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

The following examples show how to use org.apache.spark.mllib.classification.NaiveBayes. 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: SparseNaiveBayes.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


object SparseNaiveBayes {

  case class Params(
      input: String = null,
      minPartitions: Int = 0,
      numFeatures: Int = -1,
      lambda: Double = 1.0) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("SparseNaiveBayes") {
      head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
      opt[Int]("numPartitions")
        .text("min number of partitions")
        .action((x, c) => c.copy(minPartitions = x))
      opt[Int]("numFeatures")
        .text("number of features")
        .action((x, c) => c.copy(numFeatures = x))
      opt[Double]("lambda")
        .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
        .action((x, c) => c.copy(lambda = x))
      arg[String]("<input>")
        .text("input paths to labeled examples in LIBSVM format")
        .required()
        .action((x, c) => c.copy(input = 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"SparseNaiveBayes with $params")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()

    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest

    println(s"Test accuracy = $accuracy.")

    sc.stop()
  }
}
// scalastyle:on println
Example 2
Source File: SparseNaiveBayes.scala    From BigDatalog   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


object SparseNaiveBayes {

  case class Params(
      input: String = null,
      minPartitions: Int = 0,
      numFeatures: Int = -1,
      lambda: Double = 1.0) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("SparseNaiveBayes") {
      head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
      opt[Int]("numPartitions")
        .text("min number of partitions")
        .action((x, c) => c.copy(minPartitions = x))
      opt[Int]("numFeatures")
        .text("number of features")
        .action((x, c) => c.copy(numFeatures = x))
      opt[Double]("lambda")
        .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
        .action((x, c) => c.copy(lambda = x))
      arg[String]("<input>")
        .text("input paths to labeled examples in LIBSVM format")
        .required()
        .action((x, c) => c.copy(input = x))
    }

    parser.parse(args, defaultParams).map { params =>
      run(params)
    }.getOrElse {
      sys.exit(1)
    }
  }

  def run(params: Params) {
    val conf = new SparkConf().setAppName(s"SparseNaiveBayes with $params")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()

    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest

    println(s"Test accuracy = $accuracy.")

    sc.stop()
  }
}
// scalastyle:on println
Example 3
Source File: NaiveBayesExample.scala    From BigDatalog   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

// $example on$
import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel}
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
// $example off$
import org.apache.spark.{SparkConf, SparkContext}

object NaiveBayesExample {

  def main(args: Array[String]) : Unit = {
    val conf = new SparkConf().setAppName("NaiveBayesExample")
    val sc = new SparkContext(conf)
    // $example on$
    val data = sc.textFile("data/mllib/sample_naive_bayes_data.txt")
    val parsedData = data.map { line =>
      val parts = line.split(',')
      LabeledPoint(parts(0).toDouble, Vectors.dense(parts(1).split(' ').map(_.toDouble)))
    }

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

    val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial")

    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()

    // Save and load model
    model.save(sc, "target/tmp/myNaiveBayesModel")
    val sameModel = NaiveBayesModel.load(sc, "target/tmp/myNaiveBayesModel")
    // $example off$
  }
}

// scalastyle:on println
Example 4
Source File: SparseNaiveBayes.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.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


object SparseNaiveBayes {

  case class Params(
      input: String = null,
      minPartitions: Int = 0,
      numFeatures: Int = -1,
      lambda: Double = 1.0) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("SparseNaiveBayes") {
      head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
      opt[Int]("numPartitions")
        .text("min number of partitions")
        .action((x, c) => c.copy(minPartitions = x))
      opt[Int]("numFeatures")
        .text("number of features")
        .action((x, c) => c.copy(numFeatures = x))
      opt[Double]("lambda")
        .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
        .action((x, c) => c.copy(lambda = x))
      arg[String]("<input>")
        .text("input paths to labeled examples in LIBSVM format")
        .required()
        .action((x, c) => c.copy(input = 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"SparseNaiveBayes with $params")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()

