org.apache.spark.ml.tuning.TrainValidationSplit Scala Examples

The following examples show how to use org.apache.spark.ml.tuning.TrainValidationSplit. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: TrainValidationSplitParitySpec.scala    From mleap   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.parity.validation

import org.apache.spark.ml.{Pipeline, Transformer}
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.feature.{StringIndexer, VectorAssembler}
import org.apache.spark.ml.parity.SparkParityBase
import org.apache.spark.ml.regression.RandomForestRegressor
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.sql.DataFrame

class TrainValidationSplitParitySpec extends SparkParityBase {
  override val dataset: DataFrame = baseDataset.select("fico_score_group_fnl", "dti", "loan_amount")
  override val sparkTransformer: Transformer = {
    val regressor = new RandomForestRegressor().
      setFeaturesCol("features").
      setLabelCol("loan_amount").
      setPredictionCol("prediction")
    val paramGrid = new ParamGridBuilder()
      .addGrid(regressor.numTrees, Array(2, 3, 4))
      .build()

    new Pipeline().setStages(Array(new StringIndexer().
      setInputCol("fico_score_group_fnl").
      setOutputCol("fico_index"),
      new VectorAssembler().
        setInputCols(Array("fico_index", "dti")).
        setOutputCol("features"),
      new TrainValidationSplit().
        setEvaluator(new RegressionEvaluator().
          setLabelCol("loan_amount").
          setPredictionCol("prediction")).
        setEstimator(regressor).
        setEstimatorParamMaps(paramGrid))).fit(dataset)
  }
  override val ignoreSerializationTest = true
}
Example 2
Source File: MNIST.scala    From spark-gp   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.ml.classification.examples

import org.apache.spark.ml.classification.GaussianProcessClassifier
import org.apache.spark.ml.commons.kernel.RBFKernel
import org.apache.spark.ml.commons.util.Scaling
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.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession

object MNIST extends App with Scaling {
  val name = "MNIST"
  val spark = SparkSession.builder().appName(name).master(s"local[${args(0)}]").getOrCreate()
  val path = args(1)
  val parallelism = args(0).toInt * 4
  val forExpert = args(2).toInt
  val activeSet = args(3).toInt

  import spark.sqlContext.implicits._
  val dataset = (scale _ andThen labels201 _) (spark.read.format("csv").load(path).rdd.map(row => {
    val features = Vectors.dense((1 until row.length).map("_c" + _).map(row.getAs[String]).map(_.toDouble).toArray)
    val label = row.getAs[String]("_c0").toDouble
    LabeledPoint(label, features)
  }).cache()).toDF.repartition(parallelism).cache()

  val gp = new GaussianProcessClassifier()
    .setDatasetSizeForExpert(forExpert)
    .setActiveSetSize(activeSet)
    .setKernel(() => new RBFKernel(10))
    .setTol(1e-3)

  val cv = new TrainValidationSplit()
    .setEstimator(gp)
    .setEvaluator(new MulticlassClassificationEvaluator().setMetricName("accuracy"))
    .setEstimatorParamMaps(new ParamGridBuilder().build())
    .setTrainRatio(0.8)

  println("Accuracy: " + cv.fit(dataset).validationMetrics.toList)

  def labels201(data: RDD[LabeledPoint]) : RDD[LabeledPoint] = {
    val old2new = data.map(_.label).distinct().collect().zipWithIndex.toMap
    data.map(lp => LabeledPoint(old2new(lp.label), lp.features))
  }
}
Example 3
Source File: LogisticRegressionPipeline.scala    From Machine-Learning-with-Spark-Second-Edition   with MIT License 5 votes vote down vote up 
package org.sparksamples.classification.stumbleupon

import org.apache.log4j.Logger
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.mllib.evaluation.RegressionMetrics
import org.apache.spark.sql.DataFrame


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

  def logisticRegressionPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val lr = new LogisticRegression()

    val paramGrid = new ParamGridBuilder()
      .addGrid(lr.regParam, Array(0.1, 0.01))
      .addGrid(lr.fitIntercept)
      .addGrid(lr.elasticNetParam, Array(0.0, 0.25, 0.5, 0.75, 1.0))
      .build()

