This gist contains code snippets for my blogpost: 'Random Forest with Python and Spark ML'

evaluate.py

import matplotlib.pyplot as plt

evaluator = RegressionEvaluator(labelCol="label", predictionCol="prediction", metricName="rmse")

rmse = evaluator.evaluate(predictions)

rfPred = model.transform(df)

rfResult = rfPred.toPandas()

plt.plot(rfResult.label, rfResult.prediction, 'bo')
plt.xlabel('Price')
plt.ylabel('Prediction')
plt.suptitle("Model Performance RMSE: %f" % rmse)
plt.show()