Strategy

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. var algo: Algo.Algo

   

   Learning goal.

   Learning goal. Supported: org.apache.spark.mllib.tree.configuration.Algo.Classification, org.apache.spark.mllib.tree.configuration.Algo.Regression

   Annotations

   @Since( "1.0.0" )

5. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

6. var categoricalFeaturesInfo: Map[Int, Int]

   

   A map storing information about the categorical variables and the number of discrete values they take.

   A map storing information about the categorical variables and the number of discrete values they take. An entry (n -> k) indicates that feature n is categorical with k categories indexed from 0: {0, 1, ..., k-1}.

   Annotations

   @Since( "1.0.0" )

7. var checkpointInterval: Int

   

   How often to checkpoint when the node Id cache gets updated.

   How often to checkpoint when the node Id cache gets updated. E.g. 10 means that the cache will get checkpointed every 10 updates. If the checkpoint directory is not set in org.apache.spark.SparkContext, this setting is ignored.

   Annotations

   @Since( "1.2.0" )

8. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

9. def copy: Strategy

   

   Returns a shallow copy of this instance.

   Returns a shallow copy of this instance.

   Annotations

   @Since( "1.2.0" )

10. final def eq(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

11. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

12. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

13. def getAlgo(): Algo.Algo

    

    Annotations

    @Since( "1.0.0" )

14. def getCategoricalFeaturesInfo(): Map[Int, Int]

    

    Annotations

    @Since( "1.0.0" )

15. def getCheckpointInterval(): Int

    

    Annotations

    @Since( "1.2.0" )

16. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

17. def getImpurity(): Impurity

    

    Annotations

    @Since( "1.0.0" )

18. def getMaxBins(): Int

    

    Annotations

    @Since( "1.0.0" )

19. def getMaxDepth(): Int

    

    Annotations

    @Since( "1.0.0" )

20. def getMaxMemoryInMB(): Int

    

    Annotations

    @Since( "1.0.0" )

21. def getMinInfoGain(): Double

    

    Annotations

    @Since( "1.2.0" )

22. def getMinInstancesPerNode(): Int

    

    Annotations

    @Since( "1.2.0" )

23. def getNumClasses(): Int

    

    Annotations

    @Since( "1.2.0" )

24. def getQuantileCalculationStrategy(): QuantileStrategy.QuantileStrategy

    

    Annotations

    @Since( "1.0.0" )

25. def getSubsamplingRate(): Double

    

    Annotations

    @Since( "1.2.0" )

26. def getUseNodeIdCache(): Boolean

    

    Annotations

    @Since( "1.2.0" )

27. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

28. var impurity: Impurity

    

    Criterion used for information gain calculation.

    Criterion used for information gain calculation. Supported for Classification: org.apache.spark.mllib.tree.impurity.Gini, org.apache.spark.mllib.tree.impurity.Entropy. Supported for Regression: org.apache.spark.mllib.tree.impurity.Variance.

    Annotations

    @Since( "1.0.0" )

29. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

30. def isMulticlassClassification: Boolean

    
    Annotations

    @Since( "1.2.0" )

31. def isMulticlassWithCategoricalFeatures: Boolean

    
    Annotations

    @Since( "1.2.0" )

32. var maxBins: Int

    

    Maximum number of bins used for discretizing continuous features and for choosing how to split on features at each node.

    Maximum number of bins used for discretizing continuous features and for choosing how to split on features at each node. More bins give higher granularity.

    Annotations

    @Since( "1.0.0" )

33. var maxDepth: Int

    

    Maximum depth of the tree (e.g.

    Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means 1 internal node + 2 leaf nodes).

    Annotations

    @Since( "1.0.0" )

34. var maxMemoryInMB: Int

    

    Maximum memory in MB allocated to histogram aggregation.

    Maximum memory in MB allocated to histogram aggregation. Default value is 256 MB. If too small, then 1 node will be split per iteration, and its aggregates may exceed this size.

    Annotations

    @Since( "1.0.0" )

35. var minInfoGain: Double

    

    Minimum information gain a split must get.

    Minimum information gain a split must get. Default value is 0.0. If a split has less information gain than minInfoGain, this split will not be considered as a valid split.

    Annotations

    @Since( "1.2.0" )

36. var minInstancesPerNode: Int

    

    Minimum number of instances each child must have after split.

    Minimum number of instances each child must have after split. Default value is 1. If a split cause left or right child to have less than minInstancesPerNode, this split will not be considered as a valid split.

    Annotations

    @Since( "1.2.0" )

37. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

38. final def notify(): Unit

    

    Definition Classes

    AnyRef

39. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

40. var numClasses: Int

    

    Number of classes for classification.

    Number of classes for classification. (Ignored for regression.) Default value is 2 (binary classification).

    Annotations

    @Since( "1.2.0" )

41. var quantileCalculationStrategy: QuantileStrategy.QuantileStrategy

    

    Algorithm for calculating quantiles.

    Algorithm for calculating quantiles. Supported: org.apache.spark.mllib.tree.configuration.QuantileStrategy.Sort

    Annotations

    @Since( "1.0.0" )

42. def setAlgo(algo: String): Unit

    

    Sets Algorithm using a String.

    Sets Algorithm using a String.

    Annotations

    @Since( "1.2.0" )

43. def setAlgo(arg0: Algo.Algo): Unit

    

44. def setCategoricalFeaturesInfo(categoricalFeaturesInfo: Map[Integer, Integer]): Unit

    

    Sets categoricalFeaturesInfo using a Java Map.

    Sets categoricalFeaturesInfo using a Java Map.

    Annotations

    @Since( "1.2.0" )

45. def setCategoricalFeaturesInfo(arg0: Map[Int, Int]): Unit

    

46. def setCheckpointInterval(arg0: Int): Unit

    

    Annotations

    @Since( "1.2.0" )

47. def setImpurity(arg0: Impurity): Unit

    

    Annotations

    @Since( "1.0.0" )

48. def setMaxBins(arg0: Int): Unit

    

    Annotations

    @Since( "1.0.0" )

49. def setMaxDepth(arg0: Int): Unit

    

    Annotations

    @Since( "1.0.0" )

50. def setMaxMemoryInMB(arg0: Int): Unit

    

    Annotations

    @Since( "1.0.0" )

51. def setMinInfoGain(arg0: Double): Unit

    

    Annotations

    @Since( "1.2.0" )

52. def setMinInstancesPerNode(arg0: Int): Unit

    

    Annotations

    @Since( "1.2.0" )

53. def setNumClasses(arg0: Int): Unit

    

    Annotations

    @Since( "1.2.0" )

54. def setQuantileCalculationStrategy(arg0: QuantileStrategy.QuantileStrategy): Unit

    

    Annotations

    @Since( "1.0.0" )

55. def setSubsamplingRate(arg0: Double): Unit

    

    Annotations

    @Since( "1.2.0" )

56. def setUseNodeIdCache(arg0: Boolean): Unit

    

    Annotations

    @Since( "1.2.0" )

57. var subsamplingRate: Double

    

    Fraction of the training data used for learning decision tree.

    Fraction of the training data used for learning decision tree.

    Annotations

    @Since( "1.2.0" )

58. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

59. def toString(): String

    

    Definition Classes

    AnyRef → Any

60. var useNodeIdCache: Boolean

    

    If this is true, instead of passing trees to executors, the algorithm will maintain a separate RDD of node Id cache for each row.

    If this is true, instead of passing trees to executors, the algorithm will maintain a separate RDD of node Id cache for each row.

    Annotations

    @Since( "1.2.0" )

61. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

62. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

63. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )