Вы можете попробовать это:
(trainingData, testData) = data.randomSplit([0.7, 0.3])
model = DecisionTree.trainRegressor(trainingData, categoricalFeaturesInfo={}, impurity='variance', numClasses=2)
paramGrid = ParamGridBuilder() \
.addGrid(model.maxDepth, [4, 5, 6, 7]) \
.addGrid(model.maxBins, [24, 28, 32, 36]) \
.build()
crossval = CrossValidator(estimator=model,
estimatorParamMaps=paramGrid,
evaluator=BinaryClassificationEvaluator(),
numFolds=3)
# Run cross-validation, and choose the best set of parameters.
cvModel = crossval.fit(training)