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

//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.NGram

class LocalNGram(override val sparkTransformer: NGram) extends LocalTransformer[NGram] {
  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val method = classOf[NGram].getMethod("createTransformFunc")
        val f = method.invoke(sparkTransformer).asInstanceOf[Seq[String] => Seq[String]]
        val data = column.data.head.asInstanceOf[Seq[String]]
        val newData = f.apply(data).toList
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, List(newData)))
      case None => localData
    }
  }
}

object LocalNGram extends LocalModel[NGram] {
  override def load(metadata: Metadata, data: Map[String, Any]): NGram = {
    new NGram(metadata.uid)
        .setN(metadata.paramMap("n").asInstanceOf[Number].intValue())
        .setInputCol(metadata.paramMap("inputCol").asInstanceOf[String])
        .setOutputCol(metadata.paramMap("outputCol").asInstanceOf[String])
  }

  override implicit def getTransformer(transformer: NGram): LocalTransformer[NGram] = new LocalNGram(transformer)
}

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

示例2: LocalNGram

//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.NGram

class LocalNGram(override val sparkTransformer: NGram) extends LocalTransformer[NGram] {
  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val method = classOf[NGram].getMethod("createTransformFunc")
        val f = method.invoke(sparkTransformer).asInstanceOf[Seq[String] => Seq[String]]
        val data = column.data.head.asInstanceOf[Seq[String]]
        val newData = f.apply(data).toList
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, List(newData)))
      case None => localData
    }
  }
}

object LocalNGram extends LocalModel[NGram] {
  override def load(metadata: Metadata, data: Map[String, Any]): NGram = {
    new NGram(metadata.uid)
        .setN(metadata.paramMap("n").asInstanceOf[Number].intValue())
        .setInputCol(metadata.paramMap("inputCol").asInstanceOf[String])
        .setOutputCol(metadata.paramMap("outputCol").asInstanceOf[String])
  }

  override implicit def getTransformer(transformer: NGram): LocalTransformer[NGram] = new LocalNGram(transformer)
}

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

示例3: NgramJob

//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.NGram
import org.apache.spark.sql.SparkSession


object NgramJob 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, Array("Provectus", "is", "such", "a", "cool", "company")),
      (1, Array("Big", "data", "rules", "the", "world")),
      (2, Array("Cloud", "solutions", "are", "our", "future"))
    )).toDF("id", "words")

    val ngram = new NGram().setN(2).setInputCol("words").setOutputCol("ngrams")

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

    val model = pipeline.fit(df)

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

  def serve(modelPath: String, features: List[String]): Map[String, Any] = {

    import LocalPipelineModel._

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

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

开发者ID:Hydrospheredata，项目名称:mist，代码行数:45，代码来源:NgramJob.scala

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