org.apache.spark.mllib.classification.SVMModel Scala Examples

The following examples show how to use org.apache.spark.mllib.classification.SVMModel. 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: PMMLModelExportFactory.scala From iolap with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 2

Source File: SVMWithSGDExample.scala From Swallow with Apache License 2.0

5 votes

package com.intel.hibench.sparkbench.ml

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.{SVMModel, SVMWithSGD}
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.rdd.RDD
import org.apache.spark.mllib.regression.LabeledPoint

import scopt.OptionParser

object SVMWithSGDExample {

   case class Params(
     numIterations: Int = 100,
     stepSize: Double = 1.0,
     regParam: Double = 0.01,
     dataPath: String = null
   )

  def main(args: Array[String]): Unit = {
    val defaultParams = Params()

    val parser = new OptionParser[Params]("SVM") {
      head("SVM: an example of SVM for classification.")
      opt[Int]("numIterations")
        .text(s"numIterations, default: ${defaultParams.numIterations}")
        .action((x,c) => c.copy(numIterations = x))
      opt[Double]("stepSize")
        .text(s"stepSize, default: ${defaultParams.stepSize}")
        .action((x,c) => c.copy(stepSize = x))
      opt[Double]("regParam")
        .text(s"regParam, default: ${defaultParams.regParam}")
        .action((x,c) => c.copy(regParam = x))
      arg[String]("<dataPath>")
        .required()
        .text("data path of SVM")
        .action((x, c) => c.copy(dataPath = x)) 
    }
    parser.parse(args, defaultParams) match {
      case Some(params) => run(params)
      case _ => sys.exit(1)
    }
  }

  def run(params: Params): Unit = {

    val conf = new SparkConf().setAppName(s"SVM with $params")
                              .set("spark.shuffle.compress", "false")
                              .set("spark.io.compression.codec", "org.apache.spark.io.LZFCompressionCodec")
                              .set("spark.smartCompress", "false")
                         
    val sc = new SparkContext(conf)

    val dataPath = params.dataPath
    val numIterations = params.numIterations
    val stepSize = params.stepSize
    val regParam = params.regParam

    val data: RDD[LabeledPoint] = sc.objectFile(dataPath)

    // Split data into training (60%) and test (40%).
    val splits = data.randomSplit(Array(0.6, 0.4), seed = 11L)
    val training = splits(0).cache()
    val test = splits(1)

    // Run training algorithm to build the model
    val model = SVMWithSGD.train(training, numIterations, stepSize, regParam)

    // Clear the default threshold.
    model.clearThreshold()

    // Compute raw scores on the test set.
    val scoreAndLabels = test.map { point =>
      val score = model.predict(point.features)
      (score, point.label)
    }

    // Get evaluation metrics.
    val metrics = new BinaryClassificationMetrics(scoreAndLabels)
    val auROC = metrics.areaUnderROC()

    println("Area under ROC = " + auROC)

    sc.stop()
  }
}

Example 3

Source File: PMMLModelExportFactorySuite.scala From BigDatalog with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

class PMMLModelExportFactorySuite extends SparkFunSuite {

  test("PMMLModelExportFactory create KMeansPMMLModelExport when passing a KMeansModel") {
    val clusterCenters = Array(
      Vectors.dense(1.0, 2.0, 6.0),
      Vectors.dense(1.0, 3.0, 0.0),
      Vectors.dense(1.0, 4.0, 6.0))
    val kmeansModel = new KMeansModel(clusterCenters)

    val modelExport = PMMLModelExportFactory.createPMMLModelExport(kmeansModel)

    assert(modelExport.isInstanceOf[KMeansPMMLModelExport])
  }

  test("PMMLModelExportFactory create GeneralizedLinearPMMLModelExport when passing a "
    + "LinearRegressionModel, RidgeRegressionModel or LassoModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val linearRegressionModel =
      new LinearRegressionModel(linearInput(0).features, linearInput(0).label)
    val linearModelExport = PMMLModelExportFactory.createPMMLModelExport(linearRegressionModel)
    assert(linearModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val ridgeRegressionModel =
      new RidgeRegressionModel(linearInput(0).features, linearInput(0).label)
    val ridgeModelExport = PMMLModelExportFactory.createPMMLModelExport(ridgeRegressionModel)
    assert(ridgeModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val lassoModel = new LassoModel(linearInput(0).features, linearInput(0).label)
    val lassoModelExport = PMMLModelExportFactory.createPMMLModelExport(lassoModel)
    assert(lassoModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])
  }

