Scala RandomForestRegressionModel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.regression.RandomForestRegressionModel类的典型用法代码示例。如果您正苦于以下问题：Scala RandomForestRegressionModel类的具体用法？Scala RandomForestRegressionModel怎么用？Scala RandomForestRegressionModel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RandomForestRegressionModel类的4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: LocalRandomForestRegressionModel

//设置package包名称以及导入依赖的类
package io.hydrosphere.spark_ml_serving.regression

import io.hydrosphere.spark_ml_serving._
import org.apache.spark.ml.linalg.{Vector, Vectors}
import org.apache.spark.ml.regression.{DecisionTreeRegressionModel, RandomForestRegressionModel}


class LocalRandomForestRegressionModel(override val sparkTransformer: RandomForestRegressionModel) extends LocalTransformer[RandomForestRegressionModel] {
  override def transform(localData: LocalData): LocalData = {
    val cls = classOf[RandomForestRegressionModel]
    val predict = cls.getMethod("predict", classOf[Vector])
    localData.column(sparkTransformer.getFeaturesCol) match {
      case Some(column) =>
        val predictionCol = LocalDataColumn(sparkTransformer.getPredictionCol, column.data.map(f => Vectors.dense(f.asInstanceOf[Array[Double]])).map{ vector =>
          predict.invoke(sparkTransformer, vector).asInstanceOf[Double]
        })
        localData.withColumn(predictionCol)
      case None => localData
    }
  }
}

object LocalRandomForestRegressionModel extends LocalModel[RandomForestRegressionModel] {
  override def load(metadata: Metadata, data: Map[String, Any]): RandomForestRegressionModel = {
    val treesMetadata = metadata.paramMap("treesMetadata").asInstanceOf[Map[String, Any]]
    val trees = treesMetadata map { treeKv =>
      val treeMeta = treeKv._2.asInstanceOf[Map[String, Any]]
      val meta = treeMeta("metadata").asInstanceOf[Metadata]
      LocalDecisionTreeRegressionModel.createTree(
        meta,
        data(treeKv._1).asInstanceOf[Map[String, Any]]
      )
    }
    val ctor = classOf[RandomForestRegressionModel].getDeclaredConstructor(classOf[String], classOf[Array[DecisionTreeRegressionModel]], classOf[Int])
    ctor.setAccessible(true)
    val inst = ctor
      .newInstance(
        metadata.uid,
        trees.to[Array],
        metadata.numFeatures.get.asInstanceOf[java.lang.Integer]
      )
      .setFeaturesCol(metadata.paramMap("featuresCol").asInstanceOf[String])
      .setPredictionCol(metadata.paramMap("predictionCol").asInstanceOf[String])

    inst
      .set(inst.seed, metadata.paramMap("seed").toString.toLong)
      .set(inst.subsamplingRate, metadata.paramMap("subsamplingRate").toString.toDouble)
      .set(inst.impurity, metadata.paramMap("impurity").toString)
  }

  override implicit def getTransformer(transformer: RandomForestRegressionModel): LocalTransformer[RandomForestRegressionModel] = new LocalRandomForestRegressionModel(transformer)
}

开发者ID:Hydrospheredata，项目名称:spark-ml-serving，代码行数:53，代码来源:LocalRandomForestRegressionModel.scala

示例2: ScorePredictor

//设置package包名称以及导入依赖的类
package org.wikimedia.research.recommendation.job.translation

import java.io.File

import org.apache.log4j.{LogManager, Logger}
import org.apache.spark.ml.regression.RandomForestRegressionModel
import org.apache.spark.sql.types.{DoubleType, StringType, StructField, StructType}
import org.apache.spark.sql.{DataFrame, Row, SaveMode, SparkSession}

import scala.collection.parallel.mutable.ParArray

object ScorePredictor {
  val log: Logger = LogManager.getLogger(ScorePredictor.getClass)

