Class MultiInstanceToPropositional
java.lang.Object
weka.filters.Filter
weka.filters.unsupervised.attribute.MultiInstanceToPropositional
- All Implemented Interfaces:
Serializable,CapabilitiesHandler,MultiInstanceCapabilitiesHandler,OptionHandler,RevisionHandler,UnsupervisedFilter
public class MultiInstanceToPropositional
extends Filter
implements OptionHandler, UnsupervisedFilter, MultiInstanceCapabilitiesHandler
Converts the multi-instance dataset into single instance dataset so that the Nominalize, Standardize and other type of filters or transformation can be applied to these data for the further preprocessing.
Note: the first attribute of the converted dataset is a nominal attribute and refers to the bagId. Valid options are:
Note: the first attribute of the converted dataset is a nominal attribute and refers to the bagId. Valid options are:
-A <num> The type of weight setting for each prop. instance: 0.weight = original single bag weight /Total number of prop. instance in the corresponding bag; 1.weight = 1.0; 2.weight = 1.0/Total number of prop. instance in the corresponding bag; 3. weight = Total number of prop. instance / (Total number of bags * Total number of prop. instance in the corresponding bag). (default:0)
- Version:
- $Revision: 9141 $
- Author:
- Lin Dong (ld21@cs.waikato.ac.nz)
- See Also:
-
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final Tag[]weight methodsstatic final intweight method: 1.0static final intweight method: 1.0 / Total # of prop.static final intweight method: Total # of prop.static final intweight method: keep the weight to be the same as the original value -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionbooleanSignify that this batch of input to the filter is finished.Returns the Capabilities of this filter.Returns the capabilities of this multi-instance filter for the relational data (i.e., the bags).String[]Gets the current settings of the classifier.Returns the revision string.Returns the current weighting method for instances.Returns a string describing this filterbooleanInput an instance for filtering.Returns an enumeration describing the available optionsstatic voidMain method for running this filter.booleansetInputFormat(Instances instanceInfo) Sets the format of the input instances.voidsetOptions(String[] options) Parses a given list of options.voidsetWeightMethod(SelectedTag method) The new method for weighting the instances.Returns the tip text for this propertyMethods inherited from class weka.filters.Filter
batchFilterFile, filterFile, getCapabilities, getOutputFormat, isFirstBatchDone, isNewBatch, isOutputFormatDefined, makeCopies, makeCopy, numPendingOutput, output, outputPeek, toString, useFilter, wekaStaticWrapper
-
Field Details
-
WEIGHTMETHOD_ORIGINAL
public static final int WEIGHTMETHOD_ORIGINALweight method: keep the weight to be the same as the original value- See Also:
-
WEIGHTMETHOD_1
public static final int WEIGHTMETHOD_1weight method: 1.0- See Also:
-
WEIGHTMETHOD_INVERSE1
public static final int WEIGHTMETHOD_INVERSE1weight method: 1.0 / Total # of prop. instance in the corresp. bag- See Also:
-
WEIGHTMETHOD_INVERSE2
public static final int WEIGHTMETHOD_INVERSE2weight method: Total # of prop. instance / (Total # of bags * Total # of prop. instance in the corresp. bag)- See Also:
-
TAGS_WEIGHTMETHOD
weight methods
-
-
Constructor Details
-
MultiInstanceToPropositional
public MultiInstanceToPropositional()
-
-
Method Details
-
listOptions
Returns an enumeration describing the available options- Specified by:
listOptionsin interfaceOptionHandler- Returns:
- an enumeration of all the available options
-
setOptions
Parses a given list of options. Valid options are:-A <num> The type of weight setting for each prop. instance: 0.weight = original single bag weight /Total number of prop. instance in the corresponding bag; 1.weight = 1.0; 2.weight = 1.0/Total number of prop. instance in the corresponding bag; 3. weight = Total number of prop. instance / (Total number of bags * Total number of prop. instance in the corresponding bag). (default:0)
- Specified by:
setOptionsin interfaceOptionHandler- Parameters:
options- the list of options as an array of strings- Throws:
Exception- if an option is not supported
-
getOptions
Gets the current settings of the classifier.- Specified by:
getOptionsin interfaceOptionHandler- Returns:
- an array of strings suitable for passing to setOptions
-
weightMethodTipText
Returns the tip text for this property- Returns:
- tip text for this property suitable for displaying in the explorer/experimenter gui
-
setWeightMethod
The new method for weighting the instances.- Parameters:
method- the new method
-
getWeightMethod
Returns the current weighting method for instances.- Returns:
- the current weight method
-
globalInfo
Returns a string describing this filter- Returns:
- a description of the filter suitable for displaying in the explorer/experimenter gui
-
getCapabilities
Returns the Capabilities of this filter.- Specified by:
getCapabilitiesin interfaceCapabilitiesHandler- Overrides:
getCapabilitiesin classFilter- Returns:
- the capabilities of this object
- See Also:
-
getMultiInstanceCapabilities
Returns the capabilities of this multi-instance filter for the relational data (i.e., the bags).- Specified by:
getMultiInstanceCapabilitiesin interfaceMultiInstanceCapabilitiesHandler- Returns:
- the capabilities of this object
- See Also:
-
setInputFormat
Sets the format of the input instances.- Overrides:
setInputFormatin classFilter- Parameters:
instanceInfo- an Instances object containing the input instance structure (any instances contained in the object are ignored - only the structure is required).- Returns:
- true if the outputFormat may be collected immediately
- Throws:
Exception- if the input format can't be set successfully
-
input
Input an instance for filtering. Filter requires all training instances be read before producing output.- Overrides:
inputin classFilter- Parameters:
instance- the input instance- Returns:
- true if the filtered instance may now be collected with output().
- Throws:
IllegalStateException- if no input format has been set.
-
batchFinished
public boolean batchFinished()Signify that this batch of input to the filter is finished. If the filter requires all instances prior to filtering, output() may now be called to retrieve the filtered instances.- Overrides:
batchFinishedin classFilter- Returns:
- true if there are instances pending output
- Throws:
IllegalStateException- if no input structure has been defined
-
getRevision
Returns the revision string.- Specified by:
getRevisionin interfaceRevisionHandler- Overrides:
getRevisionin classFilter- Returns:
- the revision
-
main
Main method for running this filter.- Parameters:
args- should contain arguments to the filter: use -h for help
-