  test("PMMLModelExportFactory create BinaryClassificationPMMLModelExport "
    + "when passing a LogisticRegressionModel or SVMModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val logisticRegressionModel =
      new LogisticRegressionModel(linearInput(0).features, linearInput(0).label)
    val logisticRegressionModelExport =
      PMMLModelExportFactory.createPMMLModelExport(logisticRegressionModel)
    assert(logisticRegressionModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])

    val svmModel = new SVMModel(linearInput(0).features, linearInput(0).label)
    val svmModelExport = PMMLModelExportFactory.createPMMLModelExport(svmModel)
    assert(svmModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])
  }

  test("PMMLModelExportFactory throw IllegalArgumentException "
    + "when passing a Multinomial Logistic Regression") {
    
    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}

Example 4

Source File: PMMLModelExportFactory.scala From BigDatalog with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 5

Source File: PMMLModelExportFactorySuite.scala From Spark-2.3.1 with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

class PMMLModelExportFactorySuite extends SparkFunSuite {

  test("PMMLModelExportFactory create KMeansPMMLModelExport when passing a KMeansModel") {
    val clusterCenters = Array(
      Vectors.dense(1.0, 2.0, 6.0),
      Vectors.dense(1.0, 3.0, 0.0),
      Vectors.dense(1.0, 4.0, 6.0))
    val kmeansModel = new KMeansModel(clusterCenters)

    val modelExport = PMMLModelExportFactory.createPMMLModelExport(kmeansModel)

    assert(modelExport.isInstanceOf[KMeansPMMLModelExport])
  }

  test("PMMLModelExportFactory create GeneralizedLinearPMMLModelExport when passing a "
    + "LinearRegressionModel, RidgeRegressionModel or LassoModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val linearRegressionModel =
      new LinearRegressionModel(linearInput(0).features, linearInput(0).label)
    val linearModelExport = PMMLModelExportFactory.createPMMLModelExport(linearRegressionModel)
    assert(linearModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val ridgeRegressionModel =
      new RidgeRegressionModel(linearInput(0).features, linearInput(0).label)
    val ridgeModelExport = PMMLModelExportFactory.createPMMLModelExport(ridgeRegressionModel)
    assert(ridgeModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val lassoModel = new LassoModel(linearInput(0).features, linearInput(0).label)
    val lassoModelExport = PMMLModelExportFactory.createPMMLModelExport(lassoModel)
    assert(lassoModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])
  }

  test("PMMLModelExportFactory create BinaryClassificationPMMLModelExport "
    + "when passing a LogisticRegressionModel or SVMModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val logisticRegressionModel =
      new LogisticRegressionModel(linearInput(0).features, linearInput(0).label)
    val logisticRegressionModelExport =
      PMMLModelExportFactory.createPMMLModelExport(logisticRegressionModel)
    assert(logisticRegressionModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])

    val svmModel = new SVMModel(linearInput(0).features, linearInput(0).label)
    val svmModelExport = PMMLModelExportFactory.createPMMLModelExport(svmModel)
    assert(svmModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])
  }

  test("PMMLModelExportFactory throw IllegalArgumentException "
    + "when passing a Multinomial Logistic Regression") {
    
    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}

Example 6

Source File: PMMLModelExportFactory.scala From Spark-2.3.1 with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 7

Source File: PMMLModelExportFactorySuite.scala From spark1.52 with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      //numClasses 分类数
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}

Example 8

Source File: PMMLModelExportFactory.scala From spark1.52 with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 9

