Package weka.attributeSelection
Class LatentSemanticAnalysis
java.lang.Object
weka.attributeSelection.ASEvaluation
weka.attributeSelection.UnsupervisedAttributeEvaluator
weka.attributeSelection.LatentSemanticAnalysis
- All Implemented Interfaces:
Serializable
,AttributeEvaluator
,AttributeTransformer
,CapabilitiesHandler
,OptionHandler
,RevisionHandler
public class LatentSemanticAnalysis
extends UnsupervisedAttributeEvaluator
implements AttributeTransformer, OptionHandler
Performs latent semantic analysis and transformation of the data.
Use in conjunction with a Ranker search. A low-rank approximation
of the full data is found by specifying the number of singular values
to use. The dataset may be transformed to give the relation of either
the attributes or the instances (default) to the concept space created
by the transformation.
Valid options are:
-N Normalize input data.
-R Rank approximation used in LSA. May be actual number of LSA attributes to include (if greater than 1) or a proportion of total singular values to account for (if between 0 and 1). A value less than or equal to zero means use all latent variables. (default = 0.95)
-A Maximum number of attributes to include in transformed attribute names. (-1 = include all)
- Version:
- $Revision: 11821 $
- Author:
- Amri Napolitano
- See Also:
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionvoid
buildEvaluator
(Instances data) Initializes the singular values/vectors and performs the analysisconvertInstance
(Instance instance) Transform an instance in original (unnormalized) formatdouble
evaluateAttribute
(int att) Evaluates the merit of a transformed attribute.Returns the capabilities of this evaluator.int
Gets maximum number of attributes to include in transformed attribute names.boolean
Gets whether or not input data is to be normalizedString[]
Gets the current settings of LatentSemanticAnalysisdouble
getRank()
Gets the desired matrix rank (or coverage proportion) for feature-space reductionReturns the revision string.Returns a string describing this attribute transformerReturns an enumeration describing the available options.static void
Main method for testing this classReturns the tip text for this propertyReturns the tip text for this propertyReturns the tip text for this propertyvoid
setMaximumAttributeNames
(int newMaxAttributes) Sets maximum number of attributes to include in transformed attribute names.void
setNormalize
(boolean newNormalize) Set whether input data will be normalized.void
setOptions
(String[] options) Parses a given list of options.void
setRank
(double newRank) Sets the desired matrix rank (or coverage proportion) for feature-space reductiontoString()
Returns a description of this attribute transformertransformedData
(Instances data) Transform the supplied data set (assumed to be the same format as the training data)Returns just the header for the transformed data (ie.Methods inherited from class weka.attributeSelection.ASEvaluation
clean, forName, makeCopies, postProcess
-
Constructor Details
-
LatentSemanticAnalysis
public LatentSemanticAnalysis()
-
-
Method Details
-
globalInfo
Returns a string describing this attribute transformer- Returns:
- a description of the evaluator suitable for displaying in the explorer/experimenter gui
-
listOptions
Returns an enumeration describing the available options.- Specified by:
listOptions
in interfaceOptionHandler
- Returns:
- an enumeration of all the available options.
-
setOptions
Parses a given list of options. Valid options are:-N Normalize input data.
-R Rank approximation used in LSA. May be actual number of LSA attributes to include (if greater than 1) or a proportion of total singular values to account for (if between 0 and 1). A value less than or equal to zero means use all latent variables. (default = 0.95)
-A Maximum number of attributes to include in transformed attribute names. (-1 = include all)
- Specified by:
setOptions
in interfaceOptionHandler
- Parameters:
options
- the list of options as an array of strings- Throws:
Exception
- if an option is not supported
-
normalizeTipText
Returns the tip text for this property- Returns:
- tip text for this property suitable for displaying in the explorer/experimenter gui
-
setNormalize
public void setNormalize(boolean newNormalize) Set whether input data will be normalized.- Parameters:
newNormalize
- true if input data is to be normalized
-
getNormalize
public boolean getNormalize()Gets whether or not input data is to be normalized- Returns:
- true if input data is to be normalized
-
rankTipText
Returns the tip text for this property- Returns:
- tip text for this property suitable for displaying in the explorer/experimenter gui
-
setRank
public void setRank(double newRank) Sets the desired matrix rank (or coverage proportion) for feature-space reduction- Parameters:
newRank
- the desired rank (or coverage) for feature-space reduction
-
getRank
public double getRank()Gets the desired matrix rank (or coverage proportion) for feature-space reduction- Returns:
- the rank (or coverage) for feature-space reduction
-
maximumAttributeNamesTipText
Returns the tip text for this property- Returns:
- tip text for this property suitable for displaying in the explorer/experimenter gui
-
setMaximumAttributeNames
public void setMaximumAttributeNames(int newMaxAttributes) Sets maximum number of attributes to include in transformed attribute names.- Parameters:
newMaxAttributes
- the maximum number of attributes
-
getMaximumAttributeNames
public int getMaximumAttributeNames()Gets maximum number of attributes to include in transformed attribute names.- Returns:
- the maximum number of attributes
-
getOptions
Gets the current settings of LatentSemanticAnalysis- Specified by:
getOptions
in interfaceOptionHandler
- Returns:
- an array of strings suitable for passing to setOptions()
-
getCapabilities
Returns the capabilities of this evaluator.- Specified by:
getCapabilities
in interfaceCapabilitiesHandler
- Overrides:
getCapabilities
in classASEvaluation
- Returns:
- the capabilities of this evaluator
- See Also:
-
buildEvaluator
Initializes the singular values/vectors and performs the analysis- Specified by:
buildEvaluator
in classASEvaluation
- Parameters:
data
- the instances to analyse/transform- Throws:
Exception
- if analysis fails
-
transformedHeader
Returns just the header for the transformed data (ie. an empty set of instances. This is so that AttributeSelection can determine the structure of the transformed data without actually having to get all the transformed data through getTransformedData().- Specified by:
transformedHeader
in interfaceAttributeTransformer
- Returns:
- the header of the transformed data.
- Throws:
Exception
- if the header of the transformed data can't be determined.
-
transformedData
Transform the supplied data set (assumed to be the same format as the training data)- Specified by:
transformedData
in interfaceAttributeTransformer
- Returns:
- the transformed training data
- Throws:
Exception
- if transformed data can't be returned
-
evaluateAttribute
Evaluates the merit of a transformed attribute. This is defined to be the square of the singular value for the latent variable corresponding to the transformed attribute.- Specified by:
evaluateAttribute
in interfaceAttributeEvaluator
- Parameters:
att
- the attribute to be evaluated- Returns:
- the merit of a transformed attribute
- Throws:
Exception
- if attribute can't be evaluated
-
convertInstance
Transform an instance in original (unnormalized) format- Specified by:
convertInstance
in interfaceAttributeTransformer
- Parameters:
instance
- an instance in the original (unnormalized) format- Returns:
- a transformed instance
- Throws:
Exception
- if instance can't be transformed
-
toString
Returns a description of this attribute transformer -
getRevision
Returns the revision string.- Specified by:
getRevision
in interfaceRevisionHandler
- Overrides:
getRevision
in classASEvaluation
- Returns:
- the revision
-
main
Main method for testing this class- Parameters:
argv
- should contain the command line arguments to the evaluator/transformer (see AttributeSelection)
-