Repository: spark Updated Branches: refs/heads/master f893955b9 -> 322d286bb
http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DTStatsAggregator.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DTStatsAggregator.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DTStatsAggregator.scala index ce8825c..7985ed4 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DTStatsAggregator.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DTStatsAggregator.scala @@ -27,7 +27,7 @@ import org.apache.spark.mllib.tree.impurity._ * and helps with indexing. * This class is abstract to support learning with and without feature subsampling. */ -private[tree] class DTStatsAggregator( +private[spark] class DTStatsAggregator( val metadata: DecisionTreeMetadata, featureSubset: Option[Array[Int]]) extends Serializable { http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala index f73896e..380291a 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala @@ -37,7 +37,7 @@ import org.apache.spark.rdd.RDD * I.e., the feature takes values in {0, ..., arity - 1}. * @param numBins Number of bins for each feature. */ -private[tree] class DecisionTreeMetadata( +private[spark] class DecisionTreeMetadata( val numFeatures: Int, val numExamples: Long, val numClasses: Int, @@ -94,7 +94,7 @@ private[tree] class DecisionTreeMetadata( } -private[tree] object DecisionTreeMetadata extends Logging { +private[spark] object DecisionTreeMetadata extends Logging { /** * Construct a [[DecisionTreeMetadata]] instance for this dataset and parameters. http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/NodeIdCache.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/NodeIdCache.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/NodeIdCache.scala index bdd0f57..8f9eb24 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/NodeIdCache.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/NodeIdCache.scala @@ -75,7 +75,7 @@ private[tree] case class NodeIndexUpdater( * (how often should the cache be checkpointed.). */ @DeveloperApi -private[tree] class NodeIdCache( +private[spark] class NodeIdCache( var nodeIdsForInstances: RDD[Array[Int]], val checkpointInterval: Int) { @@ -170,7 +170,7 @@ private[tree] class NodeIdCache( } @DeveloperApi -private[tree] object NodeIdCache { +private[spark] object NodeIdCache { /** * Initialize the node Id cache with initial node Id values. * @param data The RDD of training rows. http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TimeTracker.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TimeTracker.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TimeTracker.scala index d215d68..aac8424 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TimeTracker.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TimeTracker.scala @@ -25,7 +25,7 @@ import org.apache.spark.annotation.Experimental * Time tracker implementation which holds labeled timers. */ @Experimental -private[tree] class TimeTracker extends Serializable { +private[spark] class TimeTracker extends Serializable { private val starts: MutableHashMap[String, Long] = new MutableHashMap[String, Long]() http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TreePoint.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TreePoint.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TreePoint.scala index 50b292e..21919d6 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TreePoint.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/TreePoint.scala @@ -37,11 +37,11 @@ import org.apache.spark.rdd.RDD * @param binnedFeatures Binned feature values. * Same length as LabeledPoint.features, but values are bin indices. */ -private[tree] class TreePoint(val label: Double, val binnedFeatures: Array[Int]) +private[spark] class TreePoint(val label: Double, val binnedFeatures: Array[Int]) extends Serializable { } -private[tree] object TreePoint { +private[spark] object TreePoint { /** * Convert an input dataset into its TreePoint representation, http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala index 72eb24c..578749d 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Impurity.scala @@ -57,7 +57,7 @@ trait Impurity extends Serializable { * Note: Instances of this class do not hold the data; they operate on views of the data. * @param statsSize Length of the vector of sufficient statistics for one bin. */ -private[tree] abstract class ImpurityAggregator(val statsSize: Int) extends Serializable { +private[spark] abstract class ImpurityAggregator(val statsSize: Int) extends Serializable { /** * Merge the stats from one bin into another. @@ -95,7 +95,7 @@ private[tree] abstract class ImpurityAggregator(val statsSize: Int) extends Seri * (node, feature, bin). * @param stats Array of sufficient statistics for a (node, feature, bin). */ -private[tree] abstract class ImpurityCalculator(val stats: Array[Double]) { +private[spark] abstract class ImpurityCalculator(val stats: Array[Double]) { /** * Make a deep copy of this [[ImpurityCalculator]]. http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala index 2d087c9..dc9e0f9 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/InformationGainStats.scala @@ -67,7 +67,7 @@ class InformationGainStats( } -private[tree] object InformationGainStats { +private[spark] object InformationGainStats { /** * An [[org.apache.spark.mllib.tree.model.InformationGainStats]] object to * denote that current split doesn't satisfies minimum info gain or http://git-wip-us.apache.org/repos/asf/spark/blob/322d286b/mllib/src/test/java/org/apache/spark/ml/regression/JavaDecisionTreeRegressorSuite.java ---------------------------------------------------------------------- diff --git a/mllib/src/test/java/org/apache/spark/ml/regression/JavaDecisionTreeRegressorSuite.java b/mllib/src/test/java/org/apache/spark/ml/regression/JavaDecisionTreeRegressorSuite.java index 71b0418..ebe800e 100644 --- a/mllib/src/test/java/org/apache/spark/ml/regression/JavaDecisionTreeRegressorSuite.java +++ b/mllib/src/test/java/org/apache/spark/ml/regression/JavaDecisionTreeRegressorSuite.java @@ -57,7 +57,7 @@ public class JavaDecisionTreeRegressorSuite implements Serializable { JavaRDD<LabeledPoint> data = sc.parallelize( LogisticRegressionSuite.generateLogisticInputAsList(A, B, nPoints, 42), 2).cache(); Map<Integer, Integer> categoricalFeatures = new HashMap<Integer, Integer>(); - DataFrame dataFrame = TreeTests.setMetadata(data, categoricalFeatures, 2); + DataFrame dataFrame = TreeTests.setMetadata(data, categoricalFeatures, 0); // This tests setters. Training with various options is tested in Scala. DecisionTreeRegressor dt = new DecisionTreeRegressor() --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
