weka.classifiers.misc

Class IsolationForest

java.lang.Object

weka.classifiers.AbstractClassifier

weka.classifiers.RandomizableClassifier

weka.classifiers.misc.IsolationForest

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, weka.classifiers.Classifier, weka.core.BatchPredictor, weka.core.CapabilitiesHandler, weka.core.CapabilitiesIgnorer, weka.core.CommandlineRunnable, weka.core.OptionHandler, weka.core.Randomizable, weka.core.RevisionHandler, weka.core.TechnicalInformationHandler

public class IsolationForest
extends weka.classifiers.RandomizableClassifier
implements weka.core.TechnicalInformationHandler, java.io.Serializable

Implements the isolation forest method for anomaly detection.

Note that this classifier is designed for anomaly detection, it is not designed for solving two-class or multi-class classification problems!

The data is expected to have have a class attribute with one or two values, which is ignored at training time. The distributionForInstance() method returns (1 - anomaly score) as the first element in the distribution, the second element (in the case of two classes) is the anomaly score.

To evaluate performance of this method for a dataset where anomalies are known, simply code the anomalies using the class attribute: normal cases should correspond to the first value of the class attribute, anomalies to the second one.

For more information, see:

Fei Tony Liu, Kai Ming Ting, Zhi-Hua Zhou: Isolation Forest. In: ICDM, 413-422, 2008.

BibTeX:

 @inproceedings{Liu2008,
    author = {Fei Tony Liu and Kai Ming Ting and Zhi-Hua Zhou},
    booktitle = {ICDM},
    pages = {413-422},
    publisher = {IEEE Computer Society},
    title = {Isolation Forest},
    year = {2008}
 }
 

Valid options are:

 -I <number of trees>
  The number of trees in the forest (default 100).

 -N <the size of the subsample for each tree>
  The subsample size for each tree (default 256).

 -S <num>
  Random number seed.
  (default 1)

 -output-debug-info
  If set, classifier is run in debug mode and
  may output additional info to the console

 -do-not-check-capabilities
  If set, classifier capabilities are not checked before classifier is built
  (use with caution).

 -num-decimal-places
  The number of decimal places for the output of numbers in the model (default 2).

Version:

$Revision: 12345 $

Author:

Eibe Frank (eibe@cs.waikato.ac.nz)

See Also:

Serialized Form

Field Summary

Fields inherited from class weka.classifiers.AbstractClassifier

BATCH_SIZE_DEFAULT, NUM_DECIMAL_PLACES_DEFAULT

Constructor Summary

Constructors

Constructor and Description
IsolationForest()

Method Summary

Modifier and Type	Method and Description
void	buildClassifier(weka.core.Instances data) Builds the forest.
static double	c(double n) Returns the average path length of an unsuccessful search.
double[]	distributionForInstance(weka.core.Instance inst) Returns distribution of scores.
weka.core.Capabilities	getCapabilities() Returns the Capabilities of this filter.
int	getNumTrees() Get the value of numTrees.
java.lang.String[]	getOptions() Gets options from this classifier.
int	getSubsampleSize() Get the value of subsampleSize.
weka.core.TechnicalInformation	getTechnicalInformation() Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.
java.lang.String	globalInfo() Returns a string describing this filter
java.util.Enumeration<weka.core.Option>	listOptions() Lists the command-line options for this classifier.
static void	main(java.lang.String[] args) Main method for this class.
java.lang.String	numTreesTipText() Returns the tip text for this property
void	setNumTrees(int k) Set the value of numTrees.
void	setOptions(java.lang.String[] options) Parses a given list of options.
void	setSubsampleSize(int n) Set the value of subsampleSize.
java.lang.String	subsampleSizeTipText() Returns the tip text for this property
java.lang.String	toString() Returns brief description of the classifier.

