Package weka.experiment

Class CrossValidationResultProducer

java.lang.Object
weka.experiment.CrossValidationResultProducer
All Implemented Interfaces:
Serializable, AdditionalMeasureProducer, OptionHandler, RevisionHandler, ResultProducer
Direct Known Subclasses:
CrossValidationSplitResultProducer
public class CrossValidationResultProducer extends Object implements ResultProducer, OptionHandler, AdditionalMeasureProducer, RevisionHandler
Generates for each run, carries out an n-fold cross-validation, using the set SplitEvaluator to generate some results. If the class attribute is nominal, the dataset is stratified. Results for each fold are generated, so you may wish to use this in addition with an AveragingResultProducer to obtain averages for each run.

Valid options are: 

 -X <number of folds>
  The number of folds to use for the cross-validation.
  (default 10)
 
 -D
 Save raw split evaluator output.
 
 -O <file/directory name/path>
  The filename where raw output will be stored.
  If a directory name is specified then then individual
  outputs will be gzipped, otherwise all output will be
  zipped to the named file. Use in conjuction with -D. (default splitEvalutorOut.zip)
 
 -W <class name>
  The full class name of a SplitEvaluator.
  eg: weka.experiment.ClassifierSplitEvaluator
 
 Options specific to split evaluator weka.experiment.ClassifierSplitEvaluator:
 
 -W <class name>
  The full class name of the classifier.
  eg: weka.classifiers.bayes.NaiveBayes
 
 -C <index>
  The index of the class for which IR statistics
  are to be output. (default 1)
 
 -I <index>
  The index of an attribute to output in the
  results. This attribute should identify an
  instance in order to know which instances are
  in the test set of a cross validation. if 0
  no output (default 0).
 
 -P
  Add target and prediction columns to the result
  for each fold.
 
 Options specific to classifier weka.classifiers.rules.ZeroR:
 
 -D
  If set, classifier is run in debug mode and
  may output additional info to the console
All options after -- will be passed to the split evaluator.
Version:
$Revision: 10203 $
Author:
Len Trigg (trigg@cs.waikato.ac.nz)
See Also:

  • Field Details

    • DATASET_FIELD_NAME

      public static String DATASET_FIELD_NAME
      The name of the key field containing the dataset name

    • RUN_FIELD_NAME

      public static String RUN_FIELD_NAME
      The name of the key field containing the run number

    • FOLD_FIELD_NAME

      public static String FOLD_FIELD_NAME
      The name of the key field containing the fold number

    • TIMESTAMP_FIELD_NAME

      public static String TIMESTAMP_FIELD_NAME
      The name of the result field containing the timestamp

  • Constructor Details

    • CrossValidationResultProducer

      public CrossValidationResultProducer()

  • Method Details

    • globalInfo

      public String globalInfo()
      Returns a string describing this result producer
      Returns:
      a description of the result producer suitable for displaying in the explorer/experimenter gui

    • setInstances

      public void setInstances(Instances instances)
      Sets the dataset that results will be obtained for.
      Specified by:
      setInstances in interface ResultProducer
      Parameters:
      instances - a value of type 'Instances'.

    • setResultListener

      public void setResultListener(ResultListener listener)
      Sets the object to send results of each run to.
      Specified by:
      setResultListener in interface ResultProducer
      Parameters:
      listener - a value of type 'ResultListener'

    • setAdditionalMeasures

      public void setAdditionalMeasures(String[] additionalMeasures)
      Set a list of method names for additional measures to look for in SplitEvaluators. This could contain many measures (of which only a subset may be produceable by the current SplitEvaluator) if an experiment is the type that iterates over a set of properties.
      Specified by:
      setAdditionalMeasures in interface ResultProducer
      Parameters:
      additionalMeasures - an array of measure names, null if none

    • enumerateMeasures

      public Enumeration<String> enumerateMeasures()
      Returns an enumeration of any additional measure names that might be in the SplitEvaluator
      Specified by:
      enumerateMeasures in interface AdditionalMeasureProducer
      Returns:
      an enumeration of the measure names

    • getMeasure

      public double getMeasure(String additionalMeasureName)
      Returns the value of the named measure
      Specified by:
      getMeasure in interface AdditionalMeasureProducer
      Parameters:
      additionalMeasureName - the name of the measure to query for its value
      Returns:
      the value of the named measure
      Throws:
      IllegalArgumentException - if the named measure is not supported

    • getTimestamp

      public static Double getTimestamp()
      Gets a Double representing the current date and time. eg: 1:46pm on 20/5/1999 -> 19990520.1346
      Returns:
      a value of type Double

    • preProcess

      public void preProcess() throws Exception
      Prepare to generate results.
      Specified by:
      preProcess in interface ResultProducer
      Throws:
      Exception - if an error occurs during preprocessing.

    • postProcess

      public void postProcess() throws Exception
      Perform any postprocessing. When this method is called, it indicates that no more requests to generate results for the current experiment will be sent.
      Specified by:
      postProcess in interface ResultProducer
      Throws:
      Exception - if an error occurs

    • doRunKeys

      public void doRunKeys(int run) throws Exception
      Gets the keys for a specified run number. Different run numbers correspond to different randomizations of the data. Keys produced should be sent to the current ResultListener
      Specified by:
      doRunKeys in interface ResultProducer
      Parameters:
      run - the run number to get keys for.
      Throws:
      Exception - if a problem occurs while getting the keys

    • doRun

      public void doRun(int run) throws Exception
      Gets the results for a specified run number. Different run numbers correspond to different randomizations of the data. Results produced should be sent to the current ResultListener
      Specified by:
      doRun in interface ResultProducer
      Parameters:
      run - the run number to get results for.
      Throws:
      Exception - if a problem occurs while getting the results

    • getKeyNames

      public String[] getKeyNames()
      Gets the names of each of the columns produced for a single run. This method should really be static.
      Specified by:
      getKeyNames in interface ResultProducer
      Returns:
      an array containing the name of each column

    • getKeyTypes

      public Object[] getKeyTypes()
      Gets the data types of each of the columns produced for a single run. This method should really be static.
      Specified by:
      getKeyTypes in interface ResultProducer
      Returns:
      an array containing objects of the type of each column. The objects should be Strings, or Doubles.