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

    val trainValidationSplit = new TrainValidationSplit()
      .setEstimator(pipeline)
      .setEvaluator(new RegressionEvaluator)
      .setEstimatorParamMaps(paramGrid)
      // 80% of the data will be used for training and the remaining 20% for validation.
      .setTrainRatio(0.8)

    val Array(training, test) = dataFrame.randomSplit(Array(0.8, 0.2), seed = 12345)
    //val model = trainValidationSplit.fit(training)
    val model = trainValidationSplit.fit(dataFrame)

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

    // have to do a type conversion for RegressionMetrics
    val rm = new RegressionMetrics(holdout.rdd.map(x => (x(0).asInstanceOf[Double], x(1).asInstanceOf[Double])))

    logger.info("Test Metrics")
    logger.info("Test Explained Variance:")
    logger.info(rm.explainedVariance)
    logger.info("Test R^2 Coef:")
    logger.info(rm.r2)
    logger.info("Test MSE:")
    logger.info(rm.meanSquaredError)
    logger.info("Test RMSE:")
    logger.info(rm.rootMeanSquaredError)

    val totalPoints = dataFrame.count()
    val lrTotalCorrect = holdout.rdd.map(x => if (x(0).asInstanceOf[Double] == x(1).asInstanceOf[Double]) 1 else 0).sum()
    val accuracy = lrTotalCorrect/totalPoints
    println("Accuracy of LogisticRegression is: ", accuracy)

    holdout.rdd.map(x => x(0).asInstanceOf[Double]).repartition(1).saveAsTextFile("/Users/manpreet.singh/Sandbox/codehub/github/machinelearning/spark-ml/Chapter_06/2.0.0/scala-spark-app/src/main/scala/org/sparksamples/classification/results/LR.xls")
    holdout.rdd.map(x => x(1).asInstanceOf[Double]).repartition(1).saveAsTextFile("/Users/manpreet.singh/Sandbox/codehub/github/machinelearning/spark-ml/Chapter_06/2.0.0/scala-spark-app/src/main/scala/org/sparksamples/classification/results/Actual.xls")

    savePredictions(holdout, dataFrame, rm, "/Users/manpreet.singh/Sandbox/codehub/github/machinelearning/spark-ml/Chapter_06/2.0.0/scala-spark-app/src/main/scala/org/sparksamples/classification/results/LogisticRegression.csv")
  }

  def savePredictions(predictions:DataFrame, testRaw:DataFrame, regressionMetrics: RegressionMetrics, filePath:String) = {
    println("Mean Squared Error:", regressionMetrics.meanSquaredError)
    println("Root Mean Squared Error:", regressionMetrics.rootMeanSquaredError)

    predictions
      .coalesce(1)
      .write.format("com.databricks.spark.csv")
      .option("header", "true")
      .save(filePath)
  }
}
Example 4
Source File: LogisticRegressionPipeline.scala    From Machine-Learning-with-Spark-Second-Edition   with MIT License 5 votes vote down vote up 
package org.sparksamples.classification.stumbleupon

import org.apache.log4j.Logger
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.mllib.evaluation.RegressionMetrics
import org.apache.spark.sql.DataFrame


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

  def logisticRegressionPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val lr = new LogisticRegression()

    val paramGrid = new ParamGridBuilder()
      .addGrid(lr.regParam, Array(0.1, 0.01))
      .addGrid(lr.fitIntercept)
      .addGrid(lr.elasticNetParam, Array(0.0, 0.25, 0.5, 0.75, 1.0))
      .build()

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

    val trainValidationSplit = new TrainValidationSplit()
      .setEstimator(pipeline)
      .setEvaluator(new RegressionEvaluator)
      .setEstimatorParamMaps(paramGrid)
      // 80% of the data will be used for training and the remaining 20% for validation.
      .setTrainRatio(0.8)

    val Array(training, test) = dataFrame.randomSplit(Array(0.8, 0.2), seed = 12345)
    //val model = trainValidationSplit.fit(training)
    val model = trainValidationSplit.fit(dataFrame)