    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest

    println(s"Test accuracy = $accuracy.")

    sc.stop()
  }
}
// scalastyle:on println
Example 5
Source File: NaiveBayesExample.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.mllib

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel}
import org.apache.spark.mllib.util.MLUtils
// $example off$

object NaiveBayesExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("NaiveBayesExample")
    val sc = new SparkContext(conf)
    // $example on$
    // Load and parse the data file.
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

    // Split data into training (60%) and test (40%).
    val Array(training, test) = data.randomSplit(Array(0.6, 0.4))

    val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial")

    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()

    // Save and load model
    model.save(sc, "target/tmp/myNaiveBayesModel")
    val sameModel = NaiveBayesModel.load(sc, "target/tmp/myNaiveBayesModel")
    // $example off$

    sc.stop()
  }
}

// scalastyle:on println
Example 6
Source File: SparseNaiveBayes.scala    From spark1.52   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


    }

    parser.parse(args, defaultParams).map { params =>
      run(params)
    }.getOrElse {
      sys.exit(1)
    }
  }

  def run(params: Params) {
    val conf = new SparkConf().setAppName(s"SparseNaiveBayes with $params").setMaster("local")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    //缓存的例子,因为它将被用于在训练和评估。
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()
    //numTraining = 81, numTest = 19.
    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest
   //Test accuracy = 1.0. 准确率
    println(s"Test accuracy = $accuracy.")

    sc.stop()
  }
}
// scalastyle:on println
Example 7
Source File: SparseNaiveBayes.scala    From iolap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.examples.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


object SparseNaiveBayes {

  case class Params(
      input: String = null,
      minPartitions: Int = 0,
      numFeatures: Int = -1,
      lambda: Double = 1.0) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("SparseNaiveBayes") {
      head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
      opt[Int]("numPartitions")
        .text("min number of partitions")
        .action((x, c) => c.copy(minPartitions = x))
      opt[Int]("numFeatures")
        .text("number of features")
        .action((x, c) => c.copy(numFeatures = x))
      opt[Double]("lambda")
        .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
        .action((x, c) => c.copy(lambda = x))
      arg[String]("<input>")
        .text("input paths to labeled examples in LIBSVM format")
        .required()
        .action((x, c) => c.copy(input = x))
    }

    parser.parse(args, defaultParams).map { params =>
      run(params)
    }.getOrElse {
      sys.exit(1)
    }
  }

  def run(params: Params) {
    val conf = new SparkConf().setAppName(s"SparseNaiveBayes with $params")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()

    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest

    println(s"Test accuracy = $accuracy.")

    sc.stop()
  }
}
Example 8
Source File: SparseNaiveBayes.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


object SparseNaiveBayes {

  case class Params(
      input: String = null,
      minPartitions: Int = 0,
      numFeatures: Int = -1,
      lambda: Double = 1.0) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("SparseNaiveBayes") {
      head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
      opt[Int]("numPartitions")
        .text("min number of partitions")
        .action((x, c) => c.copy(minPartitions = x))
      opt[Int]("numFeatures")
        .text("number of features")
        .action((x, c) => c.copy(numFeatures = x))
      opt[Double]("lambda")
        .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
        .action((x, c) => c.copy(lambda = x))
      arg[String]("<input>")
        .text("input paths to labeled examples in LIBSVM format")
        .required()
        .action((x, c) => c.copy(input = 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"SparseNaiveBayes with $params")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()

    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest

    println(s"Test accuracy = $accuracy.")

    sc.stop()
  }
}
// scalastyle:on println
Example 9
Source File: NaiveBayesExample.scala    From multi-tenancy-spark   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel}
import org.apache.spark.mllib.util.MLUtils
// $example off$

object NaiveBayesExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("NaiveBayesExample")
    val sc = new SparkContext(conf)
    // $example on$
    // Load and parse the data file.
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

