weka.filters.unsupervised.attribute
Class AddNoise

java.lang.Object
  extended byweka.filters.Filter
      extended byweka.filters.unsupervised.attribute.AddNoise
All Implemented Interfaces:
OptionHandler, java.io.Serializable, UnsupervisedFilter

public class AddNoise
extends Filter
implements UnsupervisedFilter, OptionHandler

Introduces noise data a random subsample of the dataset by changing a given attribute (attribute must be nominal) Valid options are:

-C col
Index of the attribute to be changed. (default last)

-M
flag: missing values are treated as an extra value

-P num
Percentage of noise to be introduced to the data (default 10).

-S seed
Random number seed for choosing the data to be changed

and for choosing the value it is changed to (default 1).

Version:
$Revision: 1.2 $
Author:
Gabi Schmidberger (gabi@cs.waikato.ac.nz)
See Also:
Serialized Form

Field Summary
private  SingleIndex m_AttIndex
          The attribute's index setting.
private  int m_Percent
          The subsample size, percent of original set, default 10%
private  int m_RandomSeed
          The random number generator seed
private  boolean m_UseMissing
          Flag if missing values are taken as value.
 
Fields inherited from class weka.filters.Filter
m_NewBatch
 
Constructor Summary
AddNoise()
           
 
Method Summary
 void addNoise(Instances instances, int seed, int percent, int attIndex, boolean useMissing)
          add noise to the dataset a given percentage of the instances are changed in the way, that a set of instances are randomly selected using seed.
 java.lang.String attIndexSetTipText()
          Returns the tip text for this property
 boolean batchFinished()
          Signify that this batch of input to the filter is finished.
private  void changeValueRandomly(java.util.Random r, int numOfValues, int indexOfAtt, Instance instance, boolean useMissing)
          method to set a new value
 java.lang.String getAttributeIndex()
          Get the index of the attribute used.
 java.lang.String[] getOptions()
          Gets the current settings of the filter.
 int getPercent()
          Gets the size of noise data as a percentage of the original set.
 int getRandomSeed()
          Gets the random number seed.
 boolean getUseMissing()
          Gets the flag if missing values are treated as extra values.
 java.lang.String globalInfo()
          Returns a string describing this filter
 boolean input(Instance instance)
          Input an instance for filtering.
 java.util.Enumeration listOptions()
          Returns an enumeration describing the available options
static void main(java.lang.String[] argv)
          Main method for testing this class.
 java.lang.String percentTipText()
          Returns the tip text for this property
 java.lang.String randomSeedTipText()
          Returns the tip text for this property
 void setAttributeIndex(java.lang.String attIndex)
          Sets index of the attribute used.
 boolean setInputFormat(Instances instanceInfo)
          Sets the format of the input instances.
 void setOptions(java.lang.String[] options)
          Parses a list of options for this object.
 void setPercent(int newPercent)
          Sets the size of noise data, as a percentage of the original set.
 void setRandomSeed(int newSeed)
          Sets the random number seed.
 void setUseMissing(boolean newUseMissing)
          Sets the flag if missing values are treated as extra values.
 java.lang.String useMissingTipText()
          Returns the tip text for this property
 
Methods inherited from class weka.filters.Filter
batchFilterFile, bufferInput, copyStringValues, copyStringValues, filterFile, flushInput, getInputFormat, getInputStringIndex, getOutputFormat, getOutputStringIndex, getStringIndices, inputFormat, inputFormatPeek, isOutputFormatDefined, numPendingOutput, output, outputFormat, outputFormatPeek, outputPeek, push, resetQueue, setOutputFormat, useFilter
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

m_AttIndex

private SingleIndex m_AttIndex
The attribute's index setting.


m_UseMissing

private boolean m_UseMissing
Flag if missing values are taken as value.


m_Percent

private int m_Percent
The subsample size, percent of original set, default 10%


m_RandomSeed

private int m_RandomSeed
The random number generator seed

Constructor Detail

AddNoise

public AddNoise()
Method Detail

globalInfo

public java.lang.String globalInfo()
Returns a string describing this filter

Returns:
a description of the filter suitable for displaying in the explorer/experimenter gui

listOptions

public java.util.Enumeration listOptions()
Returns an enumeration describing the available options

Specified by:
listOptions in interface OptionHandler
Returns:
an enumeration of all the available options

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception
Parses a list of options for this object. Valid options are:

-C col
Index of the attribute to be changed. (default last)

-M
missing values are treated as an extra value

-P num
Specify the percentage of noise introduced to the data (default 10).

