Scala DecisionTreeClassifier类代码示例

//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 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 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
import io.hydrosphere.mist.api._
import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.DecisionTreeClassifier
import org.apache.spark.ml.feature.{IndexToString, StringIndexer, VectorIndexer}
import org.apache.spark.sql.SparkSession

object DTreeClassificationJob extends MLMistJob{
  def session: SparkSession = SparkSession
    .builder()
    .appName(context.appName)
    .config(context.getConf)
    .getOrCreate()

  def train(datasetPath: String, savePath: String): Map[String, Any] = {
    val data = session.read.format("libsvm").load(datasetPath)
    val Array(training, _) = data.randomSplit(Array(0.7, 0.3))
    val labelIndexer = new StringIndexer()
      .setInputCol("label")
      .setOutputCol("indexedLabel")
      .fit(data)
    val featureIndexer = new VectorIndexer()
      .setInputCol("features")
      .setOutputCol("indexedFeatures")
      .setMaxCategories(4)// features with > 4 distinct values are treated as continuous.
      .fit(data)
    val dt = new DecisionTreeClassifier()
      .setLabelCol("indexedLabel")
      .setFeaturesCol("indexedFeatures")

    val labelConverter = new IndexToString()
      .setInputCol("prediction")
      .setOutputCol("predictedLabel")
      .setLabels(labelIndexer.labels)

    val pipeline = new Pipeline()
      .setStages(Array(labelIndexer, featureIndexer, dt, labelConverter))

    val model = pipeline.fit(training)

    model.write.overwrite().save(savePath)
    Map.empty[String, Any]
}
  def serve(modelPath: String, features: List[Array[Double]]): Map[String, Any] = {
    import LocalPipelineModel._

    val pipeline = PipelineLoader.load(modelPath)
    val data = LocalData(
      LocalDataColumn("features", features)
    )
    val result: LocalData = pipeline.transform(data)
    Map("result" -> result.select("predictedLabel").toMapList)
  }
} 

//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 applications.mining

import config.paramconf.ClassParams
import functions.Preprocessor
import org.apache.log4j.{Level, Logger}
import org.apache.spark.ml.classification.DecisionTreeClassifier
import org.apache.spark.ml.feature._
import org.apache.spark.sql.SparkSession


object TrainNewsClassWithDTDemo {
  def main(args: Array[String]): Unit = {
    Logger.getLogger("org").setLevel(Level.WARN)

    val spark = SparkSession
      .builder
      .master("local[2]")
      .appName("train news with DT Demo")
      .getOrCreate()

    val args = Array("ckooc-ml/data/classnews/train")
    val filePath = args(0)

    import spark.implicits._
    val data = spark.sparkContext.textFile(filePath).flatMap { line =>
      val tokens: Array[String] = line.split("\u00ef")
      if (tokens.length > 3) Some((tokens(0), tokens(1), tokens(2), tokens(3))) else None
    }.toDF("label", "title", "time", "content")
    data.persist()

    val preprocessor = new Preprocessor
    val pipeline = preprocessor.preprocess(data)

    // DT????
    val params = new ClassParams
    val dtClassifier = new DecisionTreeClassifier()
      .setMinInfoGain(params.minInfoGain)
      .setMaxDepth(params.maxDepth) //??Spark?????30???
      .setLabelCol("indexedLabel")
      .setFeaturesCol("features")

    val indexModel = pipeline.getStages(1).asInstanceOf[StringIndexerModel]
    //?????
    val labelConverter = new IndexToString()
      .setLabels(indexModel.labels)
      .setInputCol(dtClassifier.getPredictionCol)
      .setOutputCol("predictedLabel")

    val stages = pipeline.getStages ++ Array(dtClassifier, labelConverter)
    pipeline.setStages(stages)

    val model = pipeline.fit(data)
    model.write.overwrite().save(params.DTModelPath)

    data.unpersist()
    spark.stop()
  }
}