    • getResultNames

      public String[] getResultNames()
      Gets the names of each of the columns produced for a single run. This method should really be static.
      Specified by:
      getResultNames in interface ResultProducer
      Returns:
      an array containing the name of each column

    • getResultTypes

      public Object[] getResultTypes()
      Gets the data types of each of the columns produced for a single run. This method should really be static.
      Specified by:
      getResultTypes in interface ResultProducer
      Returns:
      an array containing objects of the type of each column. The objects should be Strings, or Doubles.

    • getCompatibilityState

      public String getCompatibilityState()
      Gets a description of the internal settings of the result producer, sufficient for distinguishing a ResultProducer instance from another with different settings (ignoring those settings set through this interface). For example, a cross-validation ResultProducer may have a setting for the number of folds. For a given state, the results produced should be compatible. Typically if a ResultProducer is an OptionHandler, this string will represent the command line arguments required to set the ResultProducer to that state.
      Specified by:
      getCompatibilityState in interface ResultProducer
      Returns:
      the description of the ResultProducer state, or null if no state is defined

    • outputFileTipText

      public String outputFileTipText()
      Returns the tip text for this property
      Returns:
      tip text for this property suitable for displaying in the explorer/experimenter gui

    • getOutputFile

      public File getOutputFile()
      Get the value of OutputFile.
      Returns:
      Value of OutputFile.

    • setOutputFile

      public void setOutputFile(File newOutputFile)
      Set the value of OutputFile.
      Parameters:
      newOutputFile - Value to assign to OutputFile.

    • numFoldsTipText

      public String numFoldsTipText()
      Returns the tip text for this property
      Returns:
      tip text for this property suitable for displaying in the explorer/experimenter gui

    • getNumFolds

      public int getNumFolds()
      Get the value of NumFolds.
      Returns:
      Value of NumFolds.

    • setNumFolds

      public void setNumFolds(int newNumFolds)
      Set the value of NumFolds.
      Parameters:
      newNumFolds - Value to assign to NumFolds.

    • rawOutputTipText

      public String rawOutputTipText()
      Returns the tip text for this property
      Returns:
      tip text for this property suitable for displaying in the explorer/experimenter gui

    • getRawOutput

      public boolean getRawOutput()
      Get if raw split evaluator output is to be saved
      Returns:
      true if raw split evalutor output is to be saved

    • setRawOutput

      public void setRawOutput(boolean d)
      Set to true if raw split evaluator output is to be saved
      Parameters:
      d - true if output is to be saved

    • splitEvaluatorTipText

      public String splitEvaluatorTipText()
      Returns the tip text for this property
      Returns:
      tip text for this property suitable for displaying in the explorer/experimenter gui

    • getSplitEvaluator

      public SplitEvaluator getSplitEvaluator()
      Get the SplitEvaluator.
      Returns:
      the SplitEvaluator.

    • setSplitEvaluator

      public void setSplitEvaluator(SplitEvaluator newSplitEvaluator)
      Set the SplitEvaluator.
      Parameters:
      newSplitEvaluator - new SplitEvaluator to use.

    • listOptions

      public Enumeration<Option> 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(String[] options) throws Exception
      Parses a given list of options.

      Valid options are: 

       -X <number of folds>
  The number of folds to use for the cross-validation.
  (default 10)
 
       -D
 Save raw split evaluator output.
 
       -O <file/directory name/path>
  The filename where raw output will be stored.
  If a directory name is specified then then individual
  outputs will be gzipped, otherwise all output will be
  zipped to the named file. Use in conjuction with -D. (default splitEvalutorOut.zip)
 
       -W <class name>
  The full class name of a SplitEvaluator.
  eg: weka.experiment.ClassifierSplitEvaluator
 
       Options specific to split evaluator weka.experiment.ClassifierSplitEvaluator:
 
       -W <class name>
  The full class name of the classifier.
  eg: weka.classifiers.bayes.NaiveBayes
 
       -C <index>
  The index of the class for which IR statistics
  are to be output. (default 1)
 
       -I <index>
  The index of an attribute to output in the
  results. This attribute should identify an
  instance in order to know which instances are
  in the test set of a cross validation. if 0
  no output (default 0).
 
       -P
  Add target and prediction columns to the result
  for each fold.
 
       Options specific to classifier weka.classifiers.rules.ZeroR:
 
       -D
  If set, classifier is run in debug mode and
  may output additional info to the console
      All options after -- will be passed to the split evaluator.
      Specified by:
      setOptions in interface OptionHandler
      Parameters:
      options - the list of options as an array of strings
      Throws:
      Exception - if an option is not supported

    • getOptions

      public String[] getOptions()
      Gets the current settings of the result producer.
      Specified by:
      getOptions in interface OptionHandler
      Returns:
      an array of strings suitable for passing to setOptions

    • toString

      public String toString()
      Gets a text descrption of the result producer.
      Overrides:
      toString in class Object
      Returns:
      a text description of the result producer.

    • getRevision

      public String getRevision()
      Returns the revision string.
      Specified by:
      getRevision in interface RevisionHandler
      Returns:
      the revision

    • main

      public static void main(String[] args)
      Quick test of timestamp
      Parameters:
      args - the commandline options