  def predictScores(spark: SparkSession,
                    modelsInputDir: File,
                    predictionsOutputDir: Option[File],
                    sites: ParArray[String],
                    featureData: DataFrame): Unit = {
    log.info("Scoring items")

    val predictions: Array[DataFrame] = sites.map(target => {
      try {
        log.info("Scoring for " + target)
        log.info("Getting work data for " + target)
        val workData: DataFrame = Utils.getWorkData(spark, featureData, target, exists = false)
        log.info("Loading model for " + target)
        val model = RandomForestRegressionModel.load(
          new File(modelsInputDir, target).getAbsolutePath)
        log.info("Scoring data for " + target)
        val predictions = model
          .setPredictionCol(target)
          .transform(workData)
          .select("id", target)

        predictions
      } catch {
        case unknown: Throwable =>
          log.error("Score for " + target + " failed", unknown)
          val schema = StructType(Seq(
            StructField("id", StringType, nullable = false),
            StructField(target, DoubleType, nullable = true)))
          spark.createDataFrame(spark.sparkContext.emptyRDD[Row], schema)
      }
    }).toArray

    val predictedScores = predictions.reduce((left, right) => left.join(right, Seq("id"), "outer"))

    log.info("Saving predictions")
    predictionsOutputDir.foreach(f = o =>
      predictedScores.coalesce(1)
        .write
        .mode(SaveMode.ErrorIfExists)
        .option("header", value = true)
        .option("compression", "bzip2")
        .csv(new File(o, "allPredictions").getAbsolutePath))
  }
}

开发者ID:schana，项目名称:recommendation-translation，代码行数:59，代码来源:ScorePredictor.scala

示例3: LocalRandomForestRegressionModel

//设置package包名称以及导入依赖的类
package io.hydrosphere.mist.api.ml.regression

import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.linalg.{Vector, Vectors}
import org.apache.spark.ml.regression.{DecisionTreeRegressionModel, RandomForestRegressionModel}


class LocalRandomForestRegressionModel(override val sparkTransformer: RandomForestRegressionModel) extends LocalTransformer[RandomForestRegressionModel] {
  override def transform(localData: LocalData): LocalData = {
    val cls = classOf[RandomForestRegressionModel]
    val predict = cls.getMethod("predict", classOf[Vector])
    localData.column(sparkTransformer.getFeaturesCol) match {
      case Some(column) =>
        val predictionCol = LocalDataColumn(sparkTransformer.getPredictionCol, column.data.map(f => Vectors.dense(f.asInstanceOf[Array[Double]])).map{ vector =>
          predict.invoke(sparkTransformer, vector).asInstanceOf[Double]
        })
        localData.withColumn(predictionCol)
      case None => localData
    }
  }
}

object LocalRandomForestRegressionModel extends LocalModel[RandomForestRegressionModel] {
  override def load(metadata: Metadata, data: Map[String, Any]): RandomForestRegressionModel = {
    val treesMetadata = metadata.paramMap("treesMetadata").asInstanceOf[Map[String, Any]]
    val trees = treesMetadata map { treeKv =>
      val treeMeta = treeKv._2.asInstanceOf[Map[String, Any]]
      val meta = treeMeta("metadata").asInstanceOf[Metadata]
      LocalDecisionTreeRegressionModel.createTree(
        meta,
        data(treeKv._1).asInstanceOf[Map[String, Any]]
      )
    }
    val ctor = classOf[RandomForestRegressionModel].getDeclaredConstructor(classOf[String], classOf[Array[DecisionTreeRegressionModel]], classOf[Int])
    ctor.setAccessible(true)
    val inst = ctor
      .newInstance(
        metadata.uid,
        trees.to[Array],
        metadata.numFeatures.get.asInstanceOf[java.lang.Integer]
      )
      .setFeaturesCol(metadata.paramMap("featuresCol").asInstanceOf[String])
      .setPredictionCol(metadata.paramMap("predictionCol").asInstanceOf[String])

    inst
      .set(inst.seed, metadata.paramMap("seed").toString.toLong)
      .set(inst.subsamplingRate, metadata.paramMap("subsamplingRate").toString.toDouble)
      .set(inst.impurity, metadata.paramMap("impurity").toString)
  }

  override implicit def getTransformer(transformer: RandomForestRegressionModel): LocalTransformer[RandomForestRegressionModel] = new LocalRandomForestRegressionModel(transformer)
}

