Scala GaussianMixture类代码示例

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› Scala›Scala教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Scala中org.apache.spark.ml.clustering.GaussianMixture类的典型用法代码示例。如果您正苦于以下问题：Scala GaussianMixture类的具体用法？Scala GaussianMixture怎么用？Scala GaussianMixture使用的例子？那么恭喜您, 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GaussianMixture类的2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，您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: GMMClusteringPersist

//设置package包名称以及导入依赖的类
package org.sparksamples.gmm

import java.text.SimpleDateFormat

import org.apache.spark.SparkConf
import org.apache.spark.ml.clustering.{GaussianMixture}
import org.apache.spark.sql.SparkSession


object GMMClusteringPersist {
  val PATH = "/home/ubuntu/work/spark-2.0.0-bin-hadoop2.7/"
  val BASE = "./data/movie_lens_libsvm_2f"

  val time = System.currentTimeMillis()
  val formatter = new SimpleDateFormat("dd_MM_yyyy_hh_mm_ss")

  import java.util.Calendar
  val calendar = Calendar.getInstance()
  calendar.setTimeInMillis(time)
  val date_time = formatter.format(calendar.getTime())

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

    val spConfig = (new SparkConf).setMaster("local[1]").setAppName("SparkApp").
      set("spark.driver.allowMultipleContexts", "true")

    val spark = SparkSession
      .builder()
      .appName("Spark SQL Example")
      .config(spConfig)
      .getOrCreate()

    val datasetUsers = spark.read.format("libsvm").load(
      BASE + "/movie_lens_2f_users_libsvm/part-00000")
    datasetUsers.show(3)

    val gmmUsers = new GaussianMixture().setK(5).setSeed(1L)
    gmmUsers.setMaxIter(20)
    val modelUsers = gmmUsers.fit(datasetUsers)

    val predictedDataSetUsers = modelUsers.transform(datasetUsers)
    val predictionsUsers = predictedDataSetUsers.select("prediction").rdd.map(x=> x(0))
    predictionsUsers.saveAsTextFile(BASE + "/prediction/" + date_time + "/gmm_2f_users")


    val dataSetItems = spark.read.format("libsvm").load(BASE +
      "/movie_lens_2f_items_libsvm/part-00000")


    val gmmItems = new GaussianMixture().setK(5).setSeed(1L)
    val modelItems = gmmItems.fit(dataSetItems)

    val predictedDataSetItems = modelItems.transform(dataSetItems)
    val predictionsItems = predictedDataSetItems.select("prediction").rdd.map(x=> x(0))
    predictionsItems.saveAsTextFile(BASE + "/prediction/" + date_time + "/gmm_2f_items")
    spark.stop()
  }
}

开发者ID:PacktPublishing，项目名称:Machine-Learning-with-Spark-Second-Edition，代码行数:59，代码来源:GMMClusteringPersist.scala

示例2: GaussianMixtureJob

//设置package包名称以及导入依赖的类
import DTreeClassificationJob.context
import io.hydrosphere.mist.api._
import io.hydrosphere.mist.api.ml._
import io.hydrosphere.mist.api.ml.{LocalData, LocalDataColumn, PipelineLoader}
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.clustering.GaussianMixture
import org.apache.spark.sql.SparkSession


object GaussianMixtureJob extends MLMistJob {
  def session: SparkSession = SparkSession
    .builder()
    .appName(context.appName)
    .config(context.getConf)
    .getOrCreate()

  def train(): Map[String, Any] = {
    val dataset = session.read.format("libsvm").load("jobs/data/mllib/sample_kmeans_data.txt")

    val gmm = new GaussianMixture().setK(2)

    val pipeline = new Pipeline().setStages(Array(gmm))

    val model = pipeline.fit(dataset)

    model.write.overwrite().save("models/gaussian_mixture")
    Map.empty[String, Any]
  }

  def serve(text: List[String]): Map[String, Any] = {
    import LocalPipelineModel._

    val pipeline = PipelineLoader.load("models/gaussian_mixture")
    val data = LocalData(
      LocalDataColumn("text", text)
    )
    val result: LocalData = pipeline.transform(data)
    Map("result" -> result.select("text", "prediction").toMapList)
  }
}

开发者ID:Hydrospheredata，项目名称:mist，代码行数:41，代码来源:GaussianMixtureJob.scala

注：本文中的org.apache.spark.ml.clustering.GaussianMixture类示例整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。