boston_cv.py

from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
from pyspark.ml.evaluation import RegressionEvaluator

crossval = CrossValidator(estimator=LinearRegression(labelCol = "target"),  
                         estimatorParamMaps=ParamGridBuilder().addGrid(
                           LinearRegression.elasticNetParam, [0, 0.5, 1.0]).build(),
                         evaluator=RegressionEvaluator(
                           labelCol = "target", metricName = "r2"),
                         numFolds=10)

# cross validate the model and select the best fit
cvModel = crossval.fit(boston_train) 
model = cvModel.bestModel

# calculate results 
boston_pred = model.transform(boston_test)
r = boston_pred.stat.corr("prediction", "target")
print("R-sqaured: " + str(r**2))