org.apache.spark.examples.ml.LogisticRegressionSummaryExample.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
import org.apache.spark.sql.functions.max

object LogisticRegressionSummaryExample {

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

    // Load training data
    val training = spark.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")

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

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

    // $example on$
    // Extract the summary from the returned LogisticRegressionModel instance trained in the earlier
    // example
    val trainingSummary = lrModel.binarySummary

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

    // Obtain the receiver-operating characteristic as a dataframe and areaUnderROC.
    val roc = trainingSummary.roc
    roc.show()
    println(s"areaUnderROC: ${trainingSummary.areaUnderROC}")

    // Set the model threshold to maximize F-Measure
    val fMeasure = trainingSummary.fMeasureByThreshold
    val maxFMeasure = fMeasure.select(max("F-Measure")).head().getDouble(0)
    val bestThreshold = fMeasure.where($"F-Measure" === maxFMeasure)
      .select("threshold").head().getDouble(0)
    lrModel.setThreshold(bestThreshold)
    // $example off$

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