Hi Asim, The "featureImportances" is only exposed at ML not MLlib. You need to update your code to use RandomForestClassifier of ML to train and get one RandomForestClassificationModel. Then you can call RandomForestClassificationModel.featureImportances <https://github.com/apache/spark/blob/master/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala#L237> to get the importances of each feature.
For how to use RandomForestClassifier, you can refer this example <https://github.com/apache/spark/blob/master/examples/src/main/scala/org/apache/spark/examples/ml/RandomForestClassifierExample.scala> . Yanbo 2015-12-17 13:41 GMT+08:00 Asim Jalis <asimja...@gmail.com>: > I wanted to use get feature importances related to a Random Forest as > described in this JIRA: https://issues.apache.org/jira/browse/SPARK-5133 > > However, I don’t see how to call this. I don't see any methods exposed on > > org.apache.spark.mllib.tree.RandomForest > > How can I get featureImportances when I generate a RandomForest model in > this code? > > import org.apache.spark.mllib.linalg.Vectors > import org.apache.spark.mllib.regression.LabeledPoint > import org.apache.spark.mllib.tree.RandomForest > import org.apache.spark.mllib.tree.model.RandomForestModel > import org.apache.spark.mllib.util.MLUtils > import org.apache.spark.rdd.RDD > import util.Random > > def displayModel(model:RandomForestModel) = { > // Display model. > println("Learned classification tree model:\n" + model.toDebugString) > } > > def saveModel(model:RandomForestModel,path:String) = { > // Save and load model. > model.save(sc, path) > val sameModel = DecisionTreeModel.load(sc, path) > } > > def testModel(model:RandomForestModel,testData:RDD[LabeledPoint]) = { > // Test model. > val labelAndPreds = testData.map { point => > val prediction = model.predict(point.features) > (point.label, prediction) > } > val testErr = labelAndPreds. > filter(r => r._1 != r._2).count.toDouble / testData.count() > println("Test Error = " + testErr) > } > > def buildModel(trainingData:RDD[LabeledPoint], > numClasses:Int,categoricalFeaturesInfo:Map[Int,Int]) = { > val numTrees = 30 > val featureSubsetStrategy = "auto" > val impurity = "gini" > val maxDepth = 4 > val maxBins = 32 > > // Build model. > val model = RandomForest.trainClassifier( > trainingData, numClasses, categoricalFeaturesInfo, > numTrees, featureSubsetStrategy, impurity, maxDepth, > maxBins) > > model > } > > // Create plain RDD. > val rdd = sc.parallelize(Range(0,1000)) > > // Convert to LabeledPoint RDD. > val data = rdd. > map(x => { > val label = x % 2 > val feature1 = x % 5 > val feature2 = x % 7 > val features = Seq(feature1,feature2). > map(_.toDouble). > zipWithIndex. > map(_.swap) > val vector = Vectors.sparse(features.size, features) > val point = new LabeledPoint(label, vector) > point }) > > // Split data into training (70%) and test (30%). > val splits = data.randomSplit(Array(0.7, 0.3)) > val (trainingData, testData) = (splits(0), splits(1)) > > // Set up parameters for training. > val numClasses = data.map(_.label).distinct.count.toInt > val categoricalFeaturesInfo = Map[Int, Int]() > > val model = buildModel( > trainingData, > numClasses, > categoricalFeaturesInfo) > testModel(model,testData) > >