Source File: PMMLModelExportFactorySuite.scala From iolap with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

class PMMLModelExportFactorySuite extends SparkFunSuite {

  test("PMMLModelExportFactory create KMeansPMMLModelExport when passing a KMeansModel") {
    val clusterCenters = Array(
      Vectors.dense(1.0, 2.0, 6.0),
      Vectors.dense(1.0, 3.0, 0.0),
      Vectors.dense(1.0, 4.0, 6.0))
    val kmeansModel = new KMeansModel(clusterCenters)

    val modelExport = PMMLModelExportFactory.createPMMLModelExport(kmeansModel)

    assert(modelExport.isInstanceOf[KMeansPMMLModelExport])
  }

  test("PMMLModelExportFactory create GeneralizedLinearPMMLModelExport when passing a "
    + "LinearRegressionModel, RidgeRegressionModel or LassoModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val linearRegressionModel =
      new LinearRegressionModel(linearInput(0).features, linearInput(0).label)
    val linearModelExport = PMMLModelExportFactory.createPMMLModelExport(linearRegressionModel)
    assert(linearModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val ridgeRegressionModel =
      new RidgeRegressionModel(linearInput(0).features, linearInput(0).label)
    val ridgeModelExport = PMMLModelExportFactory.createPMMLModelExport(ridgeRegressionModel)
    assert(ridgeModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val lassoModel = new LassoModel(linearInput(0).features, linearInput(0).label)
    val lassoModelExport = PMMLModelExportFactory.createPMMLModelExport(lassoModel)
    assert(lassoModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])
  }

  test("PMMLModelExportFactory create BinaryClassificationPMMLModelExport "
    + "when passing a LogisticRegressionModel or SVMModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val logisticRegressionModel =
      new LogisticRegressionModel(linearInput(0).features, linearInput(0).label)
    val logisticRegressionModelExport =
      PMMLModelExportFactory.createPMMLModelExport(logisticRegressionModel)
    assert(logisticRegressionModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])

    val svmModel = new SVMModel(linearInput(0).features, linearInput(0).label)
    val svmModelExport = PMMLModelExportFactory.createPMMLModelExport(svmModel)
    assert(svmModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])
  }

  test("PMMLModelExportFactory throw IllegalArgumentException "
    + "when passing a Multinomial Logistic Regression") {
    
    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}

Example 10

Source File: PMMLModelExportFactory.scala From drizzle-spark with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 11

Source File: PMMLModelExportFactorySuite.scala From multi-tenancy-spark with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

class PMMLModelExportFactorySuite extends SparkFunSuite {

  test("PMMLModelExportFactory create KMeansPMMLModelExport when passing a KMeansModel") {
    val clusterCenters = Array(
      Vectors.dense(1.0, 2.0, 6.0),
      Vectors.dense(1.0, 3.0, 0.0),
      Vectors.dense(1.0, 4.0, 6.0))
    val kmeansModel = new KMeansModel(clusterCenters)

    val modelExport = PMMLModelExportFactory.createPMMLModelExport(kmeansModel)

    assert(modelExport.isInstanceOf[KMeansPMMLModelExport])
  }

  test("PMMLModelExportFactory create GeneralizedLinearPMMLModelExport when passing a "
    + "LinearRegressionModel, RidgeRegressionModel or LassoModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val linearRegressionModel =
      new LinearRegressionModel(linearInput(0).features, linearInput(0).label)
    val linearModelExport = PMMLModelExportFactory.createPMMLModelExport(linearRegressionModel)
    assert(linearModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val ridgeRegressionModel =
      new RidgeRegressionModel(linearInput(0).features, linearInput(0).label)
    val ridgeModelExport = PMMLModelExportFactory.createPMMLModelExport(ridgeRegressionModel)
    assert(ridgeModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val lassoModel = new LassoModel(linearInput(0).features, linearInput(0).label)
    val lassoModelExport = PMMLModelExportFactory.createPMMLModelExport(lassoModel)
    assert(lassoModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])
  }

  test("PMMLModelExportFactory create BinaryClassificationPMMLModelExport "
    + "when passing a LogisticRegressionModel or SVMModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val logisticRegressionModel =
      new LogisticRegressionModel(linearInput(0).features, linearInput(0).label)
    val logisticRegressionModelExport =
      PMMLModelExportFactory.createPMMLModelExport(logisticRegressionModel)
    assert(logisticRegressionModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])

    val svmModel = new SVMModel(linearInput(0).features, linearInput(0).label)
    val svmModelExport = PMMLModelExportFactory.createPMMLModelExport(svmModel)
    assert(svmModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])
  }

  test("PMMLModelExportFactory throw IllegalArgumentException "
    + "when passing a Multinomial Logistic Regression") {
    