    // Split data into training (60%) and test (40%).
    val Array(training, test) = data.randomSplit(Array(0.6, 0.4))

    val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial")

    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()

    // Save and load model
    model.save(sc, "target/tmp/myNaiveBayesModel")
    val sameModel = NaiveBayesModel.load(sc, "target/tmp/myNaiveBayesModel")
    // $example off$
  }
}

// scalastyle:on println
Example 10
Source File: NaiveBayesExample.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel}
import org.apache.spark.mllib.util.MLUtils
// $example off$

object NaiveBayesExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("NaiveBayesExample")
    val sc = new SparkContext(conf)
    // $example on$
    // Load and parse the data file.
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

    // Split data into training (60%) and test (40%).
    val Array(training, test) = data.randomSplit(Array(0.6, 0.4))

    val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial")

    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()

    // Save and load model
    model.save(sc, "target/tmp/myNaiveBayesModel")
    val sameModel = NaiveBayesModel.load(sc, "target/tmp/myNaiveBayesModel")
    // $example off$
  }
}

// scalastyle:on println
Example 11
Source File: NaiveBayesExample.scala    From sparkoscope   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.classification.{NaiveBayes, NaiveBayesModel}
import org.apache.spark.mllib.util.MLUtils
// $example off$

object NaiveBayesExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("NaiveBayesExample")
    val sc = new SparkContext(conf)
    // $example on$
    // Load and parse the data file.
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")

    // Split data into training (60%) and test (40%).
    val Array(training, test) = data.randomSplit(Array(0.6, 0.4))

    val model = NaiveBayes.train(training, lambda = 1.0, modelType = "multinomial")

    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()

    // Save and load model
    model.save(sc, "target/tmp/myNaiveBayesModel")
    val sameModel = NaiveBayesModel.load(sc, "target/tmp/myNaiveBayesModel")
    // $example off$
  }
}

// scalastyle:on println
Example 12
Source File: DocumentClassification.scala    From Machine-Learning-with-Spark-Second-Edition   with MIT License 5 votes vote down vote up 
import org.apache.spark.SparkContext
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.evaluation.MulticlassMetrics
import org.apache.spark.mllib.feature.{HashingTF, IDF}
import org.apache.spark.mllib.linalg.SparseVector
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.linalg.{SparseVector => SV}
import org.apache.spark.mllib.util.MLUtils
//import org.apache.spark.ml.feature.HashingTF
//import org.apache.spark.ml.feature.IDF


object DocumentClassification {

  def main(args: Array[String]) {
    val sc = new SparkContext("local[2]", "First Spark App")

    val path = "../data/20news-bydate-train/*"
    val rdd = sc.wholeTextFiles(path)
    val text = rdd.map { case (file, text) => text }
    val newsgroups = rdd.map { case (file, text) => file.split("/").takeRight(2).head }
    val newsgroupsMap = newsgroups.distinct.collect().zipWithIndex.toMap
    val dim = math.pow(2, 18).toInt
    val hashingTF = new HashingTF(dim)

    var tokens = text.map(doc => TFIDFExtraction.tokenize(doc))
    val tf = hashingTF.transform(tokens)
    tf.cache
    val v = tf.first.asInstanceOf[SV]


    val idf = new IDF().fit(tf)
    val tfidf = idf.transform(tf)
    val zipped = newsgroups.zip(tfidf)
    println(zipped.first())
    val train = zipped.map { case (topic, vector) => {
      LabeledPoint(newsgroupsMap(topic), vector)
    } }

