Scala Normalizer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.feature.Normalizer类的典型用法代码示例。如果您正苦于以下问题：Scala Normalizer类的具体用法？Scala Normalizer怎么用？Scala Normalizer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Normalizer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，您的评价将有助于我们的系统推荐出更棒的Scala代码示例。

示例1: LocalNormalizer

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

import io.hydrosphere.spark_ml_serving._
import org.apache.spark.ml.feature.Normalizer
import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vector, Vectors}

class LocalNormalizer(override val sparkTransformer: Normalizer) extends LocalTransformer[Normalizer] {
  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val method = classOf[Normalizer].getMethod("createTransformFunc")
        val newData = column.data.map(r => {
          val vector = r match {
            case x: List[Any] => Vectors.dense(x.map(_.toString.toDouble).toArray)
            case x: SparseVector => x
            case x: DenseVector => x
            case unknown =>
              throw new IllegalArgumentException(s"Unknown data type for LocalMaxAbsScaler: ${unknown.getClass}")
          }
          method.invoke(sparkTransformer).asInstanceOf[Vector => Vector](vector)
        })
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, newData))
      case None => localData
    }
  }
}

object LocalNormalizer extends LocalModel[Normalizer] {
  override def load(metadata: Metadata, data: Map[String, Any]): Normalizer = {
    new Normalizer(metadata.uid)
      .setInputCol(metadata.paramMap("inputCol").asInstanceOf[String])
      .setOutputCol(metadata.paramMap("outputCol").asInstanceOf[String])
      .setP(metadata.paramMap("p").toString.toDouble)
  }

  override implicit def getTransformer(transformer: Normalizer): LocalTransformer[Normalizer] = new LocalNormalizer(transformer)
}

开发者ID:Hydrospheredata，项目名称:spark-ml-serving，代码行数:38，代码来源:LocalNormalizer.scala

示例2: LocalNormalizer

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

import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.feature.Normalizer
import org.apache.spark.ml.linalg.{DenseVector, SparseVector, Vector, Vectors}

class LocalNormalizer(override val sparkTransformer: Normalizer) extends LocalTransformer[Normalizer] {
  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val method = classOf[Normalizer].getMethod("createTransformFunc")
        val newData = column.data.map(r => {
          val vector = r match {
            case x: List[Any] => Vectors.dense(x.map(_.toString.toDouble).toArray)
            case x: SparseVector => x
            case x: DenseVector => x
            case unknown =>
              throw new IllegalArgumentException(s"Unknown data type for LocalMaxAbsScaler: ${unknown.getClass}")
          }
          method.invoke(sparkTransformer).asInstanceOf[Vector => Vector](vector)
        })
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, newData))
      case None => localData
    }
  }
}

object LocalNormalizer extends LocalModel[Normalizer] {
  override def load(metadata: Metadata, data: Map[String, Any]): Normalizer = {
    new Normalizer(metadata.uid)
      .setInputCol(metadata.paramMap("inputCol").asInstanceOf[String])
      .setOutputCol(metadata.paramMap("outputCol").asInstanceOf[String])
      .setP(metadata.paramMap("p").toString.toDouble)
  }

  override implicit def getTransformer(transformer: Normalizer): LocalTransformer[Normalizer] = new LocalNormalizer(transformer)
}

开发者ID:Hydrospheredata，项目名称:mist，代码行数:38，代码来源:LocalNormalizer.scala

示例3: NormalizerJob

//设置package包名称以及导入依赖的类
import io.hydrosphere.mist.api._
import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.linalg.{Vector => LVector}
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.feature.Normalizer
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.sql.SparkSession

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

  def train(savePath: String): Map[String, Any] = {
    val df = session.createDataFrame(Seq(
      (0, Vectors.dense(1.0, 0.5, -1.0)),
      (1, Vectors.dense(2.0, 1.0, 1.0)),
      (2, Vectors.dense(4.0, 10.0, 2.0))
    )).toDF("id", "features")

    val normalizer = new Normalizer()
      .setInputCol("features")
      .setOutputCol("normFeatures")
      .setP(1.0)

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

    val model = pipeline.fit(df)

    model.write.overwrite().save(savePath)
    Map.empty[String, Any]
  }

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

    val pipeline = PipelineLoader.load(modelPath)
    val data = LocalData(LocalDataColumn("features", features))

    val response = pipeline.transform(data).toMapList.map(rowMap => {
      val conv = rowMap("normFeatures").asInstanceOf[LVector].toArray
      rowMap + ("normFeatures" -> conv)
    })


    Map("result" -> response)
  }
}

开发者ID:Hydrospheredata，项目名称:mist，代码行数:51，代码来源:NormalizerJob.scala

注：本文中的org.apache.spark.ml.feature.Normalizer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。