\name{classifierOutput-class}
\docType{class}
\alias{classifierOutput-class}
%\alias{confuMat,classifierOutput-method}
\alias{RObject,classifierOutput-method}
\alias{RObject}
\alias{trainInd,classifierOutput-method}
\alias{trainInd}
\alias{show,classifierOutput-method}
\alias{testScores,classifierOutput-method}
\alias{trainScores,classifierOutput-method}
\alias{predictions,classifierOutput-method}
\alias{predictions}
\alias{predScores,classifierOutput-method}
\alias{predScores}
\alias{testPredictions,classifierOutput-method}
\alias{testPredictions}
\alias{trainPredictions}
\alias{trainPredictions,classifierOutput-method}
\alias{fsHistory,classifierOutput-method}
\alias{testScores}
\alias{trainScores}
\alias{testPredictions}
%\alias{fsHistory}

\title{Class "classifierOutput"}
\description{
This class summarizes the output values from different classifiers.}
\section{Objects from the Class}{
Objects are typically created during the application of a supervised 
machine learning algorithm to data and are the value returned.  It is very
unlikely that any user would create such an object by hand.
}
\section{Slots}{
  \describe{
    \item{\code{testOutcomes}:}{Object of class \code{"factor"} that
      lists the actual outcomes in the records on the test set }
    \item{\code{testPredictions}:}{Object of class \code{"factor"} that
      lists the predictions of outcomes in the test set }
    \item{\code{testScores}:}{Object of class \code{"ANY"} -- this
      element will include matrices or vectors or arrays that include
      information that is typically related to the posterior probability
      of occupancy of the predicted class or of all classes.  The actual
      contents of this slot can be determined by inspecting the converter
      element of the learnerSchema used to select the model. }
    \item{\code{trainOutcomes}:}{Object of class \code{"factor"} that
      lists the actual outcomes in records on the training set }
    \item{\code{trainPredictions}:}{Object of class \code{"factor"} that
      lists the predicted outcomes in the training set }
    \item{\code{trainScores}:}{Object of class \code{"ANY"} see
      the description of \code{testScores} above; the same information
      is returned, but applicable to the training set records.
    }
    \item{\code{trainInd}:}{Object of class \code{"numeric"} with of
      indices of data to be used for training. }
    \item{\code{RObject}:}{Object of class \code{"ANY"} -- when
      the \code{trainInd} parameter of the \code{MLearn} call is
      numeric, this slot holds
      the return value of the underlying R function that carried out
      the predictive modeling.  For example, if \code{rpartI} was used
      as MLearn \code{method}, \code{Robject} holds an instance of the
      \code{rpart} S3 class, and \code{plot} and \code{text} methods
      can be applied to this.  When the \code{trainInd} parameter
      of the \code{MLearn} call is an instance of
      \code{\linkS4class{xvalSpec}}, this slot holds a \code{list} of
      results of cross-validatory iterations.  Each element of this
      list has two elements: \code{test.idx}, giving the numeric
      indices of the test cases for the associated cross-validation
      iteration, and \code{mlans}, which is the \code{\linkS4class{classifierOutput}}
      for the associated iteration.  See the example for an illustration
      of 'digging out' the predicted probabilities associated with each
      cross-validation iteration executed through an xvalSpec specification. }
    \item{\code{embeddedCV}:}{logical value that is TRUE if
      the procedure in use performs its own cross-validation}
    \item{\code{fsHistory}:}{list of features selected
      through cross-validation process}
    \item{\code{learnerSchema}:}{propagation of the learner
      schema object used in the call}
    \item{\code{call}:}{Object of class \code{"call"} -- records the
      call used to generate the classifierOutput RObject }
  }
}

\section{Methods}{
  \describe{
    \item{confuMat}{\code{signature(obj = "classifierOutput")}: Compute
    the confusion matrix for test records. }
    \item{confuMatTrain}{\code{signature(obj = "classifierOutput")}: Compute
    the confusion matrix for training set.  Typically yields optimistically biased
    information on misclassification rate. }
    \item{RObject}{\code{signature(obj = "classifierOutput")}: The R object
     returned by the underlying classifier. This can then be passed on to
     specific methods for those objects, when they exist. }
   \item{trainInd}{\code{signature(obj = "classifierOutput")}: Returns
     the indices of data used for training. } 
   \item{show}{\code{signature(object = "classifierOutput")}: A print method
     that provides a summary of the output of the classifier. }
   \item{predictions}{\code{signature(object = "classifierOutput")}: Print
     the predicted classes for each sample/individual. The predictions
     for the training set are the training outcomes. }
   \item{predictions}{\code{signature(object = "classifierOutput", t
       = "numeric")}: Print the predicted classes for each
     sample/individual that have a \code{testScore} greater or equal
     than \code{t}. The predictions for the training set are the
     training outcomes.  Non-predicted cases and cases that 
     matche multiple classes are returned as \code{NA}s.}
   \item{predScores}{\code{signature(object = "classifierOutput")}:
     Returns the prediction scores for each sample/individual. The
     scores for the training set are set to 1. }
   \item{testScores}{\code{signature(object = "classifierOutput")}: ... }
   \item{testPredictions}{\code{signature(object = "classifierOutput")}: Print
     the predicted classes for each sample/individual in the test set. }
   \item{testPredictions}{\code{signature(object = "classifierOutput", t
       = "numeric")}: Print the predicted classes for each
     sample/individual in the test set that have a \code{testScore}
     greater or equal than \code{t}. Non-predicted cases and cases that
     matche multiple classes are returned as \code{NA}s.}
   \item{trainScores}{\code{signature(object = "classifierOutput")}: ... }
   \item{trainPredictions}{\code{signature(object =
       "classifierOutput")}: Print the predicted classes for each
     sample/individual in the train set. } 
   \item{trainPredictions}{\code{signature(object = "classifierOutput", t
       = "numeric")}: Print the predicted classes for each
     sample/individual in the train set that have a \code{testScore}
     greater or equal than \code{t}. Non-predicted cases and cases that
     matche multiple classes are returned as \code{NA}s.}
   \item{fsHistory}{\code{signature(object = "classifierOutput")}: ... }
 }
}
\author{ V. Carey }
%\seealso{
%	~~objects to See Also as \code{\link{~~fun~~}}, ~~~
%	or \code{\linkS4class{CLASSNAME}} for links to other classes
%}
\examples{
showClass("classifierOutput")
library(golubEsets)
data(Golub_Train) # now cross-validate a neural net
set.seed(1234)
xv5 = xvalSpec("LOG", 5, balKfold.xvspec(5))
m2 = MLearn(ALL.AML~., Golub_Train[1000:1050,], nnetI, xv5, 
   size=5, decay=.01, maxit=1900 )
testScores(RObject(m2)[[1]]$mlans)
alls = lapply(RObject(m2), function(x) testScores(x$mlans))
}
\keyword{classes}