caretEnsemble: caretEnsemble: Make ensembles of caret models.

Description Usage Arguments Details Value Note Examples

View source: R/caretEnsemble.R

Description

Functions for creating ensembles of caret models: caretList and caretStack

Find a good linear combination of several classification or regression models, using linear regression.

Usage

1
caretEnsemble(all.models, ...)

Arguments

all.models

an object of class caretList

...

additional arguments to pass to the optimization function

Details

Every model in the "library" must be a separate train object. For example, if you wish to combine a random forests with several different values of mtry, you must build a model for each value of mtry. If you use several values of mtry in one train model, (e.g. tuneGrid = expand.grid(.mtry=2:5)), caret will select the best value of mtry before we get a chance to include it in the ensemble. By default, RMSE is used to ensemble regression models, and AUC is used to ensemble Classification models. This function does not currently support multi-class problems

Value

a caretEnsemble object

Note

Currently when missing values are present in the training data, weights are calculated using only observations which are complete across all models in the library.The optimizer ignores missing values and calculates the weights with the observations and predictions available for each model separately. If each of the models has a different pattern of missingness in the predictors, then the resulting ensemble weights may be biased and the function issues a message.

Examples

1
2
3
4
5
6
7
## Not run: 
set.seed(42)
models <- caretList(iris[1:50,1:2], iris[1:50,3], methodList=c("glm", "lm"))
ens <- caretEnsemble(models)
summary(ens)

## End(Not run)

Example output

Loading required package: lattice
Loading required package: ggplot2

Attaching package: 'ggplot2'

The following object is masked from 'package:caretEnsemble':

    autoplot

Warning messages:
1: In trControlCheck(x = trControl, y = target) :
  trControl$savePredictions not 'all' or 'final'.  Setting to 'final' so we can ensemble the models.
2: In trControlCheck(x = trControl, y = target) :
  indexes not defined in trControl.  Attempting to set them ourselves, so each model in the ensemble will have the same resampling indexes.
There were 25 warnings (use warnings() to see them)
The following models were ensembled: glm, lm 
They were weighted: 
1.0047 0.3203 NA
The resulting RMSE is: 0.1708
The fit for each individual model on the RMSE is: 
 method      RMSE    RMSESD
    glm 0.1747355 0.0296676
     lm 0.1747355 0.0296676

caretEnsemble documentation built on May 30, 2017, 6:46 a.m.