bag {caret}

A General Framework For Bagging

Description

bag provides a framework for bagging classification or regression models. The user can provide their own functions for model building, prediction and aggregation of predictions (see Details below).

Usage

bag(x, ...)

bagControl(
  fit = NULL,
  predict = NULL,
  aggregate = NULL,
  downSample = FALSE,
  oob = TRUE,
  allowParallel = TRUE
)

## Default S3 method:
bag(x, y, B = 10, vars = ncol(x), bagControl = NULL, ...)

## S3 method for class 'bag'
predict(object, newdata = NULL, ...)

## S3 method for class 'bag'
print(x, ...)

## S3 method for class 'bag'
summary(object, ...)

## S3 method for class 'summary.bag'
print(x, digits = max(3, getOption("digits") - 3), ...)

ldaBag

plsBag

nbBag

ctreeBag

svmBag

nnetBag

Arguments

x

a matrix or data frame of predictors

...

arguments to pass to the model function

fit

a function that has arguments x, y and ... and produces a model object #' that can later be used for prediction. Example functions are found in ldaBag, plsBag, #' nbBag, svmBag and nnetBag.

predict

a function that generates predictions for each sub-model. The function should have #' arguments object and x. The output of the function can be any type of object (see the #' example below where posterior probabilities are generated. Example functions are found in ldaBag#' , plsBag, nbBag, svmBag and nnetBag.)

aggregate

a function with arguments x and type. The function that takes the output #' of the predict function and reduces the bagged predictions to a single prediction per sample. #' the type argument can be used to switch between predicting classes or class probabilities for #' classification models. Example functions are found in ldaBag, plsBag, nbBag, #' svmBag and nnetBag.

downSample

logical: for classification, should the data set be randomly sampled so that each #' class has the same number of samples as the smallest class?

oob

logical: should out-of-bag statistics be computed and the predictions retained?

allowParallel

a parallel backend is loaded and available, should the function use it?

y

a vector of outcomes

B

the number of bootstrap samples to train over.

vars

an integer. If this argument is not NULL, a random sample of size vars is taken of the predictors in each bagging iteration. If NULL, all predictors are used.

bagControl

a list of options.

object

an object of class bag.

newdata

a matrix or data frame of samples for prediction. Note that this argument must have a non-null value

digits

minimal number of significant digits.

Format

An object of class list of length 3.

An object of class list of length 3.

An object of class list of length 3.

An object of class list of length 3.

An object of class list of length 3.

An object of class list of length 3.

Details

The function is basically a framework where users can plug in any model in to assess the effect of bagging. Examples functions can be found in ldaBag, plsBag , nbBag, svmBag and nnetBag. Each has elements fit, pred and aggregate.

One note: when vars is not NULL, the sub-setting occurs prior to the fit and #' predict functions are called. In this way, the user probably does not need to account for the #' change in predictors in their functions.

When using bag with train, classification models should use type = "prob" #' inside of the predict function so that predict.train(object, newdata, type = "prob") will #' work.

If a parallel backend is registered, the foreach package is used to train the models in parallel.

Value

bag produces an object of class bag with elements

fits

a list with two sub-objects: the fit object has the actual model fit for that #' bagged samples and the vars object is either NULL or a vector of integers corresponding to which predictors were sampled for that model

control

a mirror of the arguments passed into bagControl

call

the call

B

the number of bagging iterations

dims

the dimensions of the training set

Author(s)

Max Kuhn

Examples

## A simple example of bagging conditional inference regression trees:
data(BloodBrain)

## treebag <- bag(bbbDescr, logBBB, B = 10,
##                bagControl = bagControl(fit = ctreeBag$fit,
##                                        predict = ctreeBag$pred,
##                                        aggregate = ctreeBag$aggregate))




## An example of pooling posterior probabilities to generate class predictions
data(mdrr)

## remove some zero variance predictors and linear dependencies
mdrrDescr <- mdrrDescr[, -nearZeroVar(mdrrDescr)]
mdrrDescr <- mdrrDescr[, -findCorrelation(cor(mdrrDescr), .95)]

## basicLDA <- train(mdrrDescr, mdrrClass, "lda")

## bagLDA2 <- train(mdrrDescr, mdrrClass,
##                  "bag",
##                  B = 10,
##                  bagControl = bagControl(fit = ldaBag$fit,
##                                          predict = ldaBag$pred,
##                                          aggregate = ldaBag$aggregate),
##                  tuneGrid = data.frame(vars = c((1:10)*10 , ncol(mdrrDescr))))