Repository: spark Updated Branches: refs/heads/branch-1.5 be0c9915c -> 6d8ebc801
[SPARK-10243] [MLLIB] update since versions in mllib.tree Same as #8421 but for `mllib.tree`. cc jkbradley Author: Xiangrui Meng <m...@databricks.com> Closes #8442 from mengxr/SPARK-10236. (cherry picked from commit fb7e12fe2e14af8de4c206ca8096b2e8113bfddc) Signed-off-by: Xiangrui Meng <m...@databricks.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/6d8ebc80 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/6d8ebc80 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/6d8ebc80 Branch: refs/heads/branch-1.5 Commit: 6d8ebc801799714d297c83be6935b37e26dc2df7 Parents: be0c991 Author: Xiangrui Meng <m...@databricks.com> Authored: Tue Aug 25 22:35:49 2015 -0700 Committer: Xiangrui Meng <m...@databricks.com> Committed: Tue Aug 25 22:35:56 2015 -0700 ---------------------------------------------------------------------- .../apache/spark/mllib/tree/DecisionTree.scala | 3 +- .../spark/mllib/tree/GradientBoostedTrees.scala | 2 +- .../spark/mllib/tree/configuration/Algo.scala | 2 ++ .../tree/configuration/BoostingStrategy.scala | 12 ++++---- .../mllib/tree/configuration/FeatureType.scala | 2 ++ .../tree/configuration/QuantileStrategy.scala | 2 ++ .../mllib/tree/configuration/Strategy.scala | 29 ++++++++++---------- .../mllib/tree/model/DecisionTreeModel.scala | 5 +++- .../apache/spark/mllib/tree/model/Node.scala | 18 ++++++------ .../apache/spark/mllib/tree/model/Predict.scala | 6 ++-- .../apache/spark/mllib/tree/model/Split.scala | 8 +++--- .../mllib/tree/model/treeEnsembleModels.scala | 12 ++++---- 12 files changed, 57 insertions(+), 44 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/DecisionTree.scala ---------------------------------------------------------------------- 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 9728410..4a77d4a 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 @@ -46,7 +46,8 @@ import org.apache.spark.util.random.XORShiftRandom */ @Since("1.0.0") @Experimental -class DecisionTree (private val strategy: Strategy) extends Serializable with Logging { +class DecisionTree @Since("1.0.0") (private val strategy: Strategy) + extends Serializable with Logging { strategy.assertValid() http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala index e750408..95ed48c 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoostedTrees.scala @@ -51,7 +51,7 @@ import org.apache.spark.storage.StorageLevel */ @Since("1.2.0") @Experimental -class GradientBoostedTrees(private val boostingStrategy: BoostingStrategy) +class GradientBoostedTrees @Since("1.2.0") (private val boostingStrategy: BoostingStrategy) extends Serializable with Logging { /** http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala index 8301ad1..853c731 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Algo.scala @@ -26,7 +26,9 @@ import org.apache.spark.annotation.{Experimental, Since} @Since("1.0.0") @Experimental object Algo extends Enumeration { + @Since("1.0.0") type Algo = Value + @Since("1.0.0") val Classification, Regression = Value private[mllib] def fromString(name: String): Algo = name match { http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/BoostingStrategy.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/BoostingStrategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/BoostingStrategy.scala index 7c56998..b5c72fb 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/BoostingStrategy.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/BoostingStrategy.scala @@ -41,14 +41,14 @@ import org.apache.spark.mllib.tree.loss.