Scala MulticlassClassificationEvaluator类代码示例

//设置package包名称以及导入依赖的类
package org.apache.spark.examples.ml

import org.apache.spark.SparkConf
import org.apache.spark.ml.classification.NaiveBayes
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator

import org.apache.spark.sql.SparkSession

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

    val spConfig = (new SparkConf).setMaster("local").setAppName("SparkApp")
    val spark = SparkSession
      .builder()
      .appName("SparkRatingData").config(spConfig)
      .getOrCreate()

    val data = spark.read.format("libsvm").load("./output/20news-by-date-train-libsvm/part-combined")

    val Array(trainingData, testData) = data.randomSplit(Array(0.7, 0.3), seed = 1L)

    // Train a NaiveBayes model.
    val model = new NaiveBayes()
      .fit(trainingData)
    val predictions = model.transform(testData)
    predictions.show()

    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val accuracy = evaluator.evaluate(predictions)
    println("Test set accuracy = " + accuracy)
    spark.stop()
  }
} 

//设置package包名称以及导入依赖的类
package org.stumbleuponclassifier

import org.apache.log4j.Logger
import org.apache.spark.ml.classification.DecisionTreeClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, PipelineStage}
import org.apache.spark.sql.DataFrame

import scala.collection.mutable


object DecisionTreePipeline {
  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def decisionTreePipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val Array(training, test) = dataFrame.randomSplit(Array(0.9, 0.1), seed = 12345)

    // Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()

    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
    stages += labelIndexer

    val dt = new DecisionTreeClassifier()
      .setFeaturesCol(vectorAssembler.getOutputCol)
      .setLabelCol("indexedLabel")
      .setMaxDepth(5)
      .setMaxBins(32)
      .setMinInstancesPerNode(1)
      .setMinInfoGain(0.0)
      .setCacheNodeIds(false)
      .setCheckpointInterval(10)

    stages += vectorAssembler
    stages += dt
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline
    val startTime = System.nanoTime()
    //val model = pipeline.fit(training)
    val model = pipeline.fit(dataFrame)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    //val holdout = model.transform(test).select("prediction","label")
    val holdout = model.transform(dataFrame).select("prediction","label")

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val mAccuracy = evaluator.evaluate(holdout)
    println("Test set accuracy = " + mAccuracy)
  }
} 

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator

import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer}
import org.apache.spark.ml
import org.apache.spark.ml.linalg.Vectors


object LogisticRegression extends BenchmarkAlgorithm
  with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    DataGenerator.generateContinuousFeatures(
      ctx.sqlContext,
      numExamples,
      ctx.seed(),
      numPartitions,
      numFeatures)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    val rng = ctx.newGenerator()
    val coefficients =
      Vectors.dense(Array.fill[Double](ctx.params.numFeatures)(2 * rng.nextDouble() - 1))
    // Small intercept to prevent some skew in the data.
    val intercept = 0.01 * (2 * rng.nextDouble - 1)
    ModelBuilder.newLogisticRegressionModel(coefficients, intercept)
  }

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    new ml.classification.LogisticRegression()
      .setTol(tol)
      .setMaxIter(maxIter)
      .setRegParam(regParam)
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new MulticlassClassificationEvaluator()
} 

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification

import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer, TreeUtils}
import org.apache.spark.ml.classification.DecisionTreeClassifier
import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.sql.DataFrame

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


abstract class TreeOrForestClassification extends BenchmarkAlgorithm
  with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {

  import TreeOrForestClassification.getFeatureArity

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    val featureArity: Array[Int] = getFeatureArity(ctx)
    val data: DataFrame = DataGenerator.generateMixedFeatures(ctx.sqlContext, numExamples,
      ctx.seed(), numPartitions, featureArity)
    TreeUtils.setMetadata(data, "features", featureArity)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    ModelBuilder.newDecisionTreeClassificationModel(ctx.params.depth, ctx.params.numClasses,
      getFeatureArity(ctx), ctx.seed())
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new MulticlassClassificationEvaluator()
}

object DecisionTreeClassification extends TreeOrForestClassification {

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    new DecisionTreeClassifier()
      .setMaxDepth(depth)
      .setSeed(ctx.seed())
  }
}

object TreeOrForestClassification {

  
  def getFeatureArity(ctx: MLBenchContext): Array[Int] = {
    val numFeatures = ctx.params.numFeatures
    val fourthFeatures = numFeatures / 4
    Array.fill[Int](fourthFeatures)(2) ++ // low-arity categorical
      Array.fill[Int](fourthFeatures)(20) ++ // high-arity categorical
      Array.fill[Int](numFeatures - 2 * fourthFeatures)(0) // continuous
  }
} 