    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}

Example 12

Source File: PMMLModelExportFactory.scala From multi-tenancy-spark with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 13

Source File: PMMLModelExportFactorySuite.scala From sparkoscope with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

class PMMLModelExportFactorySuite extends SparkFunSuite {

  test("PMMLModelExportFactory create KMeansPMMLModelExport when passing a KMeansModel") {
    val clusterCenters = Array(
      Vectors.dense(1.0, 2.0, 6.0),
      Vectors.dense(1.0, 3.0, 0.0),
      Vectors.dense(1.0, 4.0, 6.0))
    val kmeansModel = new KMeansModel(clusterCenters)

    val modelExport = PMMLModelExportFactory.createPMMLModelExport(kmeansModel)

    assert(modelExport.isInstanceOf[KMeansPMMLModelExport])
  }

  test("PMMLModelExportFactory create GeneralizedLinearPMMLModelExport when passing a "
    + "LinearRegressionModel, RidgeRegressionModel or LassoModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val linearRegressionModel =
      new LinearRegressionModel(linearInput(0).features, linearInput(0).label)
    val linearModelExport = PMMLModelExportFactory.createPMMLModelExport(linearRegressionModel)
    assert(linearModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val ridgeRegressionModel =
      new RidgeRegressionModel(linearInput(0).features, linearInput(0).label)
    val ridgeModelExport = PMMLModelExportFactory.createPMMLModelExport(ridgeRegressionModel)
    assert(ridgeModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val lassoModel = new LassoModel(linearInput(0).features, linearInput(0).label)
    val lassoModelExport = PMMLModelExportFactory.createPMMLModelExport(lassoModel)
    assert(lassoModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])
  }

  test("PMMLModelExportFactory create BinaryClassificationPMMLModelExport "
    + "when passing a LogisticRegressionModel or SVMModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val logisticRegressionModel =
      new LogisticRegressionModel(linearInput(0).features, linearInput(0).label)
    val logisticRegressionModelExport =
      PMMLModelExportFactory.createPMMLModelExport(logisticRegressionModel)
    assert(logisticRegressionModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])

    val svmModel = new SVMModel(linearInput(0).features, linearInput(0).label)
    val svmModelExport = PMMLModelExportFactory.createPMMLModelExport(svmModel)
    assert(svmModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])
  }

  test("PMMLModelExportFactory throw IllegalArgumentException "
    + "when passing a Multinomial Logistic Regression") {
    
    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}

Example 14

Source File: PMMLModelExportFactory.scala From sparkoscope with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.dmg.pmml.RegressionNormalizationMethodType

import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.regression.LassoModel
import org.apache.spark.mllib.regression.LinearRegressionModel
import org.apache.spark.mllib.regression.RidgeRegressionModel

private[mllib] object PMMLModelExportFactory {

  
  def createPMMLModelExport(model: Any): PMMLModelExport = {
    model match {
      case kmeans: KMeansModel =>
        new KMeansPMMLModelExport(kmeans)
      case linear: LinearRegressionModel =>
        new GeneralizedLinearPMMLModelExport(linear, "linear regression")
      case ridge: RidgeRegressionModel =>
        new GeneralizedLinearPMMLModelExport(ridge, "ridge regression")
      case lasso: LassoModel =>
        new GeneralizedLinearPMMLModelExport(lasso, "lasso regression")
      case svm: SVMModel =>
        new BinaryClassificationPMMLModelExport(
          svm, "linear SVM", RegressionNormalizationMethodType.NONE,
          svm.getThreshold.getOrElse(0.0))
      case logistic: LogisticRegressionModel =>
        if (logistic.numClasses == 2) {
          new BinaryClassificationPMMLModelExport(
            logistic, "logistic regression", RegressionNormalizationMethodType.LOGIT,
            logistic.getThreshold.getOrElse(0.5))
        } else {
          throw new IllegalArgumentException(
            "PMML Export not supported for Multinomial Logistic Regression")
        }
      case _ =>
        throw new IllegalArgumentException(
          "PMML Export not supported for model: " + model.getClass.getName)
    }
  }

