MATLAB File Help: prtDecision
  prtDecision Base class for sll prt decision objects
   This is a base class from which all prt decision objects inherit. It
   cannot be instantiated. prtDecision objects inherit the RUN function
   from prtAction objects. 
  prtDecision objects accept the outputs of classifiers or clusterers
  and return class or cluster labels.  The output of a prtDecision 
  object's run function is always a nObservations x 1 data set where
  the observations are integer valued and specify the hypothesized
  class for each observation
  Decisions can be used in two ways - either as part of an algorithm:
  algo = prtClassKnn + prtDecisionBinaryMinPe;
  Or as the internalDecider object inside a prtClass object:
   myKnn = prtClassKnn;
   myKnn.internalDecider = prtDecisionBinaryMinPe;
   myKnn = myKnn.train(dsTrain);
  In the first case, the resulting object is a prtAlgorithm, which
  changes the behavior of PLOT.  In the second case, the decision is
  incorporated into the classifier, allowing the decision contours to
  be plotted easily.
  Note that the regardless of how one uses a decider, the outputs of
  the RUN function should be identical.
   % Example 1:
  % This example demonstrates use of a prtDecision object to perform
  % class labeling as part of a prtAlgorithm
  dsTrain = prtDataGenUnimodal;
  dsTest = prtDataGenUnimodal;
  algo = prtClassKnn + prtDecisionBinaryMinPe;
  algo = algo.train(dsTrain);
  plot(algo); title('Algorithm implementation');
  outAlgo =;
   % Example 2:
   % This example demonstrtes the use of a prtDecision objet to perform
   % class labeling as prtClass objects internalDecider
   myKnn = prtClassKnn;
   myKnn.internalDecider = prtDecisionBinaryMinPe;
   myKnn = myKnn.train(dsTrain);
   outIntDec =;
   figure; plot(myKnn); title('internalDecider implementation');
Class Details
Superclasses prtAction
Sealed false
Construct on load false
Constructor Summary
prtDecision As an action subclass we must set the properties to reflect 
Property Summary
dataSet The training prtDataSet, only stored if verboseStorage is true.  
dataSetSummary Structure that summarizes prtDataSet. 
isCrossValidateValid True 
isSupervised False 
isTrained Indicates if prtAction object has been trained. 
name Descriptive name of prtAction object. 
nameAbbreviation Shortened name for the prtAction object. 
userData User specified data 
verboseStorage Specifies whether or not to store the training prtDataset. 
Method Summary
  crossValidate Cross validate prtAction using prtDataSet and cross validation keys. 
  get get the object properties 
  kfolds Perform K-folds cross-validation of prtAction 
  optimize Optimize action parameter by exhaustive function maximization. 
  run Run a prtAction object on a prtDataSet object. 
  set set the object properties 
  train Train a prtAction object using training a prtDataSet object.