org.apache.spark.ml.regression.GeneralizedLinearRegression Scala Examples

The following examples show how to use org.apache.spark.ml.regression.GeneralizedLinearRegression. 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: GeneralizedLinearRegressionExample.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.regression.GeneralizedLinearRegression
// $example off$
import org.apache.spark.sql.SparkSession



object GeneralizedLinearRegressionExample {

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

    // $example on$
    // Load training data
    val dataset = spark.read.format("libsvm")
      .load("data/mllib/sample_linear_regression_data.txt")

    val glr = new GeneralizedLinearRegression()
      .setFamily("gaussian")
      .setLink("identity")
      .setMaxIter(10)
      .setRegParam(0.3)

    // Fit the model
    val model = glr.fit(dataset)

    // Print the coefficients and intercept for generalized linear regression model
    println(s"Coefficients: ${model.coefficients}")
    println(s"Intercept: ${model.intercept}")

    // Summarize the model over the training set and print out some metrics
    val summary = model.summary
    println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}")
    println(s"T Values: ${summary.tValues.mkString(",")}")
    println(s"P Values: ${summary.pValues.mkString(",")}")
    println(s"Dispersion: ${summary.dispersion}")
    println(s"Null Deviance: ${summary.nullDeviance}")
    println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}")
    println(s"Deviance: ${summary.deviance}")
    println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}")
    println(s"AIC: ${summary.aic}")
    println("Deviance Residuals: ")
    summary.residuals().show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 2
Source File: GeneralizedLinearRegressionParitySpec.scala    From mleap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.parity.regression

import org.apache.spark.ml.feature.{OneHotEncoderEstimator, StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, Transformer}
import org.apache.spark.ml.parity.SparkParityBase
import org.apache.spark.ml.regression.GeneralizedLinearRegression
import org.apache.spark.sql._


class GeneralizedLinearRegressionParitySpec extends SparkParityBase {
  override val dataset: DataFrame = baseDataset.select("fico_score_group_fnl", "dti", "loan_amount")
  override val sparkTransformer: Transformer = new Pipeline().setStages(Array(new StringIndexer().
    setInputCol("fico_score_group_fnl").
    setOutputCol("fico_index"),
    new OneHotEncoderEstimator().
      setInputCols(Array("fico_index")).
      setOutputCols(Array("fico")),
    new VectorAssembler().
      setInputCols(Array("fico", "dti")).
      setOutputCol("features"),
    new GeneralizedLinearRegression().
      setFamily("gaussian").
      setLink("log").
      setFeaturesCol("features").
      setLabelCol("loan_amount").
      setPredictionCol("prediction"))).fit(dataset)

  override val unserializedParams = Set("stringOrderType", "labelCol", "maxIter", "tol", "regParam", "solver", "variancePower")
}
Example 3
Source File: GeneralizedLinearRegressionPipeline.scala    From Machine-Learning-with-Spark-Second-Edition   with MIT License 5 votes vote down vote up 
package org.sparksamples.regression.bikesharing

import org.apache.log4j.Logger
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.feature.{VectorAssembler, VectorIndexer}
import org.apache.spark.ml.regression.GeneralizedLinearRegression
import org.apache.spark.mllib.evaluation.RegressionMetrics
import org.apache.spark.sql.{SparkSession, _}


object GeneralizedLinearRegressionPipeline {

  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def genLinearRegressionWithVectorFormat(vectorAssembler: VectorAssembler, vectorIndexer: VectorIndexer, dataFrame: DataFrame) = {
    val lr = new GeneralizedLinearRegression()
      .setFeaturesCol("features")
      .setLabelCol("label")
      .setFamily("gaussian")
      .setLink("identity")
      .setMaxIter(10)
      .setRegParam(0.3)

    val pipeline = new Pipeline().setStages(Array(vectorAssembler, vectorIndexer, lr))

    val Array(training, test) = dataFrame.randomSplit(Array(0.8, 0.2), seed = 12345)

    val model = pipeline.fit(training)

    val fullPredictions = model.transform(test).cache()
    val predictions = fullPredictions.select("prediction").rdd.map(_.getDouble(0))
    val labels = fullPredictions.select("label").rdd.map(_.getDouble(0))
    val RMSE = new RegressionMetrics(predictions.zip(labels)).rootMeanSquaredError
    println(s"  Root mean squared error (RMSE): $RMSE")
  }

  def genLinearRegressionWithSVMFormat(spark: SparkSession) = {
    // Load training data
    val training = spark.read.format("libsvm")
      .load("./src/main/scala/org/sparksamples/regression/dataset/BikeSharing/lsvmHours.txt")

    val lr = new GeneralizedLinearRegression()
      .setFamily("gaussian")
      .setLink("identity")
      .setMaxIter(10)
      .setRegParam(0.3)