}

Example 15

Source File: SVM.scala From spark-cp with Apache License 2.0

5 votes

package se.uu.farmbio.cp.alg

import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.optimization.HingeGradient
import org.apache.spark.mllib.optimization.LBFGS
import org.apache.spark.mllib.optimization.SquaredL2Updater
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils
import org.apache.spark.rdd.RDD

import se.uu.farmbio.cp.UnderlyingAlgorithm

//Define a SVMs UnderlyingAlgorithm
private object SVM {
  def trainingProcedure(
    input: RDD[LabeledPoint],
    maxNumItearations: Int,
    regParam: Double,
    numCorrections: Int,
    convergenceTol: Double) = {

    //Train SVM with LBFGS
    val numFeatures = input.take(1)(0).features.size
    val training = input.map(x => (x.label, MLUtils.appendBias(x.features))).cache()
    val initialWeightsWithIntercept = Vectors.dense(new Array[Double](numFeatures + 1))
    val (weightsWithIntercept, _) = LBFGS.runLBFGS(
      training,
      new HingeGradient(),
      new SquaredL2Updater(),
      numCorrections,
      convergenceTol,
      maxNumItearations,
      regParam,
      initialWeightsWithIntercept)

    //Create the model using the weights
    val model = new SVMModel(
      Vectors.dense(weightsWithIntercept.toArray.slice(0, weightsWithIntercept.size - 1)),
      weightsWithIntercept(weightsWithIntercept.size - 1))

    //Return raw score predictor
    model.clearThreshold()
    model

  }
}

class SVM(val model: SVMModel)
  extends UnderlyingAlgorithm(model.predict) {

  def this(
    input: RDD[LabeledPoint],
    maxNumItearations: Int = 100,
    regParam: Double = 0.1,
    numCorrections: Int = 10,
    convergenceTol: Double = 1e-4) = {

    this(SVM.trainingProcedure(
      input,
      maxNumItearations,
      regParam,
      numCorrections,
      convergenceTol))

  }
  
  def nonConformityMeasure(newSample: LabeledPoint) = {
    val score = predictor(newSample.features)
    if (newSample.label == 1.0) {
      -score
    } else {
      score
    }
  }
  
}

Example 16

Source File: LibLinAlg.scala From spark-cp with Apache License 2.0

5 votes

package se.uu.farmbio.cp.liblinear

import org.apache.spark.mllib.classification.SVMModel
import org.apache.spark.mllib.linalg.Vector
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import de.bwaldvogel.liblinear.Feature
import de.bwaldvogel.liblinear.FeatureNode
import de.bwaldvogel.liblinear.Linear
import de.bwaldvogel.liblinear.Parameter
import de.bwaldvogel.liblinear.Problem
import de.bwaldvogel.liblinear.SolverType
import se.uu.farmbio.cp.UnderlyingAlgorithm
import se.uu.farmbio.cp.Deserializer

object LibLinAlg {

  private def vectorToFeatures(v: Vector) = {
    val indices = v.toSparse.indices
    val values = v.toSparse.values
    indices
      .zip(values)
      .sortBy {
        case (i, v) => i
      }
      .map {
        case (i, v) => new FeatureNode(i + 1, v)
          .asInstanceOf[Feature]
      }
  }

  private def train(
    input: Array[LabeledPoint],
    solverType: SolverType,
    c: Double,
    tol: Double) = {

    //configure problem
    val problem = new Problem
    problem.l = input.length
    problem.n = input(0).features.size
    problem.x = input.map { p =>
      vectorToFeatures(p.features)
    }
    problem.y = input.map(_.label + 1.0)
    problem.bias = -1.0

    //train
    val parameter = new Parameter(solverType, c, tol)
    val libLinModel = Linear.train(problem, parameter)

    //convert to Spark SVMModel
    val weights = libLinModel.getFeatureWeights
    val intercept = libLinModel.getBias
    val svmModel = new SVMModel(Vectors.dense(weights).toSparse, intercept)
    svmModel.clearThreshold
    svmModel

