org.apache.spark.mllib.tree.impurity.Variance Scala Examples

The following examples show how to use org.apache.spark.mllib.tree.impurity.Variance. 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: GradientBoostedTreesSuite.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.tree.impl

import org.apache.spark.SparkFunSuite
import org.apache.spark.internal.Logging
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.mllib.tree.{GradientBoostedTreesSuite => OldGBTSuite}
import org.apache.spark.mllib.tree.configuration.{BoostingStrategy, Strategy}
import org.apache.spark.mllib.tree.configuration.Algo._
import org.apache.spark.mllib.tree.impurity.Variance
import org.apache.spark.mllib.tree.loss.{AbsoluteError, LogLoss, SquaredError}
import org.apache.spark.mllib.util.MLlibTestSparkContext


class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext with Logging {

  import testImplicits._

  test("runWithValidation stops early and performs better on a validation dataset") {
    // Set numIterations large enough so that it stops early.
    val numIterations = 20
    val trainRdd = sc.parallelize(OldGBTSuite.trainData, 2).map(_.asML)
    val validateRdd = sc.parallelize(OldGBTSuite.validateData, 2).map(_.asML)
    val trainDF = trainRdd.toDF()
    val validateDF = validateRdd.toDF()

    val algos = Array(Regression, Regression, Classification)
    val losses = Array(SquaredError, AbsoluteError, LogLoss)
    algos.zip(losses).foreach { case (algo, loss) =>
      val treeStrategy = new Strategy(algo = algo, impurity = Variance, maxDepth = 2,
        categoricalFeaturesInfo = Map.empty)
      val boostingStrategy =
        new BoostingStrategy(treeStrategy, loss, numIterations, validationTol = 0.0)
      val (validateTrees, validateTreeWeights) = GradientBoostedTrees
        .runWithValidation(trainRdd, validateRdd, boostingStrategy, 42L)
      val numTrees = validateTrees.length
      assert(numTrees !== numIterations)

      // Test that it performs better on the validation dataset.
      val (trees, treeWeights) = GradientBoostedTrees.run(trainRdd, boostingStrategy, 42L)
      val (errorWithoutValidation, errorWithValidation) = {
        if (algo == Classification) {
          val remappedRdd = validateRdd.map(x => new LabeledPoint(2 * x.label - 1, x.features))
          (GradientBoostedTrees.computeError(remappedRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(remappedRdd, validateTrees,
              validateTreeWeights, loss))
        } else {
          (GradientBoostedTrees.computeError(validateRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(validateRdd, validateTrees,
              validateTreeWeights, loss))
        }
      }
      assert(errorWithValidation <= errorWithoutValidation)

      // Test that results from evaluateEachIteration comply with runWithValidation.
      // Note that convergenceTol is set to 0.0
      val evaluationArray = GradientBoostedTrees
        .evaluateEachIteration(validateRdd, trees, treeWeights, loss, algo)
      assert(evaluationArray.length === numIterations)
      assert(evaluationArray(numTrees) > evaluationArray(numTrees - 1))
      var i = 1
      while (i < numTrees) {
        assert(evaluationArray(i) <= evaluationArray(i - 1))
        i += 1
      }
    }
  }

}
Example 2
Source File: GradientBoostedTreesSuite.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.tree.impl

import org.apache.spark.SparkFunSuite
import org.apache.spark.internal.Logging
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.mllib.tree.{GradientBoostedTreesSuite => OldGBTSuite}
import org.apache.spark.mllib.tree.configuration.{BoostingStrategy, Strategy}
import org.apache.spark.mllib.tree.configuration.Algo._
import org.apache.spark.mllib.tree.impurity.Variance
import org.apache.spark.mllib.tree.loss.{AbsoluteError, LogLoss, SquaredError}
import org.apache.spark.mllib.util.MLlibTestSparkContext


class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext with Logging {

  import testImplicits._

  test("runWithValidation stops early and performs better on a validation dataset") {
    // Set numIterations large enough so that it stops early.
    val numIterations = 20
    val trainRdd = sc.parallelize(OldGBTSuite.trainData, 2).map(_.asML)
    val validateRdd = sc.parallelize(OldGBTSuite.validateData, 2).map(_.asML)
    val trainDF = trainRdd.toDF()
    val validateDF = validateRdd.toDF()

