org.apache.spark.examples.mllib.LBFGSExample.scala Maven / Gradle / Ivy

Go to download
/*
 * 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.spark.{SparkConf, SparkContext}
// $example on$
import org.apache.spark.mllib.classification.LogisticRegressionModel
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.optimization.{LBFGS, LogisticGradient, SquaredL2Updater}
import org.apache.spark.mllib.util.MLUtils
// $example off$

object LBFGSExample {

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

    val conf = new SparkConf().setAppName("LBFGSExample")
    val sc = new SparkContext(conf)

    // $example on$
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
    val numFeatures = data.take(1)(0).features.size

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

    // Append 1 into the training data as intercept.
    val training = splits(0).map(x => (x.label, MLUtils.appendBias(x.features))).cache()

    val test = splits(1)

    // Run training algorithm to build the model
    val numCorrections = 10
    val convergenceTol = 1e-4
    val maxNumIterations = 20
    val regParam = 0.1
    val initialWeightsWithIntercept = Vectors.dense(new Array[Double](numFeatures + 1))

    val (weightsWithIntercept, loss) = LBFGS.runLBFGS(
      training,
      new LogisticGradient(),
      new SquaredL2Updater(),
      numCorrections,
      convergenceTol,
      maxNumIterations,
      regParam,
      initialWeightsWithIntercept)

    val model = new LogisticRegressionModel(
      Vectors.dense(weightsWithIntercept.toArray.slice(0, weightsWithIntercept.size - 1)),
      weightsWithIntercept(weightsWithIntercept.size - 1))

    // 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("Loss of each step in training process")
    loss.foreach(println)
    println(s"Area under ROC = $auROC")
    // $example off$

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