All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Class weka.classifiers.AdditiveRegression

java.lang.Object
    |
    +----weka.classifiers.Classifier
            |
            +----weka.classifiers.AdditiveRegression

public class AdditiveRegression

extends Classifier

implements OptionHandler, AdditionalMeasureProducer

 Analysing:  Root_relative_squared_error
 Datasets:   36
 Resultsets: 2
 Confidence: 0.05 (two tailed)
 Date:       10/13/00 10:00 AM


 Dataset                   (1) m5.M5Prim | (2) AdditiveRegression -S 0.7 \
                                         |    -B weka.classifiers.m5.M5Prime 
                          ----------------------------
 auto93.names              (10)    54.4  |    49.41 * 
 autoHorse.names           (10)    32.76 |    26.34 * 
 autoMpg.names             (10)    35.32 |    34.84 * 
 autoPrice.names           (10)    40.01 |    36.57 * 
 baskball                  (10)    79.46 |    79.85   
 bodyfat.names             (10)    10.38 |    11.41 v 
 bolts                     (10)    19.29 |    12.61 * 
 breastTumor               (10)    96.95 |    96.23 * 
 cholesterol               (10)   101.03 |    98.88 * 
 cleveland                 (10)    71.29 |    70.87 * 
 cloud                     (10)    38.82 |    39.18   
 cpu                       (10)    22.26 |    14.74 * 
 detroit                   (10)   228.16 |    83.7  * 
 echoMonths                (10)    71.52 |    69.15 * 
 elusage                   (10)    48.94 |    49.03   
 fishcatch                 (10)    16.61 |    15.36 * 
 fruitfly                  (10)   100    |   100    * 
 gascons                   (10)    18.72 |    14.26 * 
 housing                   (10)    38.62 |    36.53 * 
 hungarian                 (10)    74.67 |    72.19 * 
 longley                   (10)    31.23 |    28.26 * 
 lowbwt                    (10)    62.26 |    61.48 * 
 mbagrade                  (10)    89.2  |    89.2    
 meta                      (10)   163.15 |   188.28 v 
 pbc                       (10)    81.35 |    79.4  * 
 pharynx                   (10)   105.41 |   105.03   
 pollution                 (10)    72.24 |    68.16 * 
 pwLinear                  (10)    32.42 |    33.33 v 
 quake                     (10)   100.21 |    99.93   
 schlvote                  (10)    92.41 |    98.23 v 
 sensory                   (10)    88.03 |    87.94   
 servo                     (10)    37.07 |    35.5  * 
 sleep                     (10)    70.17 |    71.65   
 strike                    (10)    84.98 |    83.96 * 
 veteran                   (10)    90.61 |    88.77 * 
 vineyard                  (10)    79.41 |    73.95 * 
                        ----------------------------
                              (v| |*) |   (4|8|24) 

 

For more information see:

Friedman, J.H. (1999). Stochastic Gradient Boosting. Technical Report Stanford University. http://www-stat.stanford.edu/~jhf/ftp/stobst.ps.

Valid options from the command line are:

-B classifierstring
Classifierstring should contain the full class name of a classifier followed by options to the classifier. (required).

-S shrinkage rate
Smaller values help prevent overfitting and have a smoothing effect (but increase learning time). (default = 1.0, ie no shrinkage).

-M max models
Set the maximum number of models to generate. Values <= 0 indicate no maximum, ie keep going until the reduction in error threshold is reached. (default = -1).

-D
Debugging output.

Version:

$Revision: 1.6 $

Author:

Mark Hall (mhall@cs.waikato.ac.nz)

AdditiveRegression()

Default constructor specifying DecisionStump as the classifier

AdditiveRegression(Classifier)

Constructor which takes base classifier as argument.

buildClassifier(Instances)

Build the classifier on the supplied data

classifierTipText()

Returns the tip text for this property

classifyInstance(Instance)

Classify an instance.

debugTipText()

Returns the tip text for this property

enumerateMeasures()

Returns an enumeration of the additional measure names

getClassifier()

Gets the classifier used.

getDebug()

Gets whether debugging has been turned on

getMaxModels()

Get the max number of models to generate

getMeasure(String)

Returns the value of the named measure

getOptions()

Gets the current settings of the Classifier.

