We skip the data ingestion and parsing since it is similar to previous recipes, but what is different is how we set up the parameters, especially the use of "classification" as a parameter that we pass into BoostingStrategy.defaultParams():
val algo = "Classification" val numIterations = 3 val numClasses = 2 val maxDepth = 5 val maxBins = 32 val categoricalFeatureInfo = Map[Int,Int]() val boostingStrategy = BoostingStrategy.defaultParams(algo)
We also use the evaluate() function to evaluate the parameters by looking at impurity and the confusion matrix:
evaluate(trainingData, testData, boostingStrategy)
Confusion Matrix :124.0 2.02.0 64.0Model Accuracy: 0.9791666666666666Model Error: 0.02083333333333337