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

    // have to do a type conversion for RegressionMetrics
    val rm = new RegressionMetrics(holdout.rdd.map(x => (x(0).asInstanceOf[Double], x(1).asInstanceOf[Double])))

    logger.info("Test Metrics")
    logger.info("Test Explained Variance:")
    logger.info(rm.explainedVariance)
    logger.info("Test R^2 Coef:")
    logger.info(rm.r2)
    logger.info("Test MSE:")
    logger.info(rm.meanSquaredError)
    logger.info("Test RMSE:")
    logger.info(rm.rootMeanSquaredError)

    val totalPoints = dataFrame.count()
    val lrTotalCorrect = holdout.rdd.map(x => if (x(0).asInstanceOf[Double] == x(1).asInstanceOf[Double]) 1 else 0).sum()
    val accuracy = lrTotalCorrect/totalPoints
    println("Accuracy of LogisticRegression is: ", accuracy)

    holdout.rdd.map(x => x(0).asInstanceOf[Double]).repartition(1).saveAsTextFile("/home/ubuntu/work/ml-resources/spark-ml/results/LR.xls")
    holdout.rdd.map(x => x(1).asInstanceOf[Double]).repartition(1).saveAsTextFile("/home/ubuntu/work/ml-resources/spark-ml/results/Actual.xls")

    savePredictions(holdout, dataFrame, rm, "/home/ubuntu/work/ml-resources/spark-ml/results/LogisticRegression.csv")
  }

  def savePredictions(predictions:DataFrame, testRaw:DataFrame, regressionMetrics: RegressionMetrics, filePath:String) = {
    println("Mean Squared Error:", regressionMetrics.meanSquaredError)
    println("Root Mean Squared Error:", regressionMetrics.rootMeanSquaredError)

    predictions
      .coalesce(1)
      .write.format("com.databricks.spark.csv")
      .option("header", "true")
      .save(filePath)
  }
}
Example 5
Source File: LogisticRegressionPipeline.scala    From Machine-Learning-with-Spark-Second-Edition   with MIT License 5 votes vote down vote up 
package org.stumbleuponclassifier

import org.apache.log4j.Logger
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.mllib.evaluation.RegressionMetrics
import org.apache.spark.sql.DataFrame


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

  def logisticRegressionPipeline(vectorAssembler: VectorAssembler, dataFrame: DataFrame) = {
    val lr = new LogisticRegression()

    val paramGrid = new ParamGridBuilder()
      .addGrid(lr.regParam, Array(0.1, 0.01))
      .addGrid(lr.fitIntercept)
      .addGrid(lr.elasticNetParam, Array(0.0, 0.25, 0.5, 0.75, 1.0))
      .build()

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

    val trainValidationSplit = new TrainValidationSplit()
      .setEstimator(pipeline)
      .setEvaluator(new RegressionEvaluator)
      .setEstimatorParamMaps(paramGrid)
      // 80% of the data will be used for training and the remaining 20% for validation.
      .setTrainRatio(0.8)

    val Array(training, test) = dataFrame.randomSplit(Array(0.8, 0.2), seed = 12345)
    //val model = trainValidationSplit.fit(training)
    val model = trainValidationSplit.fit(dataFrame)

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

    // have to do a type conversion for RegressionMetrics
    val rm = new RegressionMetrics(holdout.rdd.map(x => (x(0).asInstanceOf[Double], x(1).asInstanceOf[Double])))

    logger.info("Test Metrics")
    logger.info("Test Explained Variance:")
    logger.info(rm.explainedVariance)
    logger.info("Test R^2 Coef:")
    logger.info(rm.r2)
    logger.info("Test MSE:")
    logger.info(rm.meanSquaredError)
    logger.info("Test RMSE:")
    logger.info(rm.rootMeanSquaredError)

    val totalPoints = dataFrame.count()
    val lrTotalCorrect = holdout.rdd.map(x => if (x(0).asInstanceOf[Double] == x(1).asInstanceOf[Double]) 1 else 0).sum()
    val accuracy = lrTotalCorrect/totalPoints
    println("Accuracy of LogisticRegression is: ", accuracy)
  }

  def savePredictions(predictions:DataFrame, testRaw:DataFrame, regressionMetrics: RegressionMetrics, filePath:String) = {
    println("Mean Squared Error:", regressionMetrics.meanSquaredError)
    println("Root Mean Squared Error:", regressionMetrics.rootMeanSquaredError)