开发者ID:Hydrospheredata，项目名称:mist，代码行数:53，代码来源:LocalRandomForestRegressionModel.scala

示例4: BaseTransformerConverter

//设置package包名称以及导入依赖的类
package org.apache.spark.ml.mleap.converter.runtime

import com.truecar.mleap.runtime.transformer
import org.apache.spark.ml.PipelineModel
import org.apache.spark.ml.classification.RandomForestClassificationModel
import org.apache.spark.ml.feature.{IndexToString, StandardScalerModel, StringIndexerModel, VectorAssembler}
import org.apache.spark.ml.mleap.classification.SVMModel
import org.apache.spark.ml.mleap.converter.runtime.classification.{RandomForestClassificationModelToMleap, SupportVectorMachineModelToMleap}
import org.apache.spark.ml.mleap.converter.runtime.feature.{IndexToStringToMleap, StandardScalerModelToMleap, StringIndexerModelToMleap, VectorAssemblerModelToMleap}
import org.apache.spark.ml.mleap.converter.runtime.regression.{LinearRegressionModelToMleap, RandomForestRegressionModelToMleap}
import org.apache.spark.ml.regression.{LinearRegressionModel, RandomForestRegressionModel}


trait BaseTransformerConverter extends SparkTransformerConverter {
  // regression
  implicit val mleapLinearRegressionModelToMleap: TransformerToMleap[LinearRegressionModel, transformer.LinearRegressionModel] =
    addConverter(LinearRegressionModelToMleap)
  implicit val mleapRandomForestRegressionModelToMleap: TransformerToMleap[RandomForestRegressionModel, transformer.RandomForestRegressionModel] =
    addConverter(RandomForestRegressionModelToMleap)

  // classification
  implicit val mleapRandomForestClassificationModelToMleap: TransformerToMleap[RandomForestClassificationModel, transformer.RandomForestClassificationModel] =
    addConverter(RandomForestClassificationModelToMleap)
  implicit val mleapSupportVectorMachineModelToMleap: TransformerToMleap[SVMModel, transformer.SupportVectorMachineModel] =
    addConverter(SupportVectorMachineModelToMleap)

  //feature
  implicit val mleapIndexToStringToMleap: TransformerToMleap[IndexToString, transformer.ReverseStringIndexerModel] =
    addConverter(IndexToStringToMleap)
  implicit val mleapStandardScalerModelToMleap: TransformerToMleap[StandardScalerModel, transformer.StandardScalerModel] =
    addConverter(StandardScalerModelToMleap)
  implicit val mleapStringIndexerModelToMleap: TransformerToMleap[StringIndexerModel, transformer.StringIndexerModel] =
    addConverter(StringIndexerModelToMleap)
  implicit val mleapVectorAssemblerToMleap: TransformerToMleap[VectorAssembler, transformer.VectorAssemblerModel] =
    addConverter(VectorAssemblerModelToMleap)

  // other
  implicit val mleapPipelineModelToMleap: TransformerToMleap[PipelineModel, transformer.PipelineModel] =
    addConverter(PipelineModelToMleap(this))
}
object BaseTransformerConverter extends BaseTransformerConverter

开发者ID:TrueCar，项目名称:mleap，代码行数:42，代码来源:BaseTransformerConverter.scala

注：本文中的org.apache.spark.ml.regression.RandomForestRegressionModel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。