org.apache.spark.ml.feature.PolynomialExpansion Scala Examples

The following examples show how to use org.apache.spark.ml.feature.PolynomialExpansion. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: PolynomialExpansionExample.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession

object PolynomialExpansionExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("PolynomialExpansionExample")
      .getOrCreate()

    // $example on$
    val data = Array(
      Vectors.dense(2.0, 1.0),
      Vectors.dense(0.0, 0.0),
      Vectors.dense(3.0, -1.0)
    )
    val df = spark.createDataFrame(data.map(Tuple1.apply)).toDF("features")

    val polyExpansion = new PolynomialExpansion()
      .setInputCol("features")
      .setOutputCol("polyFeatures")
      .setDegree(3)

    val polyDF = polyExpansion.transform(df)
    polyDF.show(false)
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 2
Source File: LocalPolynomialExpansion.scala    From spark-ml-serving   with Apache License 2.0 5 votes vote down vote up 
package io.hydrosphere.spark_ml_serving.preprocessors

import io.hydrosphere.spark_ml_serving.TypedTransformerConverter
import io.hydrosphere.spark_ml_serving.common.utils.DataUtils._
import io.hydrosphere.spark_ml_serving.common._
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.ml.linalg.{Vector, Vectors}

class LocalPolynomialExpansion(override val sparkTransformer: PolynomialExpansion)
  extends LocalTransformer[PolynomialExpansion] {

  override def transform(localData: LocalData): LocalData = {
    localData.column(sparkTransformer.getInputCol) match {
      case Some(column) =>
        val method = classOf[PolynomialExpansion].getMethod("createTransformFunc")
        val newData = column.data.map(r => {
          val row            = r.asInstanceOf[List[Any]].map(_.toString.toDouble).toArray
          val vector: Vector = Vectors.dense(row)
          method.invoke(sparkTransformer).asInstanceOf[Vector => Vector](vector).toList
        })
        localData.withColumn(LocalDataColumn(sparkTransformer.getOutputCol, newData))
      case None => localData
    }
  }
}

object LocalPolynomialExpansion
  extends SimpleModelLoader[PolynomialExpansion]
  with TypedTransformerConverter[PolynomialExpansion] {

  override def build(metadata: Metadata, data: LocalData): PolynomialExpansion = {
    new PolynomialExpansion(metadata.uid)
      .setInputCol(metadata.paramMap("inputCol").asInstanceOf[String])
      .setOutputCol(metadata.paramMap("outputCol").asInstanceOf[String])
      .setDegree(metadata.paramMap("degree").asInstanceOf[Number].intValue())
  }

  override implicit def toLocal(
    transformer: PolynomialExpansion
  ) = new LocalPolynomialExpansion(transformer)
}
Example 3
Source File: PolynomialExpansionOp.scala    From mleap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.bundle.ops.feature

import ml.combust.bundle.BundleContext
import ml.combust.bundle.dsl._
import ml.combust.bundle.op.{OpModel, OpNode}
import ml.combust.mleap.core.types.TensorShape
import org.apache.spark.ml.bundle.{ParamSpec, SimpleParamSpec, SimpleSparkOp, SparkBundleContext}
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.sql.mleap.TypeConverters.sparkToMleapDataShape


class PolynomialExpansionOp extends SimpleSparkOp[PolynomialExpansion] {
  override val Model: OpModel[SparkBundleContext, PolynomialExpansion] = new OpModel[SparkBundleContext, PolynomialExpansion] {
    override val klazz: Class[PolynomialExpansion] = classOf[PolynomialExpansion]

    override def opName: String = Bundle.BuiltinOps.feature.polynomial_expansion

    override def store(model: Model, obj: PolynomialExpansion)
                      (implicit context: BundleContext[SparkBundleContext]): Model = {
      val dataset = context.context.dataset.get
      val inputShape = sparkToMleapDataShape(dataset.schema(obj.getInputCol), dataset).asInstanceOf[TensorShape]
      model.withValue("degree", Value.long(obj.getDegree))
        .withValue("input_size", Value.long(inputShape.dimensions.get.head))
    }

    override def load(model: Model)
                     (implicit context: BundleContext[SparkBundleContext]): PolynomialExpansion = {
      new PolynomialExpansion(uid = "").setDegree(model.value("degree").getLong.toInt)
    }
  }

  override def sparkLoad(uid: String, shape: NodeShape, model: PolynomialExpansion): PolynomialExpansion = {
    new PolynomialExpansion(uid = uid).setDegree(model.getDegree)
  }

  override def sparkInputs(obj: PolynomialExpansion): Seq[ParamSpec] = {
    Seq("input" -> obj.inputCol)
  }

  override def sparkOutputs(obj: PolynomialExpansion): Seq[SimpleParamSpec] = {
    Seq("output" -> obj.outputCol)
  }
}
Example 4
Source File: PolynomialExpansionParitySpec.scala    From mleap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.parity.feature

import org.apache.spark.ml.parity.SparkParityBase
import org.apache.spark.ml.feature.{PolynomialExpansion, VectorAssembler}
import org.apache.spark.ml.{Pipeline, Transformer}
import org.apache.spark.sql.DataFrame


class PolynomialExpansionParitySpec extends SparkParityBase {
  override val dataset: DataFrame = baseDataset.select("dti", "loan_amount")
  override val sparkTransformer: Transformer = new Pipeline().setStages(Array(new VectorAssembler().
    setInputCols(Array("dti", "loan_amount")).
    setOutputCol("features"),
    new PolynomialExpansion().
      setInputCol("features").
      setOutputCol("poly").
      setDegree(3))).fit(dataset)
}
Example 5
Source File: PolynomialExpansionExample.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession

object PolynomialExpansionExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("PolynomialExpansionExample")
      .getOrCreate()