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification

import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer, TreeUtils}
import org.apache.spark.ml.classification.GBTClassifier
import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.sql._

import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


object GBTClassification extends BenchmarkAlgorithm
  with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {

  import TreeOrForestClassification.getFeatureArity

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    val featureArity: Array[Int] = getFeatureArity(ctx)
    val data: DataFrame = DataGenerator.generateMixedFeatures(ctx.sqlContext, numExamples,
      ctx.seed(), numPartitions, featureArity)
    TreeUtils.setMetadata(data, "features", featureArity)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    import ctx.params._
    // We add +1 to the depth to make it more likely that many iterations of boosting are needed
    // to model the true tree.
    ModelBuilder.newDecisionTreeClassificationModel(depth + 1, numClasses, getFeatureArity(ctx),
      ctx.seed())
  }

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    // TODO: subsamplingRate, featureSubsetStrategy
    // TODO: cacheNodeIds, checkpoint?
    new GBTClassifier()
      .setMaxDepth(depth)
      .setMaxIter(maxIter)
      .setSeed(ctx.seed())
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new MulticlassClassificationEvaluator()
} 

//设置package包名称以及导入依赖的类
package org.stumbleuponclassifier

import org.apache.log4j.Logger
import org.apache.spark.ml.classification.NaiveBayes
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, PipelineStage}
import org.apache.spark.sql.DataFrame

import scala.collection.mutable


object NaiveBayesPipeline {
  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def naiveBayesPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val Array(training, test) = dataFrame.randomSplit(Array(0.9, 0.1), seed = 12345)

    // Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()

    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
    stages += labelIndexer

    val nb = new NaiveBayes()

    stages += vectorAssembler
    stages += nb
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline
    val startTime = System.nanoTime()
    //val model = pipeline.fit(training)
    val model = pipeline.fit(dataFrame)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    //val holdout = model.transform(test).select("prediction","label")
    val holdout = model.transform(dataFrame).select("prediction","label")

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val mAccuracy = evaluator.evaluate(holdout)
    println("Test set accuracy = " + mAccuracy)
  }
} 

//设置package包名称以及导入依赖的类
package org.stumbleuponclassifier

import org.apache.log4j.Logger
import org.apache.spark.ml.classification.RandomForestClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, PipelineStage}
import org.apache.spark.sql.DataFrame

import scala.collection.mutable


object RandomForestPipeline {
  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def randomForestPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val Array(training, test) = dataFrame.randomSplit(Array(0.9, 0.1), seed = 12345)

    // Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()

    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
    stages += labelIndexer

    val rf = new RandomForestClassifier()
      .setFeaturesCol(vectorAssembler.getOutputCol)
      .setLabelCol("indexedLabel")
      .setNumTrees(20)
      .setMaxDepth(5)
      .setMaxBins(32)
      .setMinInstancesPerNode(1)
      .setMinInfoGain(0.0)
      .setCacheNodeIds(false)
      .setCheckpointInterval(10)

    stages += vectorAssembler
    stages += rf
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline
    val startTime = System.nanoTime()
    //val model = pipeline.fit(training)
    val model = pipeline.fit(dataFrame)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    //val holdout = model.transform(test).select("prediction","label")
    val holdout = model.transform(dataFrame).select("prediction","label")

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val mAccuracy = evaluator.evaluate(holdout)
    println("Test set accuracy = " + mAccuracy)

  }
} 

//设置package包名称以及导入依赖的类
package org.sparksamples.classification.stumbleupon

import org.apache.log4j.Logger
import org.apache.spark.ml.classification.DecisionTreeClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, PipelineStage}
import org.apache.spark.sql.DataFrame

import scala.collection.mutable


object DecisionTreePipeline {
  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def decisionTreePipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val Array(training, test) = dataFrame.randomSplit(Array(0.9, 0.1), seed = 12345)

    // Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()