getShrinkage()

Get the shrinkage rate.

globalInfo()

Returns a string describing this attribute evaluator

listOptions()

Returns an enumeration describing the available options

main(String[])

Main method for testing this class.

maxModelsTipText()

Returns the tip text for this property

measureNumIterations()

return the number of iterations (base classifiers) completed

setClassifier(Classifier)

Sets the classifier

setDebug(boolean)

Set whether debugging output is produced.

setMaxModels(int)

Set the maximum number of models to generate

setOptions(String[])

Parses a given list of options.

setShrinkage(double)

Set the shrinkage parameter

shrinkageTipText()

Returns the tip text for this property

toString()

Returns textual description of the classifier.

public AdditiveRegression()

          Default constructor specifying DecisionStump as the classifier

public AdditiveRegression(Classifier classifier)

          Constructor which takes base classifier as argument.

Parameters:

classifier - the base classifier to use

public java.lang.String globalInfo()

          Returns a string describing this attribute evaluator

Returns:

a description of the evaluator suitable for displaying in the explorer/experimenter gui

public java.util.Enumeration listOptions()

          Returns an enumeration describing the available options

Returns:

an enumeration of all the available options

public void setOptions(java.lang.String options[]) throws java.lang.Exception

          Parses a given list of options. Valid options are:

-B classifierstring
Classifierstring should contain the full class name of a classifier followed by options to the classifier. (required).

-S shrinkage rate
Smaller values help prevent overfitting and have a smoothing effect (but increase learning time). (default = 1.0, ie. no shrinkage).

-D
Debugging output.

-M max models
Set the maximum number of models to generate. Values <= 0 indicate no maximum, ie keep going until the reduction in error threshold is reached. (default = -1).

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

public java.lang.String[] getOptions()

          Gets the current settings of the Classifier.

Returns:

an array of strings suitable for passing to setOptions

public java.lang.String debugTipText()

          Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

public void setDebug(boolean d)

          Set whether debugging output is produced.

Parameters:

d - true if debugging output is to be produced

public boolean getDebug()

          Gets whether debugging has been turned on

Returns:

true if debugging has been turned on

public java.lang.String classifierTipText()

          Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

public void setClassifier(Classifier classifier)

          Sets the classifier

Parameters:

classifier - the classifier with all options set.

public Classifier getClassifier()

          Gets the classifier used.

Returns:

the classifier

public java.lang.String maxModelsTipText()

          Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

public void setMaxModels(int maxM)

          Set the maximum number of models to generate

Parameters:

maxM - the maximum number of models

public int getMaxModels()

          Get the max number of models to generate

Returns:

the max number of models to generate

public java.lang.String shrinkageTipText()

          Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

public void setShrinkage(double l)

          Set the shrinkage parameter

Parameters:

l - the shrinkage rate.

public double getShrinkage()

          Get the shrinkage rate.

Returns:

the value of the learning rate

public void buildClassifier(Instances data) throws java.lang.Exception

          Build the classifier on the supplied data

Parameters:

data - the training data

Throws:

java.lang.Exception - if the classifier could not be built successfully

Overrides:

buildClassifier in class Classifier

public double classifyInstance(Instance inst) throws java.lang.Exception

          Classify an instance.

Parameters:

inst - the instance to predict

Returns:

a prediction for the instance

Throws:

java.lang.Exception - if an error occurs

Overrides:

classifyInstance in class Classifier

public java.util.Enumeration enumerateMeasures()

          Returns an enumeration of the additional measure names

Returns:

an enumeration of the measure names

public double getMeasure(java.lang.String additionalMeasureName)

          Returns the value of the named measure

Parameters:

measureName - the name of the measure to query for its value

Returns:

the value of the named measure

Throws:

java.lang.IllegalArgumentException - if the named measure is not supported

public double measureNumIterations()

          return the number of iterations (base classifiers) completed

Returns:

the number of iterations (same as number of base classifier models)

public java.lang.String toString()

          Returns textual description of the classifier.

Returns:

a description of the classifier as a string

Overrides:

toString in class java.lang.Object

public static void main(java.lang.String argv[])

          Main method for testing this class.

Parameters:

argv - should contain the following arguments: -t training file [-T test file] [-c class index]

All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home