Decision Tree

gistfile1.java

Map<Integer, Integer> categoricalFeaturesInfo = new HashMap<>();
int numClasses = 4;
String impurity = "gini";
int maxDepth = 9;
int maxBins = 32;

// create model
final DecisionTreeModel model = DecisionTree.trainClassifier(trainingData, numClasses, categoricalFeaturesInfo, impurity, maxDepth, maxBins);

// Evaluate model on training instances and compute training error
JavaPairRDD<Double, Double> predictionAndLabel = testData.mapToPair(p -> new Tuple2<>(model.predict(p.features()), p.label()));

Double testErrDT = 1.0 * predictionAndLabel.filter(pl -> !pl._1().equals(pl._2())).count() / testData.count();