    //TODO uncomment to generate libsvm format
    MLUtils.saveAsLibSVMFile(train,"./output/20news-by-date-train-libsvm")

    train.cache
    val model = NaiveBayes.train(train, lambda = 0.1)

    val testPath = "../data/20news-bydate-test/*"
    val testRDD = sc.wholeTextFiles(testPath)
    val testLabels = testRDD.map { case (file, text) =>
      val topic = file.split("/").takeRight(2).head
      newsgroupsMap(topic)
    }
    val testTf = testRDD.map { case (file, text) => hashingTF.transform(TFIDFExtraction.tokenize(text)) }
    val testTfIdf = idf.transform(testTf)
    val zippedTest = testLabels.zip(testTfIdf)
    val test = zippedTest.map { case (topic, vector) => {
      println(topic)
      println(vector)
      LabeledPoint(topic, vector)
    } }

    //TODO uncomment to generate libsvm format
    MLUtils.saveAsLibSVMFile(test,"./output/20news-by-date-test-libsvm")


    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()
    println(accuracy)
    // Updated Dec 2016 by Rajdeep
    //0.7928836962294211
    val metrics = new MulticlassMetrics(predictionAndLabel)
    println(metrics.accuracy)
    println(metrics.weightedFalsePositiveRate)
    println(metrics.weightedPrecision)
    println(metrics.weightedFMeasure)
    println(metrics.weightedRecall)
    //0.7822644376431702

    val rawTokens = rdd.map { case (file, text) => text.split(" ") }
    val rawTF = rawTokens.map(doc => hashingTF.transform(doc))
    val rawTrain = newsgroups.zip(rawTF).map { case (topic, vector) => LabeledPoint(newsgroupsMap(topic), vector) }
    val rawModel = NaiveBayes.train(rawTrain, lambda = 0.1)
    val rawTestTF = testRDD.map { case (file, text) => hashingTF.transform(text.split(" ")) }
    val rawZippedTest = testLabels.zip(rawTestTF)
    val rawTest = rawZippedTest.map { case (topic, vector) => LabeledPoint(topic, vector) }
    val rawPredictionAndLabel = rawTest.map(p => (rawModel.predict(p.features), p.label))
    val rawAccuracy = 1.0 * rawPredictionAndLabel.filter(x => x._1 == x._2).count() / rawTest.count()
    println(rawAccuracy)
    // 0.7661975570897503
    val rawMetrics = new MulticlassMetrics(rawPredictionAndLabel)
    println(rawMetrics.weightedFMeasure)
    // older value 0.7628947184990661
    // dec 2016 : 0.7653320418573546

    sc.stop()
  }

}
Example 13
Source File: DocumentClassification.scala    From Machine-Learning-with-Spark-Second-Edition   with MIT License 5 votes vote down vote up 
import org.apache.spark.SparkContext
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.evaluation.MulticlassMetrics
import org.apache.spark.mllib.feature.{HashingTF, IDF}
import org.apache.spark.mllib.linalg.SparseVector
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.linalg.{ SparseVector => SV }


object DocumentClassification {

  def main(args: Array[String]) {
    val sc = new SparkContext("local[2]", "First Spark App")

    val path = "../data/20news-bydate-train/*"
    val rdd = sc.wholeTextFiles(path)
    val text = rdd.map { case (file, text) => text }
    val newsgroups = rdd.map { case (file, text) => file.split("/").takeRight(2).head }
    val newsgroupsMap = newsgroups.distinct.collect().zipWithIndex.toMap
    val dim = math.pow(2, 18).toInt
    val hashingTF = new HashingTF(dim)

    var tokens = text.map(doc => TFIDFExtraction.tokenize(doc))
    val tf = hashingTF.transform(tokens)
    tf.cache
    val v = tf.first.asInstanceOf[SV]


    val idf = new IDF().fit(tf)
    val tfidf = idf.transform(tf)
    val zipped = newsgroups.zip(tfidf)
    val train = zipped.map { case (topic, vector) => LabeledPoint(newsgroupsMap(topic), vector) }
    train.cache
    val model = NaiveBayes.train(train, lambda = 0.1)

