Scala LinearRegression类代码示例

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

import org.apache.log4j.Logger
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.feature.{VectorAssembler, VectorIndexer}
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.mllib.evaluation.RegressionMetrics
import org.apache.spark.sql.{DataFrame, SparkSession}


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

  def linearRegressionWithVectorFormat(vectorAssembler: VectorAssembler, vectorIndexer: VectorIndexer, dataFrame: DataFrame) = {
    val lr = new LinearRegression()
      .setFeaturesCol("features")
      .setLabelCol("label")
      .setRegParam(0.1)
      .setElasticNetParam(1.0)
      .setMaxIter(10)

    val pipeline = new Pipeline().setStages(Array(vectorAssembler, vectorIndexer, lr))

    val Array(training, test) = dataFrame.randomSplit(Array(0.8, 0.2), seed = 12345)

    val model = pipeline.fit(training)

    val fullPredictions = model.transform(test).cache()
    val predictions = fullPredictions.select("prediction").rdd.map(_.getDouble(0))
    val labels = fullPredictions.select("label").rdd.map(_.getDouble(0))
    val RMSE = new RegressionMetrics(predictions.zip(labels)).rootMeanSquaredError
    println(s"  Root mean squared error (RMSE): $RMSE")
  }

  def linearRegressionWithSVMFormat(spark: SparkSession) = {
    // Load training data
    val training = spark.read.format("libsvm")
      .load("./src/main/scala/org/sparksamples/regression/dataset/BikeSharing/lsvmHours.txt")

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

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

    // Print the coefficients and intercept for linear regression
    println(s"Coefficients: ${lrModel.coefficients} Intercept: ${lrModel.intercept}")

    // Summarize the model over the training set and print out some metrics
    val trainingSummary = lrModel.summary
    println(s"numIterations: ${trainingSummary.totalIterations}")
    println(s"objectiveHistory: ${trainingSummary.objectiveHistory.toList}")
    trainingSummary.residuals.show()
    println(s"RMSE: ${trainingSummary.rootMeanSquaredError}")

    println(s"r2: ${trainingSummary.r2}")
  }
} 

//设置package包名称以及导入依赖的类
package songs

import org.apache.spark.ml.regression.{LinearRegression, LinearRegressionModel}
import org.apache.spark.mllib.evaluation.RegressionMetrics
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.SQLContext
import org.slf4j.LoggerFactory

object EvaluateModel {

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

    val conf = new SparkConf().setAppName(Config.appName)
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
    val logger = LoggerFactory.getLogger(getClass.getName)

    logger.info(s"Loading Linear Regression Model from ${Config.modelOut}")
    val model = LinearRegressionModel.load(Config.modelOut)

    logger.info("Loading datasets")
    val datasets = SongML.loadModelData(sqlContext = sqlContext)
    val pipelineModel = SongML.transformPipeline.fit(datasets.training)
    val testData = pipelineModel.transform(datasets.test).select(SongML.labelColumn,SongML.featuresColumn)

    logger.info("Calculating Regression Metrics")
    val testPredictions = model.transform(testData)
      .select(SongML.labelColumn,SongML.predictionColumn)
      .map(r => (r.getAs[Double](SongML.predictionColumn), r.getAs[Double](SongML.labelColumn)))
    val rm = new RegressionMetrics(testPredictions)

    logger.info(SongML.printStats(model,rm,"Testing"))

    logger.info("Exiting")
    sc.stop()
  }

} 

//设置package包名称以及导入依赖的类
package es.upm.ging.EjecutaRegresor

import org.apache.spark.ml.regression.{LinearRegression, LinearRegressionModel}
import org.apache.spark.sql.SparkSession



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

    val spark = SparkSession.builder().getOrCreate()
    spark.sparkContext.setLogLevel("OFF")
    val carga = new Carga(spark)

    // midf = carga.json()
    val midf = carga.mysql()
    midf.cache()

    // Imprimimos el esquema detectado
    midf.printSchema()

    // Construimos el modelo
    val iteraciones = 100
    val model = LinearRegression.train(midf, iteraciones)

    // Evaluar el modelo para el dataset de entrenamiento
    val valoresYPrediccion = midf.map { punto =>
      val prediccion = model.predict(punto.features)
      (punto.label, prediccion)
    }

    val MSE = valoresYPrediccion.map{case(v, p) => math.pow((v - p), 2)}.mean()
    println("Mean Squared Error del Entrenador = " + MSE)

    // Carga y guarda
    model.save(sc, "MiModeloLinReg")
    val MiModelo = LinearRegressionModel.load(sc, "MiModeloLinReg")

    println(valuesAndPreds.collect)
  }
} 

//设置package包名称以及导入依赖的类
import org.apache.spark.ml.regression.LinearRegression
import com.redislabs.client.redisml.MLClient
import redis.clients.jedis.{Jedis, _}

// Load training data and train
val training = spark.read.format("libsvm").load("data/mllib/sample_linear_regression_data.txt")
val lr = new LinearRegression().setMaxIter(10).setRegParam(0.3).setElasticNetParam(0.8)
val lrModel = lr.fit(training)
println(s"Coefficients: ${lrModel.coefficients} Intercept: ${lrModel.intercept}")

// Connect to Redis
val jedis = new Jedis("localhost")

// Load model to Redis
val cmd = "my_lr_model" +: lrModel.intercept.toString +: lrModel.coefficients.toArray.mkString(",").split(",")
jedis.getClient.sendCommand(MLClient.ModuleCommand.LINREG_SET, cmd: _*)
jedis.getClient().getStatusCodeReply

// Perform prediction with Redis
val cmd = Array("my_lr_model", "1", "2", "5")
jedis.getClient.sendCommand(MLClient.ModuleCommand.LINREG_PREDICT, cmd: _*)
jedis.getClient().getStatusCodeReply 

//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.linalg.Vectors
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.sql.SparkSession

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

  def train(savePath: String, datasetPath: String): Map[String, Any] = {
    val df = session.read.format("libsvm").load(datasetPath)

    val lr = new LinearRegression()
      .setMaxIter(10)
      .setRegParam(0.3)
      .setElasticNetParam(0.8)
    val pipeline = new Pipeline().setStages(Array(lr))

    val model = pipeline.fit(df)

    model.write.overwrite().save(savePath)
    Map.empty
  }

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

    val pipeline = PipelineLoader.load(modelPath)
    val data = LocalData(LocalDataColumn("features", features.map(_.toArray).map(Vectors.dense)))

    val result: LocalData = pipeline.transform(data)
    Map("result" -> result.select("prediction").toMapList)
  }
}