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

Go to download
Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.11 Show documentation
SnappyData distributed data store and execution engine
There is a newer version: 2.1.3.2
Show newest version
/*
 * 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.LogisticRegressionWithLBFGS
import org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils
// $example off$

object BinaryClassificationMetricsExample {

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

    val conf = new SparkConf().setAppName("BinaryClassificationMetricsExample")
    val sc = new SparkContext(conf)
    // $example on$
    // Load training data in LIBSVM format
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt")

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

    // Run training algorithm to build the model
    val model = new LogisticRegressionWithLBFGS()
      .setNumClasses(2)
      .run(training)

    // Clear the prediction threshold so the model will return probabilities
    model.clearThreshold

    // Compute raw scores on the test set
    val predictionAndLabels = test.map { case LabeledPoint(label, features) =>
      val prediction = model.predict(features)
      (prediction, label)
    }

    // Instantiate metrics object
    val metrics = new BinaryClassificationMetrics(predictionAndLabels)

    // Precision by threshold
    val precision = metrics.precisionByThreshold
    precision.foreach { case (t, p) =>
      println(s"Threshold: $t, Precision: $p")
    }

    // Recall by threshold
    val recall = metrics.recallByThreshold
    recall.foreach { case (t, r) =>
      println(s"Threshold: $t, Recall: $r")
    }

    // Precision-Recall Curve
    val PRC = metrics.pr

    // F-measure
    val f1Score = metrics.fMeasureByThreshold
    f1Score.foreach { case (t, f) =>
      println(s"Threshold: $t, F-score: $f, Beta = 1")
    }

    val beta = 0.5
    val fScore = metrics.fMeasureByThreshold(beta)
    f1Score.foreach { case (t, f) =>
      println(s"Threshold: $t, F-score: $f, Beta = 0.5")
    }

    // AUPRC
    val auPRC = metrics.areaUnderPR
    println("Area under precision-recall curve = " + auPRC)

    // Compute thresholds used in ROC and PR curves
    val thresholds = precision.map(_._1)

    // ROC Curve
    val roc = metrics.roc

    // AUROC
    val auROC = metrics.areaUnderROC
    println("Area under ROC = " + auROC)
    // $example off$
  }
}
// scalastyle:on println