    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
    stages += labelIndexer

    val dt = new DecisionTreeClassifier()
      .setFeaturesCol(vectorAssembler.getOutputCol)
      .setLabelCol("indexedLabel")
      .setMaxDepth(5)
      .setMaxBins(32)
      .setMinInstancesPerNode(1)
      .setMinInfoGain(0.0)
      .setCacheNodeIds(false)
      .setCheckpointInterval(10)

    stages += vectorAssembler
    stages += dt
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline
    val startTime = System.nanoTime()
    //val model = pipeline.fit(training)
    val model = pipeline.fit(dataFrame)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    //val holdout = model.transform(test).select("prediction","label")
    val holdout = model.transform(dataFrame).select("prediction","label")

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val mAccuracy = evaluator.evaluate(holdout)
    println("Test set accuracy = " + mAccuracy)
  }
} 

//设置package包名称以及导入依赖的类
package org.sparksamples.classification.stumbleupon

import org.apache.log4j.Logger
import org.apache.spark.ml.classification.NaiveBayes
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, PipelineStage}
import org.apache.spark.sql.DataFrame

import scala.collection.mutable


object NaiveBayesPipeline {
  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def naiveBayesPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val Array(training, test) = dataFrame.randomSplit(Array(0.9, 0.1), seed = 12345)

    // Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()

    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
    stages += labelIndexer

    val nb = new NaiveBayes()

    stages += vectorAssembler
    stages += nb
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline
    val startTime = System.nanoTime()
    //val model = pipeline.fit(training)
    val model = pipeline.fit(dataFrame)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    //val holdout = model.transform(test).select("prediction","label")
    val holdout = model.transform(dataFrame).select("prediction","label")

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val mAccuracy = evaluator.evaluate(holdout)
    println("Test set accuracy = " + mAccuracy)
  }
} 

//设置package包名称以及导入依赖的类
package org.sparksamples.classification.stumbleupon

import org.apache.log4j.Logger
import org.apache.spark.ml.classification.RandomForestClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.{Pipeline, PipelineStage}
import org.apache.spark.sql.DataFrame

import scala.collection.mutable


object RandomForestPipeline {
  @transient lazy val logger = Logger.getLogger(getClass.getName)

  def randomForestPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val Array(training, test) = dataFrame.randomSplit(Array(0.9, 0.1), seed = 12345)

    // Set up Pipeline
    val stages = new mutable.ArrayBuffer[PipelineStage]()

    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
    stages += labelIndexer

    val rf = new RandomForestClassifier()
      .setFeaturesCol(vectorAssembler.getOutputCol)
      .setLabelCol("indexedLabel")
      .setNumTrees(20)
      .setMaxDepth(5)
      .setMaxBins(32)
      .setMinInstancesPerNode(1)
      .setMinInfoGain(0.0)
      .setCacheNodeIds(false)
      .setCheckpointInterval(10)

    stages += vectorAssembler
    stages += rf
    val pipeline = new Pipeline().setStages(stages.toArray)

    // Fit the Pipeline
    val startTime = System.nanoTime()
    //val model = pipeline.fit(training)
    val model = pipeline.fit(dataFrame)
    val elapsedTime = (System.nanoTime() - startTime) / 1e9
    println(s"Training time: $elapsedTime seconds")

    //val holdout = model.transform(test).select("prediction","label")
    val holdout = model.transform(dataFrame).select("prediction","label")

    // Select (prediction, true label) and compute test error
    val evaluator = new MulticlassClassificationEvaluator()
      .setLabelCol("label")
      .setPredictionCol("prediction")
      .setMetricName("accuracy")
    val mAccuracy = evaluator.evaluate(holdout)
    println("Test set accuracy = " + mAccuracy)

  }
} 

//设置package包名称以及导入依赖的类
package cn.edu.bjtu


import org.apache.spark.SparkConf
import org.apache.spark.ml.classification.MultilayerPerceptronClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.sql.SparkSession

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

    val sparkConf = new SparkConf()
      .setAppName("MLPTest")
      .setMaster("spark://master:7077")
      .setJars(Array("/home/hadoop/MLP.jar"))

    val spark = SparkSession.builder()
      .config(sparkConf)
      .getOrCreate()

    spark.sparkContext.setLogLevel("WARN")


    // Load the data stored in LIBSVM format as a DataFrame.
    val data = spark.read.format("libsvm")
      .load("hdfs://master:9000/sample_formatted.txt")