-S num
Specify the random number seed (default 1).

Specified by:
setOptions in interface OptionHandler
Parameters:
options - the list of options as an array of strings
Throws:
java.lang.Exception - if an option is not supported

getOptions

public java.lang.String[] getOptions()
Gets the current settings of the filter.

Specified by:
getOptions in interface OptionHandler
Returns:
an array of strings suitable for passing to setOptions

useMissingTipText

public java.lang.String useMissingTipText()
Returns the tip text for this property

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

getUseMissing

public boolean getUseMissing()
Gets the flag if missing values are treated as extra values.

Returns:
the flag missing values.

setUseMissing

public void setUseMissing(boolean newUseMissing)
Sets the flag if missing values are treated as extra values.

Parameters:
newUseMissing - the new flag value.

randomSeedTipText

public java.lang.String randomSeedTipText()
Returns the tip text for this property

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

getRandomSeed

public int getRandomSeed()
Gets the random number seed.

Returns:
the random number seed.

setRandomSeed

public void setRandomSeed(int newSeed)
Sets the random number seed.

Parameters:
newSeed - the new random number seed.

percentTipText

public java.lang.String percentTipText()
Returns the tip text for this property

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

getPercent

public int getPercent()
Gets the size of noise data as a percentage of the original set.

Returns:
the noise data size

setPercent

public void setPercent(int newPercent)
Sets the size of noise data, as a percentage of the original set.

Parameters:
newPercent - the subsample set size, between 0 and 100.

attIndexSetTipText

public java.lang.String attIndexSetTipText()
Returns the tip text for this property

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

getAttributeIndex

public java.lang.String getAttributeIndex()
Get the index of the attribute used.

Returns:
the index of the attribute

setAttributeIndex

public void setAttributeIndex(java.lang.String attIndex)
Sets index of the attribute used.


setInputFormat

public boolean setInputFormat(Instances instanceInfo)
                       throws java.lang.Exception
Sets the format of the input instances.

Overrides:
setInputFormat in class Filter
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:
java.lang.Exception - if the input format can't be set successfully

input

public boolean input(Instance instance)
              throws java.lang.Exception
Input an instance for filtering.

Overrides:
input in class Filter
Parameters:
instance - the input instance
Returns:
true if the filtered instance may now be collected with output().
Throws:
java.lang.Exception - if the input format was not set

batchFinished

public boolean batchFinished()
                      throws java.lang.Exception
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:
batchFinished in class Filter
Returns:
true if there are instances pending output
Throws:
java.lang.Exception - if no input structure has been defined

addNoise

public void addNoise(Instances instances,
                     int seed,
                     int percent,
                     int attIndex,
                     boolean useMissing)
add noise to the dataset a given percentage of the instances are changed in the way, that a set of instances are randomly selected using seed. The attribute given by its index is changed from its current value to one of the other possibly ones, also randomly. This is done with leaving the apportion the same. if m_UseMissing is true, missing value is used as a value of its own

Parameters:
instances - is the dataset
seed - used for random function
percent - percentage of instances that are changed
attIndex - index of the attribute changed

changeValueRandomly

private void changeValueRandomly(java.util.Random r,
                                 int numOfValues,
                                 int indexOfAtt,
                                 Instance instance,
                                 boolean useMissing)
method to set a new value

Parameters:
r - random function
numOfValues -
instance -
useMissing -

main

public static void main(java.lang.String[] argv)
Main method for testing this class.

Parameters:
argv - should contain arguments to the filter: use -h for help