org.apache.spark.ml.tree

Class DecisionTreeModelReadWrite

java.lang.Object

org.apache.spark.ml.tree.DecisionTreeModelReadWrite

public class DecisionTreeModelReadWrite
extends java.lang.Object

Helper classes for tree model persistence

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	DecisionTreeModelReadWrite.NodeData Info for a Node
static class	DecisionTreeModelReadWrite.NodeData$
static class	DecisionTreeModelReadWrite.SplitData Info for a Split
static class	DecisionTreeModelReadWrite.SplitData$

Constructor Summary

Constructors

Constructor and Description
DecisionTreeModelReadWrite()

Method Summary

Methods

Modifier and Type	Method and Description
static Node	buildTreeFromNodes(DecisionTreeModelReadWrite.NodeData[] data, java.lang.String impurityType) Given all data for all nodes in a tree, rebuild the tree.
static Node	loadTreeNodes(java.lang.String path, org.apache.spark.ml.util.DefaultParamsReader.Metadata metadata, SQLContext sqlContext) Load a decision tree from a file.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

DecisionTreeModelReadWrite

public DecisionTreeModelReadWrite()

Method Detail

loadTreeNodes

public static Node loadTreeNodes(java.lang.String path,
                 org.apache.spark.ml.util.DefaultParamsReader.Metadata metadata,
                 SQLContext sqlContext)

Load a decision tree from a file.

Parameters:

path - (undocumented)

metadata - (undocumented)

sqlContext - (undocumented)

Returns:

Root node of reconstructed tree

buildTreeFromNodes

public static Node buildTreeFromNodes(DecisionTreeModelReadWrite.NodeData[] data,
                      java.lang.String impurityType)

Given all data for all nodes in a tree, rebuild the tree.

Parameters:

data - Unsorted node data

impurityType - Impurity type for this tree

Returns:

Root node of reconstructed tree