13 Sparkify Cross Validation

sparkify_13_cross_validation.py

# Our Grid Search object allows us to define various hyperparameters to test our model
params = ParamGridBuilder()\
    .addGrid(classifier.maxDepth, [2, 5, 10])\
    .addGrid(classifier.featureSubsetStrategy, ['all', 'onethird', 'sqrt', 'log2'])\
    .build()

# Define the evaluator, this will measure teh success of model(s)
evaluator = binary_evaluator = BinaryClassificationEvaluator(labelCol='churned')

# CrossValidator will build pipeline, create models based on ParamGridBuilder, 
# evalute against defined evaluator success and do cross validation using 5 folds 
cv = CrossValidator(estimator=pipeline,
          estimatorParamMaps=params,
          evaluator=evaluator, 
          numFolds=5)