    predictions
      .coalesce(1)
      .write.format("com.databricks.spark.csv")
      .option("header", "true")
      .save(filePath)
  }
}
Example 6
Source File: ACMEModel.scala    From cdsw-simple-serving   with Apache License 2.0 5 votes vote down vote up 
// Don't execute these lines in the workbench -- skip to "Start workbench session"
package acme
import org.apache.spark.ml.PipelineModel


import com.cloudera.datascience.cdsw.acme.ACMEData
import org.apache.spark.ml.classification.{LogisticRegression, LogisticRegressionModel}
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
import org.apache.spark.ml.feature.VectorAssembler
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.ml.{Pipeline, PipelineModel}
import scala.util.Random

// Read and cache training data prepared from acme-dataeng:
val training = ACMEData.readData()
training.cache()
training.show()

// Build a logistic regression model,
val assembler = new VectorAssembler().
  setInputCols(training.columns.filter(_ != "Occupancy")).
  setOutputCol("featureVec")

val lr = new LogisticRegression().
  setFeaturesCol("featureVec").
  setLabelCol("Occupancy").
  setRawPredictionCol("rawPrediction")

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

// and tune that model:
val paramGrid = new ParamGridBuilder().
  addGrid(lr.regParam, Seq(0.00001, 0.001, 0.1)).
  addGrid(lr.elasticNetParam, Seq(1.0)).
  build()
    
val eval = new BinaryClassificationEvaluator().
  setLabelCol("Occupancy").
  setRawPredictionCol("rawPrediction")

val validator = new TrainValidationSplit().
  setSeed(Random.nextLong()).
  setEstimator(pipeline).
  setEvaluator(eval).
  setEstimatorParamMaps(paramGrid).
  setTrainRatio(0.9)

val validatorModel = validator.fit(training)
val pipelineModel = validatorModel.bestModel.asInstanceOf[PipelineModel]
val lrModel = pipelineModel.stages.last.asInstanceOf[LogisticRegressionModel]
    
// Logistic regression model parameters:
training.columns.zip(lrModel.coefficients.toArray).foreach(println)

// Model hyperparameters:
lrModel.getElasticNetParam
lrModel.getRegParam
    
// Validation metric (accuracy):
validatorModel.validationMetrics.max
    
pipelineModel
// End workbench session

  }
}
Example 7
Source File: TrainValidationSplitExample.scala    From BigDatalog   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.examples.ml

import org.apache.spark.ml.evaluation.RegressionEvaluator
import org.apache.spark.ml.regression.LinearRegression
import org.apache.spark.ml.tuning.{ParamGridBuilder, TrainValidationSplit}
import org.apache.spark.sql.SQLContext
import org.apache.spark.{SparkConf, SparkContext}


object TrainValidationSplitExample {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("TrainValidationSplitExample")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)

    // Prepare training and test data.
    val data = sqlContext.read.format("libsvm").load("data/mllib/sample_libsvm_data.txt")
    val Array(training, test) = data.randomSplit(Array(0.9, 0.1), seed = 12345)

    val lr = new LinearRegression()

    // We use a ParamGridBuilder to construct a grid of parameters to search over.
    // TrainValidationSplit will try all combinations of values and determine best model using
    // the evaluator.
    val paramGrid = new ParamGridBuilder()
      .addGrid(lr.regParam, Array(0.1, 0.01))
      .addGrid(lr.fitIntercept, Array(true, false))
      .addGrid(lr.elasticNetParam, Array(0.0, 0.5, 1.0))
      .build()

    // In this case the estimator is simply the linear regression.
    // A TrainValidationSplit requires an Estimator, a set of Estimator ParamMaps, and an Evaluator.
    val trainValidationSplit = new TrainValidationSplit()
      .setEstimator(lr)
      .setEvaluator(new RegressionEvaluator)
      .setEstimatorParamMaps(paramGrid)

    // 80% of the data will be used for training and the remaining 20% for validation.
    trainValidationSplit.setTrainRatio(0.8)

    // Run train validation split, and choose the best set of parameters.
    val model = trainValidationSplit.fit(training)

    // Make predictions on test data. model is the model with combination of parameters
    // that performed best.
    model.transform(test)
      .select("features", "label", "prediction")
      .show()

    sc.stop()
  }
}