org.apache.spark.examples.ml.MulticlassLogisticRegressionWithElasticNetExample.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.ml

// $example on$
import org.apache.spark.ml.classification.LogisticRegression
// $example off$
import org.apache.spark.sql.SparkSession

object MulticlassLogisticRegressionWithElasticNetExample {

  def main(args: Array[String]): Unit = {
    val spark = SparkSession
      .builder
      .appName("MulticlassLogisticRegressionWithElasticNetExample")
      .getOrCreate()

    // $example on$
    // Load training data
    val training = spark
      .read
      .format("libsvm")
      .load("data/mllib/sample_multiclass_classification_data.txt")

    val lr = new LogisticRegression()
      .setMaxIter(10)
      .setRegParam(0.3)
      .setElasticNetParam(0.8)

    // Fit the model
    val lrModel = lr.fit(training)

    // Print the coefficients and intercept for multinomial logistic regression
    println(s"Coefficients: \n${lrModel.coefficientMatrix}")
    println(s"Intercepts: \n${lrModel.interceptVector}")

    val trainingSummary = lrModel.summary

    // Obtain the objective per iteration
    val objectiveHistory = trainingSummary.objectiveHistory
    println("objectiveHistory:")
    objectiveHistory.foreach(println)

    // for multiclass, we can inspect metrics on a per-label basis
    println("False positive rate by label:")
    trainingSummary.falsePositiveRateByLabel.zipWithIndex.foreach { case (rate, label) =>
      println(s"label $label: $rate")
    }

    println("True positive rate by label:")
    trainingSummary.truePositiveRateByLabel.zipWithIndex.foreach { case (rate, label) =>
      println(s"label $label: $rate")
    }

    println("Precision by label:")
    trainingSummary.precisionByLabel.zipWithIndex.foreach { case (prec, label) =>
      println(s"label $label: $prec")
    }

    println("Recall by label:")
    trainingSummary.recallByLabel.zipWithIndex.foreach { case (rec, label) =>
      println(s"label $label: $rec")
    }


    println("F-measure by label:")
    trainingSummary.fMeasureByLabel.zipWithIndex.foreach { case (f, label) =>
      println(s"label $label: $f")
    }

    val accuracy = trainingSummary.accuracy
    val falsePositiveRate = trainingSummary.weightedFalsePositiveRate
    val truePositiveRate = trainingSummary.weightedTruePositiveRate
    val fMeasure = trainingSummary.weightedFMeasure
    val precision = trainingSummary.weightedPrecision
    val recall = trainingSummary.weightedRecall
    println(s"Accuracy: $accuracy\nFPR: $falsePositiveRate\nTPR: $truePositiveRate\n" +
      s"F-measure: $fMeasure\nPrecision: $precision\nRecall: $recall")
    // $example off$

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