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

//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.Binarizer

class LocalBinarizer(override val sparkTransformer: Binarizer) extends LocalTransformer[Binarizer] {
  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val treshhold: Double = sparkTransformer.getThreshold
        val newData = column.data.map(r => {
          if (r.asInstanceOf[Number].doubleValue() > treshhold) 1.0 else 0.0
        })
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, newData))
      case None => localData
    }
  }
}

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

  override implicit def getTransformer(transformer: Binarizer): LocalTransformer[Binarizer] = new LocalBinarizer(transformer)
}

开发者ID:Hydrospheredata，项目名称:spark-ml-serving，代码行数:30，代码来源:LocalBinarizer.scala

示例2: LocalBinarizer

//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.Binarizer

class LocalBinarizer(override val sparkTransformer: Binarizer) extends LocalTransformer[Binarizer] {
  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val treshhold: Double = sparkTransformer.getThreshold
        val newData = column.data.map(r => {
          if (r.asInstanceOf[Number].doubleValue() > treshhold) 1.0 else 0.0
        })
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, newData))
      case None => localData
    }
  }
}

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

  override implicit def getTransformer(transformer: Binarizer): LocalTransformer[Binarizer] = new LocalBinarizer(transformer)
}

开发者ID:Hydrospheredata，项目名称:mist，代码行数:30，代码来源:LocalBinarizer.scala

示例3: BinarizerJob

//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.Pipeline
import org.apache.spark.ml.feature.Binarizer

import org.apache.spark.sql.SparkSession

object BinarizerJob extends MLMistJob {

  def session: SparkSession = SparkSession
    .builder()
    .appName(context.appName)
    .config(context.getConf)
    .getOrCreate()

  def train(savePath: String): Map[String, Any] = {
    val data = Array((0, 0.1), (1, 0.8), (2, 0.2))
    val dataFrame = session.createDataFrame(data).toDF("id", "feature")

    val binarizer: Binarizer = new Binarizer()
      .setInputCol("feature")
      .setOutputCol("binarized_feature")
      .setThreshold(5.0)

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

    val model = pipeline.fit(dataFrame)

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

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

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

    val result: LocalData = pipeline.transform(data)
    Map("result" -> result.select("feature", "binarized_feature").toMapList)
  }
}

开发者ID:Hydrospheredata，项目名称:mist，代码行数:43，代码来源:BinarizerJob.scala

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