linear-regression-implementatio.scala

val lr = new LinearRegression()
  .setLabelCol("DelayOutputVar")
  .setFeaturesCol("features")
val paramGrid = new ParamGridBuilder()
  .addGrid(lr.regParam, Array(0.1, 0.01))
  .addGrid(lr.fitIntercept)
  .addGrid(lr.elasticNetParam, Array(0.0, 1.0))
  .build()

val steps:Array[org.apache.spark.ml.PipelineStage] = if(useCategorical){
                                                        categoricalIndexers ++ categoricalEncoders ++ Array(assembler, lr)
                                                      }else{
                                                        Array(assembler, lr)
                                                      }

val pipeline = new Pipeline().setStages(steps)

val tvs = new TrainValidationSplit()
  .setEstimator(pipeline)
  .setEvaluator(new RegressionEvaluator().setLabelCol("DelayOutputVar"))
  .setEstimatorParamMaps(paramGrid)
  .setTrainRatio(0.7)

val Array(training, test) = data.randomSplit(Array(0.70, 0.30), seed = 12345)

val model = tvs.fit(training)