    val testPath = "../data/20news-bydate-test/*"
    val testRDD = sc.wholeTextFiles(testPath)
    val testLabels = testRDD.map { case (file, text) =>
      val topic = file.split("/").takeRight(2).head
      newsgroupsMap(topic)
    }
    val testTf = testRDD.map { case (file, text) => hashingTF.transform(TFIDFExtraction.tokenize(text)) }
    val testTfIdf = idf.transform(testTf)
    val zippedTest = testLabels.zip(testTfIdf)
    val test = zippedTest.map { case (topic, vector) => LabeledPoint(topic, vector) }

    val predictionAndLabel = test.map(p => (model.predict(p.features), p.label))
    val accuracy = 1.0 * predictionAndLabel.filter(x => x._1 == x._2).count() / test.count()
    println(accuracy)
    // Updated Dec 2016 by Rajdeep
    //0.7928836962294211
    val metrics = new MulticlassMetrics(predictionAndLabel)
    println(metrics.weightedFMeasure)
    //0.7822644376431702

    val rawTokens = rdd.map { case (file, text) => text.split(" ") }
    val rawTF = rawTokens.map(doc => hashingTF.transform(doc))
    val rawTrain = newsgroups.zip(rawTF).map { case (topic, vector) => LabeledPoint(newsgroupsMap(topic), vector) }
    val rawModel = NaiveBayes.train(rawTrain, lambda = 0.1)
    val rawTestTF = testRDD.map { case (file, text) => hashingTF.transform(text.split(" ")) }
    val rawZippedTest = testLabels.zip(rawTestTF)
    val rawTest = rawZippedTest.map { case (topic, vector) => LabeledPoint(topic, vector) }
    val rawPredictionAndLabel = rawTest.map(p => (rawModel.predict(p.features), p.label))
    val rawAccuracy = 1.0 * rawPredictionAndLabel.filter(x => x._1 == x._2).count() / rawTest.count()
    println(rawAccuracy)
    // 0.7661975570897503
    val rawMetrics = new MulticlassMetrics(rawPredictionAndLabel)
    println(rawMetrics.weightedFMeasure)
    // older value 0.7628947184990661
    // dec 2016 : 0.7653320418573546
    sc.stop()
  }

}
Example 14
Source File: PipeClassificationSvm.scala    From sddf   with GNU General Public License v3.0 5 votes vote down vote up 
package de.unihamburg.vsis.sddf.classification

import scala.beans.BeanInfo
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.rdd.RDD
import de.unihamburg.vsis.sddf.SddfContext.SymPairSim
import de.unihamburg.vsis.sddf.reading.SymPair
import de.unihamburg.vsis.sddf.reading.Tuple
import org.apache.spark.mllib.classification.SVMWithSGD

class PipeClassificationSvm(numIterations: Int = 100) extends AbstractPipeClassification {

  val paramMap: Map[String, Any] = Map(("numIterations", numIterations))

    def trainModelAndClassify(
    trainingData: RDD[LabeledPoint],
    symPairSim: SymPairSim): RDD[(SymPair[Tuple], Array[Double], Double)] = {
    
    val model = SVMWithSGD.train(trainingData, numIterations)

    log.debug("Classification Model:" + model)

    // Marking Missing Values as Not Equal (0)
    symPairSim.map(pair => (pair._1, pair._2, model.predict(Vectors.dense(pair._2))))
  }

