diff options
| -rwxr-xr-x | examples/src/main/python/mllib/decision_tree_runner.py | 4 | ||||
| -rw-r--r-- | mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala | 3 | ||||
| -rw-r--r-- | python/pyspark/mllib/tree.py | 14 | ||||
| -rwxr-xr-x | python/run-tests | 1 |
4 files changed, 14 insertions, 8 deletions
diff --git a/examples/src/main/python/mllib/decision_tree_runner.py b/examples/src/main/python/mllib/decision_tree_runner.py index 8efadb5223..db96a7cb37 100755 --- a/examples/src/main/python/mllib/decision_tree_runner.py +++ b/examples/src/main/python/mllib/decision_tree_runner.py @@ -124,7 +124,9 @@ if __name__ == "__main__": (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() diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala index 6b9a8f72c2..5cdd258f6c 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala +++ b/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) diff --git a/python/pyspark/mllib/tree.py b/python/pyspark/mllib/tree.py index e1a4671709..e9d778df5a 100644 --- a/python/pyspark/mllib/tree.py +++ b/python/pyspark/mllib/tree.py @@ -88,7 +88,8 @@ class DecisionTree(object): It will probably be modified for Spark v1.2. Example usage: - >>> from numpy import array, ndarray + >>> from numpy import array + >>> import sys >>> from pyspark.mllib.regression import LabeledPoint >>> from pyspark.mllib.tree import DecisionTree >>> from pyspark.mllib.linalg import SparseVector @@ -99,15 +100,15 @@ class DecisionTree(object): ... LabeledPoint(1.0, [2.0]), ... LabeledPoint(1.0, [3.0]) ... ] - >>> - >>> model = DecisionTree.trainClassifier(sc.parallelize(data), numClasses=2) - >>> print(model) + >>> categoricalFeaturesInfo = {} # no categorical features + >>> model = DecisionTree.trainClassifier(sc.parallelize(data), numClasses=2, + ... categoricalFeaturesInfo=categoricalFeaturesInfo) + >>> sys.stdout.write(model) DecisionTreeModel classifier If (feature 0 <= 0.5) Predict: 0.0 Else (feature 0 > 0.5) Predict: 1.0 - >>> model.predict(array([1.0])) > 0 True >>> model.predict(array([0.0])) == 0 @@ -119,7 +120,8 @@ class DecisionTree(object): ... LabeledPoint(1.0, SparseVector(2, {1: 2.0})) ... ] >>> - >>> model = DecisionTree.trainRegressor(sc.parallelize(sparse_data)) + >>> model = DecisionTree.trainRegressor(sc.parallelize(sparse_data), + ... categoricalFeaturesInfo=categoricalFeaturesInfo) >>> model.predict(array([0.0, 1.0])) == 1 True >>> model.predict(array([0.0, 0.0])) == 0 diff --git a/python/run-tests b/python/run-tests index 1218edcbd7..a6271e0cf5 100755 --- a/python/run-tests +++ b/python/run-tests @@ -79,6 +79,7 @@ run_test "pyspark/mllib/random.py" run_test "pyspark/mllib/recommendation.py" run_test "pyspark/mllib/regression.py" run_test "pyspark/mllib/tests.py" +run_test "pyspark/mllib/tree.py" run_test "pyspark/mllib/util.py" if [[ $FAILED == 0 ]]; then |