    val algos = Array(Regression, Regression, Classification)
    val losses = Array(SquaredError, AbsoluteError, LogLoss)
    algos.zip(losses).foreach { case (algo, loss) =>
      val treeStrategy = new Strategy(algo = algo, impurity = Variance, maxDepth = 2,
        categoricalFeaturesInfo = Map.empty)
      val boostingStrategy =
        new BoostingStrategy(treeStrategy, loss, numIterations, validationTol = 0.0)
      val (validateTrees, validateTreeWeights) = GradientBoostedTrees
        .runWithValidation(trainRdd, validateRdd, boostingStrategy, 42L)
      val numTrees = validateTrees.length
      assert(numTrees !== numIterations)

      // Test that it performs better on the validation dataset.
      val (trees, treeWeights) = GradientBoostedTrees.run(trainRdd, boostingStrategy, 42L)
      val (errorWithoutValidation, errorWithValidation) = {
        if (algo == Classification) {
          val remappedRdd = validateRdd.map(x => new LabeledPoint(2 * x.label - 1, x.features))
          (GradientBoostedTrees.computeError(remappedRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(remappedRdd, validateTrees,
              validateTreeWeights, loss))
        } else {
          (GradientBoostedTrees.computeError(validateRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(validateRdd, validateTrees,
              validateTreeWeights, loss))
        }
      }
      assert(errorWithValidation <= errorWithoutValidation)

      // Test that results from evaluateEachIteration comply with runWithValidation.
      // Note that convergenceTol is set to 0.0
      val evaluationArray = GradientBoostedTrees
        .evaluateEachIteration(validateRdd, trees, treeWeights, loss, algo)
      assert(evaluationArray.length === numIterations)
      assert(evaluationArray(numTrees) > evaluationArray(numTrees - 1))
      var i = 1
      while (i < numTrees) {
        assert(evaluationArray(i) <= evaluationArray(i - 1))
        i += 1
      }
    }
  }

}
Example 3
Source File: GradientBoostedTreesSuite.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.tree.impl

import org.apache.spark.SparkFunSuite
import org.apache.spark.internal.Logging
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.mllib.tree.{GradientBoostedTreesSuite => OldGBTSuite}
import org.apache.spark.mllib.tree.configuration.{BoostingStrategy, Strategy}
import org.apache.spark.mllib.tree.configuration.Algo._
import org.apache.spark.mllib.tree.impurity.Variance
import org.apache.spark.mllib.tree.loss.{AbsoluteError, LogLoss, SquaredError}
import org.apache.spark.mllib.util.MLlibTestSparkContext


class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext with Logging {

  import testImplicits._

  test("runWithValidation stops early and performs better on a validation dataset") {
    // Set numIterations large enough so that it stops early.
    val numIterations = 20
    val trainRdd = sc.parallelize(OldGBTSuite.trainData, 2).map(_.asML)
    val validateRdd = sc.parallelize(OldGBTSuite.validateData, 2).map(_.asML)
    val trainDF = trainRdd.toDF()
    val validateDF = validateRdd.toDF()

    val algos = Array(Regression, Regression, Classification)
    val losses = Array(SquaredError, AbsoluteError, LogLoss)
    algos.zip(losses).foreach { case (algo, loss) =>
      val treeStrategy = new Strategy(algo = algo, impurity = Variance, maxDepth = 2,
        categoricalFeaturesInfo = Map.empty)
      val boostingStrategy =
        new BoostingStrategy(treeStrategy, loss, numIterations, validationTol = 0.0)
      val (validateTrees, validateTreeWeights) = GradientBoostedTrees
        .runWithValidation(trainRdd, validateRdd, boostingStrategy, 42L)
      val numTrees = validateTrees.length
      assert(numTrees !== numIterations)