}

object PipeClassificationSvm {
  def apply(numIterations: Int = 100) = {
    new PipeClassificationSvm(numIterations)
  }
}
Example 15
Source File: PipeClassificationNaiveBayes.scala    From sddf   with GNU General Public License v3.0 5 votes vote down vote up 
package de.unihamburg.vsis.sddf.classification

import scala.beans.BeanInfo
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.rdd.RDD
import de.unihamburg.vsis.sddf.SddfContext.SymPairSim
import de.unihamburg.vsis.sddf.reading.SymPair
import de.unihamburg.vsis.sddf.reading.Tuple
import org.apache.spark.mllib.classification.NaiveBayesModel


class PipeClassificationNaiveBayes(lambda: Double = 1.0) extends AbstractPipeClassification {

  val paramMap: Map[String, Any] = Map(("lambda", lambda))

    def trainModelAndClassify(
    trainingData: RDD[LabeledPoint],
    symPairSim: SymPairSim): RDD[(SymPair[Tuple], Array[Double], Double)] = {
    
    val model = NaiveBayes.train(trainingData, lambda)

    log.debug("Classification Model:" + model)
    log.debug("Classification Model labels :" + model.labels.mkString(" "))
    log.debug("Classification Model pi:     " + model.pi.mkString(" "))
    log.debug("Classification Model theta:  " + model.theta.foreach(_.mkString(" ")))

    // Marking Missing Values as Not Equal (0)
    symPairSim.map(pair => (pair._1, pair._2, model.predict(Vectors.dense(pair._2))))
  }

}

object PipeClassificationNaiveBayes {
  def apply(lambda: Double = 1.0) = {
    new PipeClassificationNaiveBayes(lambda)
  }
}
Example 16
Source File: DigitRecognizer.scala    From AI   with Apache License 2.0 5 votes vote down vote up 
package com.bigchange.train

import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}



    val predictResult = Seq(0.001,0.01,0.1,1.0,10.0).map { param =>
      val nbModel = trainNBWithParams(testData,param,"multinomial")
      val predictResult =  testData.map { labeledPoint =>
        val predicted = nbModel.predict(labeledPoint.features)
        if (predicted > 0.5) 1 else 0
      }.reduce(_ + _)
      val accuracy = predictResult / testData.count * 1.0
      println(s"nb model with lambda:$param,modelTpye:multinomial,Accuracy:$accuracy")
    }
  }
}
Example 17
Source File: SparseNaiveBayes.scala    From drizzle-spark   with Apache License 2.0 5 votes vote down vote up 
// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.log4j.{Level, Logger}
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.NaiveBayes
import org.apache.spark.mllib.util.MLUtils


object SparseNaiveBayes {

  case class Params(
      input: String = null,
      minPartitions: Int = 0,
      numFeatures: Int = -1,
      lambda: Double = 1.0) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("SparseNaiveBayes") {
      head("SparseNaiveBayes: an example naive Bayes app for LIBSVM data.")
      opt[Int]("numPartitions")
        .text("min number of partitions")
        .action((x, c) => c.copy(minPartitions = x))
      opt[Int]("numFeatures")
        .text("number of features")
        .action((x, c) => c.copy(numFeatures = x))
      opt[Double]("lambda")
        .text(s"lambda (smoothing constant), default: ${defaultParams.lambda}")
        .action((x, c) => c.copy(lambda = x))
      arg[String]("<input>")
        .text("input paths to labeled examples in LIBSVM format")
        .required()
        .action((x, c) => c.copy(input = 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"SparseNaiveBayes with $params")
    val sc = new SparkContext(conf)

    Logger.getRootLogger.setLevel(Level.WARN)

    val minPartitions =
      if (params.minPartitions > 0) params.minPartitions else sc.defaultMinPartitions

    val examples =
      MLUtils.loadLibSVMFile(sc, params.input, params.numFeatures, minPartitions)
    // Cache examples because it will be used in both training and evaluation.
    examples.cache()

    val splits = examples.randomSplit(Array(0.8, 0.2))
    val training = splits(0)
    val test = splits(1)

    val numTraining = training.count()
    val numTest = test.count()

    println(s"numTraining = $numTraining, numTest = $numTest.")

    val model = new NaiveBayes().setLambda(params.lambda).run(training)

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))
    val accuracy = predictionAndLabel.filter(x => x._1 == x._2).count().toDouble / numTest

    println(s"Test accuracy = $accuracy.")

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