Fixed bug in python example decision_tree_runner.py with missing argument. Changed main DecisionTree aggregate to treeAggregate.

Author: jkbradley

examples/src/main/python/mllib/decision_tree_runner.py

@@ -124,7 +124,9 @@ def usage():
     (reindexedData, origToNewLabels) = reindexClassLabels(points)
 
     # Train a classifier.
-    model = DecisionTree.trainClassifier(reindexedData, numClasses=2)
+    categoricalFeaturesInfo={} # no categorical features
+    model = DecisionTree.trainClassifier(reindexedData, numClasses=2,
+                                         categoricalFeaturesInfo=categoricalFeaturesInfo)
     # Print learned tree and stats.
     print "Trained DecisionTree for classification:"
     print "  Model numNodes: %d\n" % model.numNodes()

mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala

@@ -22,6 +22,7 @@ import scala.collection.JavaConverters._
 import org.apache.spark.annotation.Experimental
 import org.apache.spark.api.java.JavaRDD
 import org.apache.spark.Logging
+import org.apache.spark.mllib.rdd.RDDFunctions._
 import org.apache.spark.mllib.regression.LabeledPoint
 import org.apache.spark.mllib.tree.configuration.Strategy
 import org.apache.spark.mllib.tree.configuration.Algo._
@@ -826,7 +827,7 @@ object DecisionTree extends Serializable with Logging {
     // Calculate bin aggregates.
     timer.start("aggregation")
     val binAggregates = {
-      input.aggregate(Array.fill[Double](binAggregateLength)(0))(binSeqOp, binCombOp)
+      input.treeAggregate(Array.fill[Double](binAggregateLength)(0))(binSeqOp, binCombOp)
     }
     timer.stop("aggregation")
     logDebug("binAggregates.length = " + binAggregates.length)