{LogLoss, SquaredError, Loss} */ @Since("1.2.0") @Experimental -case class BoostingStrategy( +case class BoostingStrategy @Since("1.4.0") ( // Required boosting parameters - @BeanProperty var treeStrategy: Strategy, - @BeanProperty var loss: Loss, + @Since("1.2.0") @BeanProperty var treeStrategy: Strategy, + @Since("1.2.0") @BeanProperty var loss: Loss, // Optional boosting parameters - @BeanProperty var numIterations: Int = 100, - @BeanProperty var learningRate: Double = 0.1, - @BeanProperty var validationTol: Double = 1e-5) extends Serializable { + @Since("1.2.0") @BeanProperty var numIterations: Int = 100, + @Since("1.2.0") @BeanProperty var learningRate: Double = 0.1, + @Since("1.4.0") @BeanProperty var validationTol: Double = 1e-5) extends Serializable { /** * Check validity of parameters. http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala index bb7c7ee..4e0cd47 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/FeatureType.scala @@ -26,6 +26,8 @@ import org.apache.spark.annotation.{Experimental, Since} @Since("1.0.0") @Experimental object FeatureType extends Enumeration { + @Since("1.0.0") type FeatureType = Value + @Since("1.0.0") val Continuous, Categorical = Value } http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala index 904e42d..8262db8 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/QuantileStrategy.scala @@ -26,6 +26,8 @@ import org.apache.spark.annotation.{Experimental, Since} @Since("1.0.0") @Experimental object QuantileStrategy extends Enumeration { + @Since("1.0.0") type QuantileStrategy = Value + @Since("1.0.0") val Sort, MinMax, ApproxHist = Value } http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala index b74e3f1..89cc13b 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/configuration/Strategy.scala @@ -69,20 +69,20 @@ import org.apache.spark.mllib.tree.configuration.QuantileStrategy._ */ @Since("1.0.0") @Experimental -class Strategy ( - @BeanProperty var algo: Algo, - @BeanProperty var impurity: Impurity, - @BeanProperty var maxDepth: Int, - @BeanProperty var numClasses: Int = 2, - @BeanProperty var maxBins: Int = 32, - @BeanProperty var quantileCalculationStrategy: QuantileStrategy = Sort, - @BeanProperty var categoricalFeaturesInfo: Map[Int, Int] = Map[Int, Int](), - @BeanProperty var minInstancesPerNode: Int = 1, - @BeanProperty var minInfoGain: Double = 0.0, - @BeanProperty var maxMemoryInMB: Int = 256, - @BeanProperty var subsamplingRate: Double = 1, - @BeanProperty var useNodeIdCache: Boolean = false, - @BeanProperty var checkpointInterval: Int = 10) extends Serializable { +class Strategy @Since("1.3.0") ( + @Since("1.0.0") @BeanProperty var algo: Algo, + @Since("1.0.0") @BeanProperty var impurity: Impurity, + @Since("1.0.0") @BeanProperty var maxDepth: Int, + @Since("1.2.0") @BeanProperty var numClasses: Int = 2, + @Since("1.0.0") @BeanProperty var maxBins: Int = 32, + @Since("1.0.0") @BeanProperty var quantileCalculationStrategy: QuantileStrategy = Sort, + @Since("1.0.0") @BeanProperty var categoricalFeaturesInfo: Map[Int, Int] = Map[Int, Int](), + @Since("1.2.0") @BeanProperty var minInstancesPerNode: Int = 1, + @Since("1.2.0") @BeanProperty var minInfoGain: Double = 0.0, + @Since("1.0.0") @BeanProperty var maxMemoryInMB: Int = 256, + @Since("1.2.0") @BeanProperty var subsamplingRate: Double = 1, + @Since("1.2.0") @BeanProperty var useNodeIdCache: Boolean = false, + @Since("1.2.0") @BeanProperty var checkpointInterval: Int = 10) extends Serializable { /** */ @@ -206,6 +206,7 @@ object Strategy { } @deprecated("Use Strategy.defaultStrategy instead.", "1.5.0") + @Since("1.2.0") def defaultStategy(algo: Algo): Strategy = defaultStrategy(algo) } http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala index 3eefd13..e1bf23f 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/DecisionTreeModel.scala @@ -43,7 +43,9 @@ import org.apache.spark.util.Utils */ @Since("1.0.0") @Experimental -class DecisionTreeModel(val topNode: Node, val algo: Algo) extends Serializable with Saveable { +class DecisionTreeModel @Since("1.0.0") ( + @Since("1.0.0") val topNode: Node, + @Since("1.0.0") val algo: Algo) extends Serializable with Saveable { /** * Predict