    // $example on$
    val data = Array(
      Vectors.dense(2.0, 1.0),
      Vectors.dense(0.0, 0.0),
      Vectors.dense(3.0, -1.0)
    )
    val df = spark.createDataFrame(data.map(Tuple1.apply)).toDF("features")

    val polyExpansion = new PolynomialExpansion()
      .setInputCol("features")
      .setOutputCol("polyFeatures")
      .setDegree(3)

    val polyDF = polyExpansion.transform(df)
    polyDF.show(false)
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 6
Source File: PolynomialExpansionExample.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession

object PolynomialExpansionExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("PolynomialExpansionExample")
      .getOrCreate()

    // $example on$
    val data = Array(
      Vectors.dense(2.0, 1.0),
      Vectors.dense(0.0, 0.0),
      Vectors.dense(3.0, -1.0)
    )
    val df = spark.createDataFrame(data.map(Tuple1.apply)).toDF("features")

    val polyExpansion = new PolynomialExpansion()
      .setInputCol("features")
      .setOutputCol("polyFeatures")
      .setDegree(3)

    val polyDF = polyExpansion.transform(df)
    polyDF.show(false)
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 7
Source File: PolynomialExpander.scala    From seahorse   with Apache License 2.0 5 votes vote down vote up 
package ai.deepsense.deeplang.doperables.spark.wrappers.transformers

import org.apache.spark.ml.feature.PolynomialExpansion

import ai.deepsense.deeplang.doperables.SparkTransformerAsMultiColumnTransformer
import ai.deepsense.deeplang.params.Param
import ai.deepsense.deeplang.params.validators.RangeValidator
import ai.deepsense.deeplang.params.wrappers.spark.IntParamWrapper

class PolynomialExpander extends SparkTransformerAsMultiColumnTransformer[PolynomialExpansion] {

  override def convertInputNumericToVector: Boolean = true
  override def convertOutputVectorToDouble: Boolean = false

  val degree = new IntParamWrapper[PolynomialExpansion](
    name = "degree",
    description = Some("The polynomial degree to expand."),
    sparkParamGetter = _.degree,
    validator = RangeValidator(2.0, Int.MaxValue, step = Some(1.0)))
  setDefault(degree, 2.0)

  override protected def getSpecificParams: Array[Param[_]] = Array(degree)
}
Example 8
Source File: PolynomialExpansionExample.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession

object PolynomialExpansionExample {
  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("PolynomialExpansionExample")
      .getOrCreate()

    // $example on$
    val data = Array(
      Vectors.dense(2.0, 1.0),
      Vectors.dense(0.0, 0.0),
      Vectors.dense(3.0, -1.0)
    )
    val df = spark.createDataFrame(data.map(Tuple1.apply)).toDF("features")

    val polyExpansion = new PolynomialExpansion()
      .setInputCol("features")
      .setOutputCol("polyFeatures")
      .setDegree(3)

    val polyDF = polyExpansion.transform(df)
    polyDF.show(false)
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 9
Source File: PolynomialExpansionExample.scala    From BigDatalog   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.PolynomialExpansion
import org.apache.spark.mllib.linalg.Vectors
// $example off$
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}

object PolynomialExpansionExample {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("PolynomialExpansionExample")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)

    // $example on$
    val data = Array(
      Vectors.dense(-2.0, 2.3),
      Vectors.dense(0.0, 0.0),
      Vectors.dense(0.6, -1.1)
    )
    val df = sqlContext.createDataFrame(data.map(Tuple1.apply)).toDF("features")
    val polynomialExpansion = new PolynomialExpansion()
      .setInputCol("features")
      .setOutputCol("polyFeatures")
      .setDegree(3)
    val polyDF = polynomialExpansion.transform(df)
    polyDF.select("polyFeatures").take(3).foreach(println)
    // $example off$
    sc.stop()
  }
}
// scalastyle:on println
Example 10
Source File: PolynomialExpander.scala    From seahorse-workflow-executor   with Apache License 2.0 5 votes vote down vote up 
package io.deepsense.deeplang.doperables.spark.wrappers.transformers

import org.apache.spark.ml.feature.PolynomialExpansion

import io.deepsense.deeplang.doperables.SparkTransformerAsMultiColumnTransformer
import io.deepsense.deeplang.params.Param
import io.deepsense.deeplang.params.validators.RangeValidator
import io.deepsense.deeplang.params.wrappers.spark.IntParamWrapper

class PolynomialExpander extends SparkTransformerAsMultiColumnTransformer[PolynomialExpansion] {

  override def convertInputNumericToVector: Boolean = true
  override def convertOutputVectorToDouble: Boolean = false

  val degree = new IntParamWrapper[PolynomialExpansion](
    name = "degree",
    description = Some("The polynomial degree to expand."),
    sparkParamGetter = _.degree,
    validator = RangeValidator(2.0, Int.MaxValue, step = Some(1.0)))
  setDefault(degree, 2.0)

  override protected def getSpecificParams: Array[Param[_]] = Array(degree)
}