本文整理汇总了Scala中org.apache.spark.mllib.random.RandomRDDs类的典型用法代码示例。如果您正苦于以下问题：Scala RandomRDDs类的具体用法？Scala RandomRDDs怎么用？Scala RandomRDDs使用的例子？那么, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了RandomRDDs类的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Scala代码示例。
示例1: GenerateScalingData
//设置package包名称以及导入依赖的类
package com.highperformancespark.examples.tools
import com.highperformancespark.examples.dataframe.RawPanda
import org.apache.spark._
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.Row
import org.apache.spark.mllib.random.RandomRDDs
import org.apache.spark.mllib.linalg.Vector
object GenerateScalingData {
def generateGoldilocks(sc: SparkContext, rows: Long, numCols: Int):
RDD[RawPanda] = {
val zipRDD = RandomRDDs.exponentialRDD(sc, mean = 1000, size = rows)
.map(_.toInt.toString)
val valuesRDD = RandomRDDs.normalVectorRDD(
sc, numRows = rows, numCols = numCols)
zipRDD.zip(valuesRDD).map{case (z, v) =>
RawPanda(1, z, "giant", v(0) > 0.5, v.toArray)
}
}
// end::MAGIC_PANDA[]
} 示例2: CustomDecaySpec
//设置package包名称以及导入依赖的类
package io.flatmap.ml.som
import io.flatmap.ml.som.SelfOrganizingMap.Shape
import org.apache.spark.mllib.random.RandomRDDs
import org.scalatest.{BeforeAndAfterEach, FlatSpec, Matchers}
import util.TestSparkContext
class CustomDecaySpec extends FlatSpec with Matchers with BeforeAndAfterEach with TestSparkContext {
def SOM(width: Int, height: Int, _sigma: Double, _learningRate: Double) =
new SelfOrganizingMap with CustomDecay with GaussianNeighborboodKernel with QuantizationErrorMetrics {
override val shape: Shape = (width, height)
override val learningRate: Double = _learningRate
override val sigma: Double = _sigma
}
"decay" should "decrease sigma and learningRate to one half each" in {
val data = RandomRDDs.normalVectorRDD(sparkSession.sparkContext, numRows = 512L, numCols = 3)
val sigma = 0.5
val learningRate = 0.3
val iterations = 20.0
val (_, params) =
SOM(6, 6, sigma, learningRate)
.initialize(data)
.train(data, iterations.toInt)
params.sigma should equal (sigma / (1.0 + (iterations - 1.0) / iterations))
params.learningRate should equal (learningRate / (1.0 + (iterations - 1.0) / iterations))
}
} 示例3: SelfOrganizingMapSpec
//设置package包名称以及导入依赖的类
package io.flatmap.ml.som
import breeze.numerics.closeTo
import breeze.linalg.DenseMatrix
import io.flatmap.ml.som.SelfOrganizingMap.Shape
import org.apache.spark.mllib.linalg.DenseVector
import org.apache.spark.mllib.random.RandomRDDs
import org.scalatest._
import util.{FakeDecayFunction, FakeMetrics, FakeNeighborhoodKernel, TestSparkContext}
class SelfOrganizingMapSpec extends FlatSpec with Matchers with BeforeAndAfterEach with TestSparkContext {
def SOM(width: Int, height: Int) =
new SelfOrganizingMap with FakeNeighborhoodKernel with FakeDecayFunction with FakeMetrics {
override val shape: Shape = (width, height)
override val learningRate: Double = 0.1
override val sigma: Double = 0.2
}
"instantiation" should "create a SOM with codebook of zeros" in {
val som = SOM(6, 6)
som.codeBook should === (DenseMatrix.fill[Array[Double]](6, 6)(Array.emptyDoubleArray))
}
"initialize" should "copy random data points from RDD into codebook" in {
val data = RandomRDDs.normalVectorRDD(sparkSession.sparkContext, numRows = 512L, numCols = 3)
val som = SOM(6, 6)
som.initialize(data).codeBook should !== (DenseMatrix.fill[Array[Double]](6, 6)(Array.emptyDoubleArray))
}
"winner" should "return best matching unit (BMU)" in {
val som = SOM(6, 6)
som.codeBook.keysIterator.foreach { case (x, y) => som.codeBook(x, y) = Array(0.2, 0.2, 0.2) }
som.codeBook(3, 3) = Array(0.3, 0.3, 0.3)
som.winner(new DenseVector(Array(2.0, 2.0, 2.0)), som.codeBook) should equal ((3, 3))
som.winner(new DenseVector(Array(0.26, 0.26, 0.26)), som.codeBook) should equal ((3, 3))
}
"winner" should "return last best matching unit (BMU) index in case of multiple BMUs" in {
val som = SOM(6, 6)
som.codeBook.keysIterator.foreach { case (x, y) => som.codeBook(x, y) = Array(0.2, 0.2, 0.2) }
som.codeBook(3, 3) = Array(0.3, 0.3, 0.3)
som.winner(new DenseVector(Array(0.25, 0.25, 0.25)), som.codeBook) should equal ((5, 5))
}
"classify" should "return the best matching unit along with Euclidean distance" in {
val som = SOM(6, 6)
som.codeBook.keysIterator.foreach { case (x, y) => som.codeBook(x, y) = Array(0.2, 0.2, 0.2) }
som.codeBook(3, 3) = Array(0.3, 0.3, 0.3)
val (bmu, distance) = som.classify(new DenseVector(Array(0.26, 0.26, 0.26)))
bmu should === ((3, 3))
assert(closeTo(distance, 0.06, relDiff = 1e-2))
}
}