1. Start Spark shell:

        $ spark-shell

2. Do the necessary imports:

        scala> import org.apache.spark.ml.regression.LinearRegression
        scala> import org.apache.spark.ml.evaluation.RegressionEvaluator
        scala> import org.apache.spark.ml.tuning.{ParamGridBuilder, 
        TrainValidationSplit}

3. Load data as DataFrame:

        scala> val data = 
        spark.read.format("libsvm").load
        ("s3a://sparkcookbook/housingdata/realestate.libsvm")

4. Split data into training and test sets:

        scala> val Array(training, test) = data.randomSplit
        (Array(0.7, 0.3))

5. Instantiate linear regression:

        scala> val lr = new LinearRegression().setMaxIter(10)

6. Create a parameter grid:

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

7. Create a training validation split:

        scala> val trainValidationSplit = new TrainValidationSplit()
         .setEstimator(lr)
         .setEvaluator(new RegressionEvaluator)
         .setEstimatorParamMaps(paramGrid)
         .setTrainRatio(0.8)

8. Train the model:

        scala> val model = trainValidationSplit.fit(training)

9. Do the predictions on the test dataset:

        scala> val predictions = model.transform(test)

10. Evaluate the predictions:

        scala> val evaluator = new RegressionEvaluator()
        scala> evaluator.evaluate(predictions)