Package org.tribuo.regression.rtree

Class TrainTest.RegressionTreeOptions

java.lang.Object

org.tribuo.regression.rtree.TrainTest.RegressionTreeOptions

All Implemented Interfaces:

com.oracle.labs.mlrg.olcut.config.Options

Enclosing class:

TrainTest

public static class TrainTest.RegressionTreeOptions
extends Object
implements com.oracle.labs.mlrg.olcut.config.Options

Command line options.

Field Summary

Fields

Modifier and Type	Field	Description
int	depth	Maximum depth in the decision tree.
float	fraction	Fraction of features in split.
DataOptions	general	The data loading options.
TrainTest.ImpurityType	impurityType	Impurity measure to use.
float	minChildWeight	Minimum child weight.
float	minImpurityDecrease	Minimumum decrease in impurity required in order for the node to be split.
boolean	normalize	Normalize the leaf outputs so each leaf sums to 1.0.
boolean	printTree	Prints the decision tree.
char	splitChar	Character to split the CSV response on to generate multiple regression dimensions.
TrainTest.TreeType	treeType	Tree type.
boolean	useRandomSplitPoints	Whether to choose split points for features at random.

Fields inherited from interface com.oracle.labs.mlrg.olcut.config.Options

header

Constructor Summary

Constructors

Constructor	Description
RegressionTreeOptions()

Method Summary

Modifier and Type	Method	Description
String	getOptionsDescription()

Methods inherited from class java.lang.Object

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

Field Details

general

public DataOptions general

The data loading options.

splitChar

@Option(longName="csv-response-split-char",
        usage="Character to split the CSV response on to generate multiple regression dimensions. Defaults to \':\'.")
public char splitChar

Character to split the CSV response on to generate multiple regression dimensions. Defaults to ':'.

depth

@Option(charName='d',
        longName="max-depth",
        usage="Maximum depth in the decision tree.")
public int depth

Maximum depth in the decision tree.

fraction

@Option(charName='e',
        longName="split-fraction",
        usage="Fraction of features in split.")
public float fraction

Fraction of features in split.

minChildWeight

@Option(charName='m',
        longName="min-child-weight",
        usage="Minimum child weight.")
public float minChildWeight

Minimum child weight.

minImpurityDecrease

@Option(charName='p',
        longName="min-impurity-decrease",
        usage="Minimumum decrease in impurity required in order for the node to be split.")
public float minImpurityDecrease

Minimumum decrease in impurity required in order for the node to be split.

useRandomSplitPoints

@Option(charName='r',
        longName="use-random-split-points",
        usage="Whether to choose split points for features at random.")
public boolean useRandomSplitPoints

Whether to choose split points for features at random.

normalize

@Option(charName='n',
        longName="normalize",
        usage="Normalize the leaf outputs so each leaf sums to 1.0.")
public boolean normalize

Normalize the leaf outputs so each leaf sums to 1.0.

impurityType

@Option(charName='i',
        longName="impurity",
        usage="Impurity measure to use. Defaults to MSE.")
public TrainTest.ImpurityType impurityType

Impurity measure to use. Defaults to MSE.

treeType

@Option(charName='t',
        longName="tree-type",
        usage="Tree type.")
public TrainTest.TreeType treeType

Tree type.

printTree

@Option(longName="print-tree",
        usage="Prints the decision tree.")
public boolean printTree

Prints the decision tree.

Constructor Details

RegressionTreeOptions

public RegressionTreeOptions()

Method Details

getOptionsDescription

public String getOptionsDescription()

Specified by:

getOptionsDescription in interface com.oracle.labs.mlrg.olcut.config.Options