• Home
• com.microsoft.ml.spark
• mmlspark_2.11
• 0.18.1
• source code
• Explode.scala

×

Project download

Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance.
Project price only 1 $

You can buy this project and download/modify it how often you want.

com.microsoft.ml.spark.stages.Explode.scala Maven / Gradle / Ivy

// Copyright (C) Microsoft Corporation. All rights reserved.
// Licensed under the MIT License. See LICENSE in project root for information.

package com.microsoft.ml.spark.stages

import com.microsoft.ml.spark.core.contracts.{HasInputCol, HasOutputCol, Wrappable}
import org.apache.spark.sql.{DataFrame, Dataset}
import org.apache.spark.ml.Transformer
import org.apache.spark.ml.param._
import org.apache.spark.ml.util._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._

object Explode extends DefaultParamsReadable[Explode]

class Explode(val uid: String) extends Transformer
  with HasInputCol with HasOutputCol with Wrappable with DefaultParamsWritable {
  def this() = this(Identifiable.randomUID("Explode"))

  setDefault(outputCol->(this.uid + "_output"))

  override def transform(dataset: Dataset[_]): DataFrame = {
    transformSchema(dataset.schema)
    dataset.toDF().withColumn(getOutputCol, explode(col(getInputCol)))
  }

  def transformSchema(schema: StructType): StructType = {
    val innerType = schema(getInputCol).dataType match {
      case ArrayType(it, _) => it
      case dt =>
        throw new IllegalArgumentException("Explode only accepts array columns")
    }
   schema.add(getOutputCol, innerType)
  }

  def copy(extra: ParamMap): Explode = defaultCopy(extra)

}