      // Test that it performs better on the validation dataset.
      val (trees, treeWeights) = GradientBoostedTrees.run(trainRdd, boostingStrategy, 42L)
      val (errorWithoutValidation, errorWithValidation) = {
        if (algo == Classification) {
          val remappedRdd = validateRdd.map(x => new LabeledPoint(2 * x.label - 1, x.features))
          (GradientBoostedTrees.computeError(remappedRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(remappedRdd, validateTrees,
              validateTreeWeights, loss))
        } else {
          (GradientBoostedTrees.computeError(validateRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(validateRdd, validateTrees,
              validateTreeWeights, loss))
        }
      }
      assert(errorWithValidation <= errorWithoutValidation)

      // Test that results from evaluateEachIteration comply with runWithValidation.
      // Note that convergenceTol is set to 0.0
      val evaluationArray = GradientBoostedTrees
        .evaluateEachIteration(validateRdd, trees, treeWeights, loss, algo)
      assert(evaluationArray.length === numIterations)
      assert(evaluationArray(numTrees) > evaluationArray(numTrees - 1))
      var i = 1
      while (i < numTrees) {
        assert(evaluationArray(i) <= evaluationArray(i - 1))
        i += 1
      }
    }
  }

}
Example 4
Source File: GradientBoostedTreesSuite.scala    From Spark-2.3.1   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.tree.impl

import org.apache.spark.SparkFunSuite
import org.apache.spark.internal.Logging
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.mllib.tree.{GradientBoostedTreesSuite => OldGBTSuite}
import org.apache.spark.mllib.tree.configuration.{BoostingStrategy, Strategy}
import org.apache.spark.mllib.tree.configuration.Algo._
import org.apache.spark.mllib.tree.impurity.Variance
import org.apache.spark.mllib.tree.loss.{AbsoluteError, LogLoss, SquaredError}
import org.apache.spark.mllib.util.MLlibTestSparkContext


class GradientBoostedTreesSuite extends SparkFunSuite with MLlibTestSparkContext with Logging {

  import testImplicits._

  test("runWithValidation stops early and performs better on a validation dataset") {
    // Set numIterations large enough so that it stops early.
    val numIterations = 20
    val trainRdd = sc.parallelize(OldGBTSuite.trainData, 2).map(_.asML)
    val validateRdd = sc.parallelize(OldGBTSuite.validateData, 2).map(_.asML)
    val trainDF = trainRdd.toDF()
    val validateDF = validateRdd.toDF()

    val algos = Array(Regression, Regression, Classification)
    val losses = Array(SquaredError, AbsoluteError, LogLoss)
    algos.zip(losses).foreach { case (algo, loss) =>
      val treeStrategy = new Strategy(algo = algo, impurity = Variance, maxDepth = 2,
        categoricalFeaturesInfo = Map.empty)
      val boostingStrategy =
        new BoostingStrategy(treeStrategy, loss, numIterations, validationTol = 0.0)
      val (validateTrees, validateTreeWeights) = GradientBoostedTrees
        .runWithValidation(trainRdd, validateRdd, boostingStrategy, 42L, "all")
      val numTrees = validateTrees.length
      assert(numTrees !== numIterations)

      // Test that it performs better on the validation dataset.
      val (trees, treeWeights) = GradientBoostedTrees.run(trainRdd, boostingStrategy, 42L, "all")
      val (errorWithoutValidation, errorWithValidation) = {
        if (algo == Classification) {
          val remappedRdd = validateRdd.map(x => new LabeledPoint(2 * x.label - 1, x.features))
          (GradientBoostedTrees.computeError(remappedRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(remappedRdd, validateTrees,
              validateTreeWeights, loss))
        } else {
          (GradientBoostedTrees.computeError(validateRdd, trees, treeWeights, loss),
            GradientBoostedTrees.computeError(validateRdd, validateTrees,
              validateTreeWeights, loss))
        }
      }
      assert(errorWithValidation <= errorWithoutValidation)

      // Test that results from evaluateEachIteration comply with runWithValidation.
      // Note that convergenceTol is set to 0.0
      val evaluationArray = GradientBoostedTrees
        .evaluateEachIteration(validateRdd, trees, treeWeights, loss, algo)
      assert(evaluationArray.length === numIterations)
      assert(evaluationArray(numTrees) > evaluationArray(numTrees - 1))
      var i = 1
      while (i < numTrees) {
        assert(evaluationArray(i) <= evaluationArray(i - 1))
        i += 1
      }
    }
  }

}