println)
    spark.stop()
  }

  private def mergeResults(
      a: (Vector[Double], Int),
      b: (Vector[Double], Int)): (Vector[Double], Int) = {
    (a._1 + b._1, a._2 + b._2)
  }
}
// scalastyle:on println

相关信息

spark 源码目录

相关文章

spark AccumulatorMetricsTest 源码

spark BroadcastTest 源码

spark DFSReadWriteTest 源码

spark DriverSubmissionTest 源码

spark ExceptionHandlingTest 源码

spark GroupByTest 源码

spark HdfsTest 源码

spark LocalALS 源码

spark LocalFileLR 源码

spark LocalKMeans 源码