    // Split the data into train and test
    val splits = data.randomSplit(Array(0.7, 0.3), seed = 14L)
    val train = splits(0)
    val test = splits(1)

    val layers = Array[Int](20, 20, 2)

    // create the trainer and set its parameters
    val trainer = new MultilayerPerceptronClassifier()
      .setLayers(layers)
      .setBlockSize(128)
      .setSeed(14L)
      .setMaxIter(100)

    // train the model
    val model = trainer.fit(train)

    // compute accuracy on the test set
    val result = model.transform(test)
    val predictionAndLabels = result.select("prediction", "label")
    val evaluator = new MulticlassClassificationEvaluator()
      .setMetricName("accuracy")

    println("Sensitivity = " + predictionAndLabels.filter(x => x(0) == x(1) && x(0) == 1.0).count().toDouble / predictionAndLabels.filter(x => x(1) == 1.0).count().toDouble)
    println("Specificity = " + predictionAndLabels.filter(x => x(0) == x(1) && x(0) == 0.0).count().toDouble / predictionAndLabels.filter(x => x(1) == 0.0).count().toDouble)
    println("Test set accuracy = " + evaluator.evaluate(predictionAndLabels))
  }
} 

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification

import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer, TreeUtils}
import org.apache.spark.ml.classification.DecisionTreeClassifier
import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.sql.DataFrame

import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


abstract class TreeOrForestClassification extends BenchmarkAlgorithm
  with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {

  import TreeOrForestClassification.getFeatureArity

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    val featureArity: Array[Int] = getFeatureArity(ctx)
    val data: DataFrame = DataGenerator.generateMixedFeatures(ctx.sqlContext, numExamples,
      ctx.seed(), numPartitions, featureArity)
    TreeUtils.setMetadata(data, "label", numClasses, "features", featureArity)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    ModelBuilder.newDecisionTreeClassificationModel(ctx.params.depth, ctx.params.numClasses,
      getFeatureArity(ctx), ctx.seed())
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new MulticlassClassificationEvaluator()
}

object DecisionTreeClassification extends TreeOrForestClassification {

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    new DecisionTreeClassifier()
      .setMaxDepth(depth)
      .setSeed(ctx.seed())
  }
}

object TreeOrForestClassification {

  
  def getFeatureArity(ctx: MLBenchContext): Array[Int] = {
    val numFeatures = ctx.params.numFeatures
    val fourthFeatures = numFeatures / 4
    Array.fill[Int](fourthFeatures)(2) ++ // low-arity categorical
      Array.fill[Int](fourthFeatures)(20) ++ // high-arity categorical
      Array.fill[Int](numFeatures - 2 * fourthFeatures)(0) // continuous
  }
} 

//设置package包名称以及导入依赖的类
package com.databricks.spark.sql.perf.mllib.classification

import org.apache.spark.ml.{Estimator, ModelBuilder, Transformer, TreeUtils}
import org.apache.spark.ml.classification.GBTClassifier
import org.apache.spark.ml.evaluation.{Evaluator, MulticlassClassificationEvaluator}
import org.apache.spark.sql._

import com.databricks.spark.sql.perf.mllib._
import com.databricks.spark.sql.perf.mllib.OptionImplicits._
import com.databricks.spark.sql.perf.mllib.data.DataGenerator


object GBTClassification extends BenchmarkAlgorithm
  with TestFromTraining with TrainingSetFromTransformer with ScoringWithEvaluator {

  import TreeOrForestClassification.getFeatureArity

  override protected def initialData(ctx: MLBenchContext) = {
    import ctx.params._
    val featureArity: Array[Int] = getFeatureArity(ctx)
    val data: DataFrame = DataGenerator.generateMixedFeatures(ctx.sqlContext, numExamples,
      ctx.seed(), numPartitions, featureArity)
    TreeUtils.setMetadata(data, "label", numClasses, "features", featureArity)
  }

  override protected def trueModel(ctx: MLBenchContext): Transformer = {
    import ctx.params._
    // We add +1 to the depth to make it more likely that many iterations of boosting are needed
    // to model the true tree.
    ModelBuilder.newDecisionTreeClassificationModel(depth + 1, numClasses, getFeatureArity(ctx),
      ctx.seed())
  }

  override def getEstimator(ctx: MLBenchContext): Estimator[_] = {
    import ctx.params._
    // TODO: subsamplingRate, featureSubsetStrategy
    // TODO: cacheNodeIds, checkpoint?
    new GBTClassifier()
      .setMaxDepth(depth)
      .setMaxIter(maxIter)
      .setSeed(ctx.seed())
  }

  override protected def evaluator(ctx: MLBenchContext): Evaluator =
    new MulticlassClassificationEvaluator()
} 