Methods inherited from class weka.classifiers.RandomizableClassifier

getSeed, seedTipText, setSeed

Methods inherited from class weka.classifiers.AbstractClassifier

batchSizeTipText, classifyInstance, debugTipText, distributionsForInstances, doNotCheckCapabilitiesTipText, forName, getBatchSize, getDebug, getDoNotCheckCapabilities, getNumDecimalPlaces, getRevision, implementsMoreEfficientBatchPrediction, makeCopies, makeCopy, numDecimalPlacesTipText, postExecution, preExecution, run, runClassifier, setBatchSize, setDebug, setDoNotCheckCapabilities, setNumDecimalPlaces

Methods inherited from class java.lang.Object

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

Methods inherited from interface weka.core.OptionHandler

makeCopy

Constructor Detail

IsolationForest

public IsolationForest()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing this filter

getTechnicalInformation

public weka.core.TechnicalInformation getTechnicalInformation()

Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.

Specified by:

getTechnicalInformation in interface weka.core.TechnicalInformationHandler

Returns:

the technical information about this class

getCapabilities

public weka.core.Capabilities getCapabilities()

Returns the Capabilities of this filter.

Specified by:

getCapabilities in interface weka.classifiers.Classifier

Specified by:

getCapabilities in interface weka.core.CapabilitiesHandler

Overrides:

getCapabilities in class weka.classifiers.AbstractClassifier

toString

public java.lang.String toString()

Returns brief description of the classifier.

Overrides:

toString in class java.lang.Object

numTreesTipText

public java.lang.String numTreesTipText()

Returns the tip text for this property

Returns:

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

getNumTrees

public int getNumTrees()

Get the value of numTrees.

Returns:

Value of numTrees.

setNumTrees

public void setNumTrees(int k)

Set the value of numTrees.

Parameters:

k - value to assign to numTrees.

subsampleSizeTipText

public java.lang.String subsampleSizeTipText()

Returns the tip text for this property

Returns:

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

getSubsampleSize

public int getSubsampleSize()

Get the value of subsampleSize.

Returns:

Value of subsampleSize.

setSubsampleSize

public void setSubsampleSize(int n)

Set the value of subsampleSize.

Parameters:

n - value to assign to subsampleSize.

listOptions

public java.util.Enumeration<weka.core.Option> listOptions()

Lists the command-line options for this classifier.

Specified by:

listOptions in interface weka.core.OptionHandler

Overrides:

listOptions in class weka.classifiers.RandomizableClassifier

Returns:

an enumeration over all possible options

getOptions

public java.lang.String[] getOptions()

Gets options from this classifier.

Specified by:

getOptions in interface weka.core.OptionHandler

Overrides:

getOptions in class weka.classifiers.RandomizableClassifier

Returns:

the options for the current setup

setOptions

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

Parses a given list of options.

Valid options are:

 -I <number of trees>
  The number of trees in the forest (default 100).

 -N <the size of the subsample for each tree>
  The subsample size for each tree (default 256).

 -S <num>
  Random number seed.
  (default 1)

 -output-debug-info
  If set, classifier is run in debug mode and
  may output additional info to the console

 -do-not-check-capabilities
  If set, classifier capabilities are not checked before classifier is built
  (use with caution).

 -num-decimal-places
  The number of decimal places for the output of numbers in the model (default 2).

Specified by:

setOptions in interface weka.core.OptionHandler

Overrides:

setOptions in class weka.classifiers.RandomizableClassifier

Parameters:

options - the list of options as an array of strings

Throws:

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

buildClassifier

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

Builds the forest.

Specified by:

buildClassifier in interface weka.classifiers.Classifier

Throws:

java.lang.Exception

c

public static double c(double n)

Returns the average path length of an unsuccessful search. Returns 0 if argument is less than or equal to 1

distributionForInstance

public double[] distributionForInstance(weka.core.Instance inst)

Returns distribution of scores.

Specified by:

distributionForInstance in interface weka.classifiers.Classifier

Overrides:

distributionForInstance in class weka.classifiers.AbstractClassifier

main

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

Main method for this class.