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

Go to download
Show more of this group Show more artifacts with this name
Show all versions of spark-examples_2.12 Show documentation
The 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.MulticlassMetrics
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.util.MLUtils
// $example off$

object MulticlassMetricsExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("MulticlassMetricsExample")
    val sc = new SparkContext(conf)

    // $example on$
    // Load training data in LIBSVM format
    val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_multiclass_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(3)
      .run(training)

    // 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 MulticlassMetrics(predictionAndLabels)

    // Confusion matrix
    println("Confusion matrix:")
    println(metrics.confusionMatrix)

    // Overall Statistics
    val accuracy = metrics.accuracy
    println("Summary Statistics")
    println(s"Accuracy = $accuracy")

    // Precision by label
    val labels = metrics.labels
    labels.foreach { l =>
      println(s"Precision($l) = " + metrics.precision(l))
    }

    // Recall by label
    labels.foreach { l =>
      println(s"Recall($l) = " + metrics.recall(l))
    }

    // False positive rate by label
    labels.foreach { l =>
      println(s"FPR($l) = " + metrics.falsePositiveRate(l))
    }

    // F-measure by label
    labels.foreach { l =>
      println(s"F1-Score($l) = " + metrics.fMeasure(l))
    }

    // Weighted stats
    println(s"Weighted precision: ${metrics.weightedPrecision}")
    println(s"Weighted recall: ${metrics.weightedRecall}")
    println(s"Weighted F1 score: ${metrics.weightedFMeasure}")
    println(s"Weighted false positive rate: ${metrics.weightedFalsePositiveRate}")
    // $example off$

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