values for a single data point using the model trained. @@ -110,6 +112,7 @@ class DecisionTreeModel(val topNode: Node, val algo: Algo) extends Serializable /** * Print the full model to a string. */ + @Since("1.2.0") def toDebugString: String = { val header = toString + "\n" header + topNode.subtreeToString(2) http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala index 8c54c55..ea6e5aa 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Node.scala @@ -41,15 +41,15 @@ import org.apache.spark.mllib.linalg.Vector */ @Since("1.0.0") @DeveloperApi -class Node ( - val id: Int, - var predict: Predict, - var impurity: Double, - var isLeaf: Boolean, - var split: Option[Split], - var leftNode: Option[Node], - var rightNode: Option[Node], - var stats: Option[InformationGainStats]) extends Serializable with Logging { +class Node @Since("1.2.0") ( + @Since("1.0.0") val id: Int, + @Since("1.0.0") var predict: Predict, + @Since("1.2.0") var impurity: Double, + @Since("1.0.0") var isLeaf: Boolean, + @Since("1.0.0") var split: Option[Split], + @Since("1.0.0") var leftNode: Option[Node], + @Since("1.0.0") var rightNode: Option[Node], + @Since("1.0.0") var stats: Option[InformationGainStats]) extends Serializable with Logging { override def toString: String = { s"id = $id, isLeaf = $isLeaf, predict = $predict, impurity = $impurity, " + http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala index 9657840..06ceff1 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Predict.scala @@ -26,9 +26,9 @@ import org.apache.spark.annotation.{DeveloperApi, Since} */ @Since("1.2.0") @DeveloperApi -class Predict( - val predict: Double, - val prob: Double = 0.0) extends Serializable { +class Predict @Since("1.2.0") ( + @Since("1.2.0") val predict: Double, + @Since("1.2.0") val prob: Double = 0.0) extends Serializable { override def toString: String = s"$predict (prob = $prob)" http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala index 45db83a..b85a66c 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/Split.scala @@ -34,10 +34,10 @@ import org.apache.spark.mllib.tree.configuration.FeatureType.FeatureType @Since("1.0.0") @DeveloperApi case class Split( - feature: Int, - threshold: Double, - featureType: FeatureType, - categories: List[Double]) { + @Since("1.0.0") feature: Int, + @Since("1.0.0") threshold: Double, + @Since("1.0.0") featureType: FeatureType, + @Since("1.0.0") categories: List[Double]) { override def toString: String = { s"Feature = $feature, threshold = $threshold, featureType = $featureType, " + http://git-wip-us.apache.org/repos/asf/spark/blob/6d8ebc80/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala index 1957144..df5b8fe 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/model/treeEnsembleModels.scala @@ -48,7 +48,9 @@ import org.apache.spark.util.Utils */ @Since("1.2.0") @Experimental -class RandomForestModel(override val algo: Algo, override val trees: Array[DecisionTreeModel]) +class RandomForestModel @Since("1.2.0") ( + @Since("1.2.0") override val algo: Algo, + @Since("1.2.0") override val trees: Array[DecisionTreeModel]) extends TreeEnsembleModel(algo, trees, Array.fill(trees.length)(1.0), combiningStrategy = if (algo == Classification) Vote else Average) with Saveable { @@ -115,10 +117,10 @@ object RandomForestModel extends Loader[RandomForestModel] { */ @Since("1.2.0") @Experimental -class GradientBoostedTreesModel( - override val algo: Algo, - override val trees: Array[DecisionTreeModel], - override val treeWeights: Array[Double]) +class GradientBoostedTreesModel @Since("1.2.0") ( + @Since("1.2.0") override val algo: Algo, + @Since("1.2.0") override val trees: Array[DecisionTreeModel], + @Since("1.2.0") override val treeWeights: Array[Double]) extends TreeEnsembleModel(algo, trees, treeWeights, combiningStrategy = Sum) with Saveable { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
