Random Forest

Setting Up Random Forest Regression

Note: Make sure you have your training and test data already vectorized and ready to go before you begin trying to fit the machine learning model to unprepped data.

Load in required libraries

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

Initialize Random Forest object

rf = RandomForestRegressor(labelCol="label", featuresCol="features")

Create a parameter grid for tuning the model

rfparamGrid = (ParamGridBuilder()
             #.addGrid(rf.maxDepth, [2, 5, 10, 20, 30])
               .addGrid(rf.maxDepth, [2, 5, 10])
             #.addGrid(rf.maxBins, [10, 20, 40, 80, 100])
               .addGrid(rf.maxBins, [5, 10, 20])
             #.addGrid(rf.numTrees, [5, 20, 50, 100, 500])
               .addGrid(rf.numTrees, [5, 20, 50])

Define how you want the model to be evaluated

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

Define the type of cross-validation you want to perform

# Create 5-fold CrossValidator
rfcv = CrossValidator(estimator = rf,
                      estimatorParamMaps = rfparamGrid,
                      evaluator = rfevaluator,
                      numFolds = 5)

Fit the model to the data

rfcvModel = rfcv.fit(train)

Score the testing dataset using your fitted model for evaluation purposes

rfpredictions = rfcvModel.transform(test)

Evaluate the model

print('RMSE:', rfevaluator.evaluate(rfpredictions))

Note: When you use the CrossValidator function to set up cross-validation of your models, the resulting model object will have all the runs included, but will only use the best model when you interact with the model object using other functions like evaluate or transform.

Last updated