//设置package包名称以及导入依赖的类
package io.spinor.sparkdemo.mllib

import io.spinor.sparkdemo.data.MNISTData
import io.spinor.sparkdemo.util.DemoUtil
import org.apache.spark.ml.classification.MultilayerPerceptronClassifier
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.ml.feature.LabeledPoint
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.sql.SparkSession
import org.apache.spark.{SparkConf, SparkContext}
import org.scalatest.{FlatSpec, Matchers}
import org.slf4j.LoggerFactory


class NeuralNetworkSpec extends FlatSpec with DemoUtil with Matchers {
  val logger = LoggerFactory.getLogger(classOf[NeuralNetworkSpec])

  "Training on MNIST data" should " run" in {
    val sparkConf = new SparkConf()
    sparkConf.setAppName("NeuralNetworkDemo")
    sparkConf.setMaster("local[2]")

    val sparkContext = new SparkContext(sparkConf)
    val sparkSession = SparkSession.builder().config(sparkConf).getOrCreate()
    val sqlContext = sparkSession.sqlContext
    import sqlContext.implicits._

    val mNISTData = new MNISTData()
    val trainingData = mNISTData.getTrainingData()
    val trainingPoints = sparkContext.parallelize(trainingData.map(entry => LabeledPoint(entry._2, Vectors.dense(entry._1)))).toDF()

    val classifier = new MultilayerPerceptronClassifier()
    classifier
      .setLayers(Array(784, 100))
      .setBlockSize(125)
      .setSeed(1234L)
      .setMaxIter(10)

    val model = classifier.fit(trainingPoints)

    val testData = mNISTData.getTestData()
    val testPoints = sparkContext.parallelize(testData.map(entry => {
    LabeledPoint(entry._2, Vectors.dense(entry._1))})).toDF()
    val result = model.transform(testPoints)
    val predictionAndLabels = result.select("prediction", "label")
    val evaluator = new MulticlassClassificationEvaluator().setMetricName("accuracy")

    logger.info("accuracy:" + evaluator.evaluate(predictionAndLabels))
  }
} 

//设置package包名称以及导入依赖的类
package com.zobot.ai.spark.helpers

import org.apache.spark.ml.classification.{MultilayerPerceptronClassificationModel, MultilayerPerceptronClassifier}
import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator
import org.apache.spark.sql.DataFrame

object MlpcHelpers {
  case class NeuralNetworkLayers (
    featureLayerSize: Int,
    intermediateLayerSizes: List[Int],
    classLayerSize: Int
  )

  def layersToArray(layers: NeuralNetworkLayers): Array[Int] = {
    (layers.featureLayerSize :: layers.intermediateLayerSizes ::: List(layers.classLayerSize)).toArray
  }

  def createTrainer(layers: NeuralNetworkLayers, blockSize: Int, maxIterations: Int, seed: Option[Long]): MultilayerPerceptronClassifier = {
    val mlpcClassifier = new MultilayerPerceptronClassifier()
      .setLayers(layersToArray(layers))
      .setBlockSize(blockSize)
      .setMaxIter(maxIterations)
    seed match {
      case Some(n) => mlpcClassifier.setSeed(n)
      case None => mlpcClassifier
    }
  }

  def trainModel(trainer: MultilayerPerceptronClassifier, trainingData: DataFrame): MultilayerPerceptronClassificationModel = {
    trainer.fit(trainingData)
  }

  def testModel(model: MultilayerPerceptronClassificationModel, testData: DataFrame): DataFrame = model.transform(testData)

  def getModelAccuracy(testResults: DataFrame): Double = {
    val predictionAndLabels = testResults.select("prediction", "label")
    val evaluator = new MulticlassClassificationEvaluator().setMetricName("accuracy")
    evaluator.evaluate(predictionAndLabels)
  }
}