Scala NaiveBayes类代码示例

//设置package包名称以及导入依赖的类
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.NaiveBayes
import org.apache.spark.ml.feature.{HashingTF, Tokenizer}
import org.apache.spark.sql.SparkSession

object movies {

  case class Sentence(sentence: String,label: Double)

  def main(args:Array[String]) {

    val spark = SparkSession
      .builder
      .appName("Movies Reviews")
      .config("spark.master", "local")
      .getOrCreate()


    // Prepare training documents from a list of (id, text, label) tuples.
    val neg = spark.sparkContext.textFile("file:///data/train/neg/").repartition(4)
      .map(w => Sentence(w, 0.0))

    val pos = spark.sparkContext.textFile("file:///data/train/pos/").repartition(4)
      .map(w => Sentence(w, 1.0))

    val test = spark.sparkContext.wholeTextFiles("file:///data/test/").repartition(4)
      .map({case(file,sentence) => (file.split("/").last.split("\\.")(0),sentence)})


    val training=neg.union(pos)
    val trainingDF=spark.createDataFrame(training)
    val testDF=spark.createDataFrame(test)

    // Configure an ML pipeline, which consists of three stages: tokenizer, hashingTF, and Naive Bayes
    val tokenizer = new Tokenizer()
      .setInputCol("sentence")
      .setOutputCol("words")
    val hashingTF = new HashingTF()
      .setInputCol(tokenizer.getOutputCol)
      .setOutputCol("features")
    val nb = new NaiveBayes()

    val pipeline = new Pipeline()
      .setStages(Array(tokenizer, hashingTF, nb))

    // Fit the pipeline to training documents.
    val model = pipeline.fit(trainingDF)

    // Make predictions on test documents.
    model.transform(testDF).repartition(1)
      .select("file", "prediction")
      .write.format("csv")
      .option("header","true")
      .option("delimiter","\t")
      .save("/tmp/spark-prediction")
    spark.stop()
      }
  } 

//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.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.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
import io.hydrosphere.mist.api._
import io.hydrosphere.mist.api.ml._
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.NaiveBayes
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.ml.linalg.{Vector => LVector}
import org.apache.spark.sql.SparkSession


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

  def train(savePath: String): Map[String, Any] = {
    val df = session.createDataFrame(Seq(
      (Vectors.dense(4.0, 0.2, 3.0, 4.0, 5.0), 1.0),
      (Vectors.dense(3.0, 0.3, 1.0, 4.1, 5.0), 1.0),
      (Vectors.dense(2.0, 0.5, 3.2, 4.0, 5.0), 1.0),
      (Vectors.dense(5.0, 0.7, 1.5, 4.0, 5.0), 1.0),
      (Vectors.dense(1.0, 0.1, 7.0, 4.0, 5.0), 0.0),
      (Vectors.dense(8.0, 0.3, 5.0, 1.0, 7.0), 0.0)
    )).toDF("features", "label")

    val nb = new NaiveBayes()

    val pipeline = new Pipeline().setStages(Array(nb))

    val model = pipeline.fit(df)

    model.write.overwrite().save(savePath)
    Map.empty[String, Any]
  }

  def serve(modelPath: String, features: List[List[Double]]): Map[String, Any] = {
    import LocalPipelineModel._

    val pipeline = PipelineLoader.load(modelPath)
    val data = LocalData(LocalDataColumn("features", features))

    val result = pipeline.transform(data)

    val response = result.select("probability", "rawPrediction", "prediction").toMapList.map(rowMap => {
      val mapped = rowMap("probability").asInstanceOf[LVector].toArray
      val one = rowMap + ("probability" -> mapped)

      val mapped2 = one("rawPrediction").asInstanceOf[LVector].toArray
      one + ("rawPrediction" -> mapped2)
    })
    Map("result" -> response)
  }
} 

//设置package包名称以及导入依赖的类
package naivebayes

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.ml.classification.NaiveBayes
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.rdd.RDD
import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession}

object WatherScript extends App {

  val conf = new SparkConf().setAppName("Simple Application")
  val sc = new SparkContext(conf)

  val spark = SparkSession
    .builder()
    .appName("Spark SQL basic example")
    .config("spark.some.config.option", "some-value")
    .getOrCreate()

  // For implicit conversions like converting RDDs to DataFrames
  import spark.implicits._

  val watherRaw: RDD[String] = sc.textFile("/Users/mateusz/Workspace/mllib/spark-naive-bayes/src/main/resources/wather-nums.csv")

  val dataRaw = watherRaw.map(_.split(";")).map { csv =>
    val label = csv.last.toDouble
    val point = csv.init.map(_.toDouble)
    (label, point)
  }

  val data: Dataset[LabeledPoint] = dataRaw
    .map { case (label, point) =>
      LabeledPoint(label, Vectors.dense(point))
    }.toDS()

  val Array(training: Dataset[LabeledPoint], test: Dataset[LabeledPoint]) = data.randomSplit(Array(0.7, 0.3), seed = 1234L)

  val model = new NaiveBayes()
    .setModelType("multinomial")
    .fit(training)

  val predictions = model.transform(test)
  predictions.show()

  val evaluator = new MulticlassClassificationEvaluator()
    .setLabelCol("label")
    .setPredictionCol("prediction")
    .setMetricName("accuracy")
  val accuracy = evaluator.evaluate(predictions)

  println("Test set accuracy = " + accuracy)
}