  }

}

object LibLinAlgDeserializer extends Deserializer[LibLinAlg] {
  override def deserialize(alg: String) = {
    val splitted = alg.split(",", 2)
    val intercept = splitted(0)
    val weights = splitted(1)
    val model = new SVMModel(Vectors.parse(weights).toSparse, intercept.toDouble)
    model.clearThreshold()
    new LibLinAlg(model)
  }  
}

class LibLinAlg(
  val svmModel: SVMModel)
  extends UnderlyingAlgorithm(
    (features: Vector) => svmModel.predict(features)) {

  def this(
    training: Array[LabeledPoint],
    solverType: SolverType,
    regParam: Double,
    tol: Double) = {
    this(LibLinAlg.train(training, solverType, regParam, tol))
  }

  override def nonConformityMeasure(newSample: LabeledPoint) = {
    val score = predictor(newSample.features)
    if (newSample.label == 1.0) {
      score
    } else {
      -score
    }
  }

  override def toString = {
    this.svmModel.intercept + "," +
      this.svmModel.weights.toString
  }

}

Example 17

Source File: PMMLModelExportFactorySuite.scala From drizzle-spark with Apache License 2.0

5 votes

package org.apache.spark.mllib.pmml.export

import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.classification.{LogisticRegressionModel, SVMModel}
import org.apache.spark.mllib.clustering.KMeansModel
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.{LassoModel, LinearRegressionModel, RidgeRegressionModel}
import org.apache.spark.mllib.util.LinearDataGenerator

class PMMLModelExportFactorySuite extends SparkFunSuite {

  test("PMMLModelExportFactory create KMeansPMMLModelExport when passing a KMeansModel") {
    val clusterCenters = Array(
      Vectors.dense(1.0, 2.0, 6.0),
      Vectors.dense(1.0, 3.0, 0.0),
      Vectors.dense(1.0, 4.0, 6.0))
    val kmeansModel = new KMeansModel(clusterCenters)

    val modelExport = PMMLModelExportFactory.createPMMLModelExport(kmeansModel)

    assert(modelExport.isInstanceOf[KMeansPMMLModelExport])
  }

  test("PMMLModelExportFactory create GeneralizedLinearPMMLModelExport when passing a "
    + "LinearRegressionModel, RidgeRegressionModel or LassoModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val linearRegressionModel =
      new LinearRegressionModel(linearInput(0).features, linearInput(0).label)
    val linearModelExport = PMMLModelExportFactory.createPMMLModelExport(linearRegressionModel)
    assert(linearModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val ridgeRegressionModel =
      new RidgeRegressionModel(linearInput(0).features, linearInput(0).label)
    val ridgeModelExport = PMMLModelExportFactory.createPMMLModelExport(ridgeRegressionModel)
    assert(ridgeModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])

    val lassoModel = new LassoModel(linearInput(0).features, linearInput(0).label)
    val lassoModelExport = PMMLModelExportFactory.createPMMLModelExport(lassoModel)
    assert(lassoModelExport.isInstanceOf[GeneralizedLinearPMMLModelExport])
  }

  test("PMMLModelExportFactory create BinaryClassificationPMMLModelExport "
    + "when passing a LogisticRegressionModel or SVMModel") {
    val linearInput = LinearDataGenerator.generateLinearInput(3.0, Array(10.0, 10.0), 1, 17)

    val logisticRegressionModel =
      new LogisticRegressionModel(linearInput(0).features, linearInput(0).label)
    val logisticRegressionModelExport =
      PMMLModelExportFactory.createPMMLModelExport(logisticRegressionModel)
    assert(logisticRegressionModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])

    val svmModel = new SVMModel(linearInput(0).features, linearInput(0).label)
    val svmModelExport = PMMLModelExportFactory.createPMMLModelExport(svmModel)
    assert(svmModelExport.isInstanceOf[BinaryClassificationPMMLModelExport])
  }

  test("PMMLModelExportFactory throw IllegalArgumentException "
    + "when passing a Multinomial Logistic Regression") {
    
    val multiclassLogisticRegressionModel = new LogisticRegressionModel(
      weights = Vectors.dense(0.1, 0.2, 0.3, 0.4), intercept = 1.0,
      numFeatures = 2, numClasses = 3)

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(multiclassLogisticRegressionModel)
    }
  }

  test("PMMLModelExportFactory throw IllegalArgumentException when passing an unsupported model") {
    val invalidModel = new Object

    intercept[IllegalArgumentException] {
      PMMLModelExportFactory.createPMMLModelExport(invalidModel)
    }
  }
}