spark BinaryClassification 源码

spark BinaryClassification 代码

文件路径：/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
package org.apache.spark.examples.mllib

import org.apache.logging.log4j.Level
import org.apache.logging.log4j.core.config.Configurator
import scopt.OptionParser

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.classification.{LogisticRegressionWithLBFGS, SVMWithSGD}
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.optimization.{L1Updater, SquaredL2Updater}
import org.apache.spark.mllib.util.MLUtils

/**
 * An example app for binary classification. Run with
 * {{{
 * bin/run-example org.apache.spark.examples.mllib.BinaryClassification
 * }}}
 * A synthetic dataset is located at `data/mllib/sample_binary_classification_data.txt`.
 * If you use it as a template to create your own app, please use `spark-submit` to submit your app.
 */
object BinaryClassification {

  object Algorithm extends Enumeration {
    type Algorithm = Value
    val SVM, LR = Value
  }

  object RegType extends Enumeration {
    type RegType = Value
    val L1, L2 = Value
  }

  import Algorithm._
  import RegType._

  case class Params(
      input: String = null,
      numIterations: Int = 100,
      stepSize: Double = 1.0,
      algorithm: Algorithm = LR,
      regType: RegType = L2,
      regParam: Double = 0.01) extends AbstractParams[Params]

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

    val parser = new OptionParser[Params]("BinaryClassification") {
      head("BinaryClassification: an example app for binary classification.")
      opt[Int]("numIterations")
        .text("number of iterations")
        .action((x, c) => c.copy(numIterations = x))
      opt[Double]("stepSize")
        .text("initial step size (ignored by logistic regression), " +
          s"default: ${defaultParams.stepSize}")
        .action((x, c) => c.copy(stepSize = x))
      opt[String]("algorithm")
        .text(s"algorithm (${Algorithm.values.mkString(",")}), " +
        s"default: ${defaultParams.algorithm}")
        .action((x, c) => c.copy(algorithm = Algorithm.withName(x)))
      opt[String]("regType")
        .text(s"regularization type (${RegType.values.mkString(",")}), " +
        s"default: ${defaultParams.regType}")
        .action((x, c) => c.copy(regType = RegType.withName(x)))
      opt[Double]("regParam")
        .text(s"regularization parameter, default: ${defaultParams.regParam}")
      arg[String]("<input>")
        .required()
        .text("input paths to labeled examples in LIBSVM format")
        .action((x, c) => c.copy(input = x))
      note(
        """
          |For example, the following command runs this app on a synthetic dataset:
          |
          | bin/spark-submit --class org.apache.spark.examples.mllib.BinaryClassification \
          |  examples/target/scala-*/spark-examples-*.jar \
          |  --algorithm LR --regType L2 --regParam 1.0 \
          |  data/mllib/sample_binary_classification_data.txt
        """.stripMargin)
    }

    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"BinaryClassification with $params")
    val sc = new SparkContext(conf)

    Configurator.setRootLevel(Level.WARN)

    val examples = MLUtils.loadLibSVMFile(sc, params.input).cache()

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

    val numTraining = training.count()
    val numTest = test.count()
    println(s"Training: $numTraining, test: $numTest.")

    examples.unpersist()

    val updater = params.regType match {
      case L1 => new L1Updater()
      case L2 => new SquaredL2Updater()
    }

    val model = params.algorithm match {
      case LR =>
        val algorithm = new LogisticRegressionWithLBFGS()
        algorithm.optimizer
          .setNumIterations(params.numIterations)
          .setUpdater(updater)
          .setRegParam(params.regParam)
        algorithm.run(training).clearThreshold()
      case SVM =>
        val algorithm = new SVMWithSGD()
        algorithm.optimizer
          .setNumIterations(params.numIterations)
          .setStepSize(params.stepSize)
          .setUpdater(updater)
          .setRegParam(params.regParam)
        algorithm.run(training).clearThreshold()
    }

    val prediction = model.predict(test.map(_.features))
    val predictionAndLabel = prediction.zip(test.map(_.label))

    val metrics = new BinaryClassificationMetrics(predictionAndLabel)

    println(s"Test areaUnderPR = ${metrics.areaUnderPR()}.")
    println(s"Test areaUnderROC = ${metrics.areaUnderROC()}.")

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

相关信息

spark 源码目录

相关文章

spark AbstractParams 源码

spark AssociationRulesExample 源码

spark BinaryClassificationMetricsExample 源码

spark BisectingKMeansExample 源码

spark ChiSqSelectorExample 源码

spark Correlations 源码

spark CorrelationsExample 源码

spark CosineSimilarity 源码

spark DecisionTreeClassificationExample 源码

spark DecisionTreeRegressionExample 源码