org.apache.spark.mllib.tree.model

Class Node

Object

org.apache.spark.mllib.tree.model.Node

All Implemented Interfaces:

java.io.Serializable, Logging

public class Node
extends Object
implements scala.Serializable, Logging

:: DeveloperApi :: Node in a decision tree

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
Node(int id, double predict, boolean isLeaf, scala.Option<Split> split, scala.Option<Node> leftNode, scala.Option<Node> rightNode, scala.Option<InformationGainStats> stats)

Method Summary

Methods

Modifier and Type	Method and Description
void	build(Node[] nodes) build the left node and right nodes if not leaf
int	id()
boolean	isLeaf()
scala.Option<Node>	leftNode()
double	predict()
double	predict(Vector features) predict value if node is not leaf
scala.Option<Node>	rightNode()
scala.Option<Split>	split()
scala.Option<InformationGainStats>	stats()
String	toString()

Methods inherited from class Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.spark.Logging

initialized, initializeIfNecessary, initializeLogging, initLock, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarning

Constructor Detail

Node

public Node(int id,
    double predict,
    boolean isLeaf,
    scala.Option<Split> split,
    scala.Option<Node> leftNode,
    scala.Option<Node> rightNode,
    scala.Option<InformationGainStats> stats)

Method Detail

id

public int id()

predict

public double predict()

isLeaf

public boolean isLeaf()

split

public scala.Option<Split> split()

leftNode

public scala.Option<Node> leftNode()

rightNode

public scala.Option<Node> rightNode()

stats

public scala.Option<InformationGainStats> stats()

toString

public String toString()

Overrides:

toString in class Object

build

public void build(Node[] nodes)

build the left node and right nodes if not leaf

Parameters:

nodes - array of nodes

predict

public double predict(Vector features)

predict value if node is not leaf

Parameters:

features - feature value

Returns:

predicted value