    // Fit the model
    val model = lr.fit(training)

    // Print the coefficients and intercept for generalized linear regression model
    println(s"Coefficients: ${model.coefficients}")
    println(s"Intercept: ${model.intercept}")

    // Summarize the model over the training set and print out some metrics
    val summary = model.summary
    println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}")
    println(s"T Values: ${summary.tValues.mkString(",")}")
    println(s"P Values: ${summary.pValues.mkString(",")}")
    println(s"Dispersion: ${summary.dispersion}")
    println(s"Null Deviance: ${summary.nullDeviance}")
    println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}")
    println(s"Deviance: ${summary.deviance}")
    println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}")
    println(s"AIC: ${summary.aic}")
    println("Deviance Residuals: ")
    summary.residuals().show()  }

}
Example 4
Source File: GeneralizedLinearRegressionExample.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.regression.GeneralizedLinearRegression
// $example off$
import org.apache.spark.sql.SparkSession



object GeneralizedLinearRegressionExample {

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

    // $example on$
    // Load training data
    val dataset = spark.read.format("libsvm")
      .load("data/mllib/sample_linear_regression_data.txt")

    val glr = new GeneralizedLinearRegression()
      .setFamily("gaussian")
      .setLink("identity")
      .setMaxIter(10)
      .setRegParam(0.3)

    // Fit the model
    val model = glr.fit(dataset)

    // Print the coefficients and intercept for generalized linear regression model
    println(s"Coefficients: ${model.coefficients}")
    println(s"Intercept: ${model.intercept}")

    // Summarize the model over the training set and print out some metrics
    val summary = model.summary
    println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}")
    println(s"T Values: ${summary.tValues.mkString(",")}")
    println(s"P Values: ${summary.pValues.mkString(",")}")
    println(s"Dispersion: ${summary.dispersion}")
    println(s"Null Deviance: ${summary.nullDeviance}")
    println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}")
    println(s"Deviance: ${summary.deviance}")
    println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}")
    println(s"AIC: ${summary.aic}")
    println("Deviance Residuals: ")
    summary.residuals().show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 5
Source File: GLMRegression.scala    From spark-sql-perf   with Apache License 2.0 5 votes vote down vote up 
package com.databricks.spark.sql.perf.mllib.regression

import org.apache.spark.ml.evaluation.{Evaluator, RegressionEvaluator}
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.regression.GeneralizedLinearRegression
import org.apache.spark.ml.{ModelBuilderSSP, PipelineStage, Transformer}

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


object GLMRegression extends BenchmarkAlgorithm with TestFromTraining with
  TrainingSetFromTransformer with ScoringWithEvaluator {

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    DataGenerator.generateContinuousFeatures(
      ctx.sqlContext,
      numExamples,
      ctx.seed(),
      numPartitions,
      numFeatures)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    import ctx.params._
    val rng = ctx.newGenerator()
    val coefficients =
      Vectors.dense(Array.fill[Double](ctx.params.numFeatures)(2 * rng.nextDouble() - 1))
    // Small intercept to prevent some skew in the data.
    val intercept = 0.01 * (2 * rng.nextDouble - 1)
    val m = ModelBuilderSSP.newGLR(coefficients, intercept)
    m.set(m.link, link.get)
    m.set(m.family, family.get)
    m
  }

  override def getPipelineStage(ctx: MLBenchContext): PipelineStage = {
    import ctx.params._
    new GeneralizedLinearRegression()
      .setLink(link)
      .setFamily(family)
      .setRegParam(regParam)
      .setMaxIter(maxIter)
      .setTol(tol)
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new RegressionEvaluator()
}
Example 6
Source File: GeneralizedLinearRegressionExample.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.regression.GeneralizedLinearRegression
// $example off$
import org.apache.spark.sql.SparkSession



object GeneralizedLinearRegressionExample {

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

    // $example on$
    // Load training data
    val dataset = spark.read.format("libsvm")
      .load("data/mllib/sample_linear_regression_data.txt")

    val glr = new GeneralizedLinearRegression()
      .setFamily("gaussian")
      .setLink("identity")
      .setMaxIter(10)
      .setRegParam(0.3)

    // Fit the model
    val model = glr.fit(dataset)

    // Print the coefficients and intercept for generalized linear regression model
    println(s"Coefficients: ${model.coefficients}")
    println(s"Intercept: ${model.intercept}")

    // Summarize the model over the training set and print out some metrics
    val summary = model.summary
    println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}")
    println(s"T Values: ${summary.tValues.mkString(",")}")
    println(s"P Values: ${summary.pValues.mkString(",")}")
    println(s"Dispersion: ${summary.dispersion}")
    println(s"Null Deviance: ${summary.nullDeviance}")
    println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}")
    println(s"Deviance: ${summary.deviance}")
    println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}")
    println(s"AIC: ${summary.aic}")
    println("Deviance Residuals: ")
    summary.residuals().show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println
Example 7
Source File: OpGeneralizedLinearRegressionTest.scala    From TransmogrifAI   with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
package com.salesforce.op.stages.impl.regression

import com.salesforce.op.features.types._
import com.salesforce.op.stages.impl.PredictionEquality
import com.salesforce.op.stages.sparkwrappers.specific.{OpPredictorWrapper, OpPredictorWrapperModel}
import com.salesforce.op.test._
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.regression.{GeneralizedLinearRegression, GeneralizedLinearRegressionModel}
import org.junit.runner.RunWith
import org.scalatest.junit.JUnitRunner

@RunWith(classOf[JUnitRunner])
class OpGeneralizedLinearRegressionTest extends OpEstimatorSpec[Prediction,
  OpPredictorWrapperModel[GeneralizedLinearRegressionModel],
  OpPredictorWrapper[GeneralizedLinearRegression, GeneralizedLinearRegressionModel]] with PredictionEquality {

  override def specName: String = Spec[OpGeneralizedLinearRegression]

  val (inputData, rawLabel, features) = TestFeatureBuilder(
    Seq[(RealNN, OPVector)](
      (10.0.toRealNN, Vectors.dense(1.0, 4.3, 1.3).toOPVector),
      (20.0.toRealNN, Vectors.dense(2.0, 0.3, 0.1).toOPVector),
      (30.0.toRealNN, Vectors.dense(3.0, 3.9, 4.3).toOPVector),
      (40.0.toRealNN, Vectors.dense(4.0, 1.3, 0.9).toOPVector),
      (50.0.toRealNN, Vectors.dense(5.0, 4.7, 1.3).toOPVector)
    )
  )
  val label = rawLabel.copy(isResponse = true)
  val estimator = new OpGeneralizedLinearRegression().setInput(label, features)

  val expectedResult = Seq(
    Prediction(10.0, 9.99),
    Prediction(20.0, 19.99),
    Prediction(30.0, 29.99),
    Prediction(40.0, 40.0),
    Prediction(50.0, 50.0)
  )

  it should "allow the user to set the desired spark parameters" in {
    estimator
      .setMaxIter(10)
      .setRegParam(0.1)
      .setFitIntercept(true)
      .setTol(1E-4)
      .setSolver("irls")
    estimator.fit(inputData)

    estimator.predictor.getMaxIter shouldBe 10
    estimator.predictor.getRegParam shouldBe 0.1
    estimator.predictor.getFitIntercept shouldBe true
    estimator.predictor.getTol shouldBe 1E-4
    estimator.predictor.getSolver shouldBe "irls"

  }
}
Example 8
Source File: GeneralizedLinearRegressionExample.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.regression.GeneralizedLinearRegression
// $example off$
import org.apache.spark.sql.SparkSession



object GeneralizedLinearRegressionExample {

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

    // $example on$
    // Load training data
    val dataset = spark.read.format("libsvm")
      .load("data/mllib/sample_linear_regression_data.txt")

    val glr = new GeneralizedLinearRegression()
      .setFamily("gaussian")
      .setLink("identity")
      .setMaxIter(10)
      .setRegParam(0.3)

    // Fit the model
    val model = glr.fit(dataset)

    // Print the coefficients and intercept for generalized linear regression model
    println(s"Coefficients: ${model.coefficients}")
    println(s"Intercept: ${model.intercept}")

    // Summarize the model over the training set and print out some metrics
    val summary = model.summary
    println(s"Coefficient Standard Errors: ${summary.coefficientStandardErrors.mkString(",")}")
    println(s"T Values: ${summary.tValues.mkString(",")}")
    println(s"P Values: ${summary.pValues.mkString(",")}")
    println(s"Dispersion: ${summary.dispersion}")
    println(s"Null Deviance: ${summary.nullDeviance}")
    println(s"Residual Degree Of Freedom Null: ${summary.residualDegreeOfFreedomNull}")
    println(s"Deviance: ${summary.deviance}")
    println(s"Residual Degree Of Freedom: ${summary.residualDegreeOfFreedom}")
    println(s"AIC: ${summary.aic}")
    println("Deviance Residuals: ")
    summary.residuals().show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println