Use the bootstrap to estimate the prediction error rate (wuth the
.632+ rule) and the
stability of the variable selection procedure implemented in varSelRF.
varSelRFBoot(xdata, Class, c.sd = 1,
mtryFactor = 1, ntree = 5000, ntreeIterat = 2000,
vars.drop.frac = 0.2, bootnumber = 200,
whole.range = TRUE,
recompute.var.imp = FALSE,
usingCluster = TRUE,
TheCluster = NULL, srf = NULL, verbose = TRUE, ...)A data frame or matrix, with subjects/cases in rows and variables in columns. NAs not allowed.
The dependent variable; must be a factor.
The factor that multiplies the sd. to decide on stopping the tierations or choosing the final solution. See reference for details.
The multiplication factor of \(\sqrt{number.of.variables}\) for the number of variables to use for the ntry argument of randomForest.
The number of trees to use for the first forest; same as ntree for randomForest.
The number of trees to use (ntree of randomForest) for all additional forests.
The fraction of variables, from those in the previous forest, to exclude at each iteration.
If TRUE continue dropping variables until a forest with only two variables is built, and choose the best model from the complete series of models. If FALSE, stop the iterations if the current OOB error becomes larger than the initial OOB error (plus c.sd*OOB standard error) or if the current OOB error becoems larger than the previous OOB error (plus c.sd*OOB standard error).
If TRUE recompute variable importances at each new iteration.
The number of bootstrap samples to draw.
If TRUE use a cluster to parallelize the calculations.
The name of the cluster, if one is used.
An object of class varSelRF. If used, the ntree and mtryFactor parameters are taken from this object, not from the arguments to this function. If used, it allows to skip carrying out a first iteration to build the random forest to the complete, original data set.
Give more information about what is being done.
Not used.
An object of class varSelRFBoot, which is a list with components:
The number of bootstrap replicates.
The .632+ estimate of the prediction error.
The leave-one-out estimate of the error rate (used when computing the .632+ estimate).
A random forest built from all the data, but after the variable selection. Thus, beware because the OOB error rate is severely biased down.
The variables selected in the run with all the data.
An object of class varSelRF; the one obtained from
a run of varSelRF on the original, complete, data set. See
varSelRF.
The out-of-bag predictions from the
bootstrap, of type "response".See
predict.randomForest. This is an array, with
dimensions number of cases by number of bootstrap replicates.
The out-of-bag predictions from the bootstrap,
of type "class probability". See
predict.randomForest. This is a 3-way array; the last
dimension is the bootstrap replication; for each bootstrap
replication, the 2D array
has dimensions case by number of classes, and each value is the
probability of belonging to that class.
A vector with the number of variables selected for each bootstrap sample.
The "overlap" between the variables selected from the run in original sample and the variables returned from a bootstrap sample. Overlap between the sets of variables A and B is defined as $$\frac{|variables.in.A \cap variables.in.B|}{\sqrt{|variables.in.A| |variables.in.B|}}$$ or size (cardinality) of intersection between the two sets / sqrt(product of size of each set).
A vector with all the genes selected in the runs on all the bootstrap samples. If the same gene is selected in several bootstrap runs, it appears multiple times in this vector.
Each solutions is a character vector with all
the variables in a particular solution concatenated by a "+". Thus,
all.solutions is a vector, with length equal to
number.of.bootsamples, of the solution from each bootstrap
run.
The original class argument.
A list of length number.of.bootsamples. Each
component of this list is an element of class varSelRF
and stores the results from the runs on each bootstrap sample.
If a cluster is used for the calculations, it will be used for the embarrisingly parallelizable task of building as many random forests as bootstrap samples.
Breiman, L. (2001) Random forests. Machine Learning, 45, 5--32.
Diaz-Uriarte, R. and Alvarez de Andres, S. (2005) Variable selection from random forests: application to gene expression data. Tech. report. http://ligarto.org/rdiaz/Papers/rfVS/randomForestVarSel.html
Efron, B. & Tibshirani, R. J. (1997) Improvements on cross-validation: the .632+ bootstrap method. J. American Statistical Association, 92, 548--560.
Svetnik, V., Liaw, A. , Tong, C & Wang, T. (2004) Application of Breiman's random forest to modeling structure-activity relationships of pharmaceutical molecules. Pp. 334-343 in F. Roli, J. Kittler, and T. Windeatt (eds.). Multiple Classier Systems, Fifth International Workshop, MCS 2004, Proceedings, 9-11 June 2004, Cagliari, Italy. Lecture Notes in Computer Science, vol. 3077. Berlin: Springer.
randomForest,
varSelRF,
summary.varSelRFBoot,
plot.varSelRFBoot,
# NOT RUN {
## This is a small example, but can take some time.
## make a small cluster, for the sake of illustration
forkCL <- makeForkCluster(2)
clusterSetRNGStream(forkCL, iseed = 123)
clusterEvalQ(forkCL, library(varSelRF))
x <- matrix(rnorm(25 * 30), ncol = 30)
x[1:10, 1:2] <- x[1:10, 1:2] + 2
cl <- factor(c(rep("A", 10), rep("B", 15)))
rf.vs1 <- varSelRF(x, cl, ntree = 200, ntreeIterat = 100,
vars.drop.frac = 0.2)
rf.vsb <- varSelRFBoot(x, cl,
bootnumber = 10,
usingCluster = TRUE,
srf = rf.vs1,
TheCluster = forkCL)
rf.vsb
summary(rf.vsb)
plot(rf.vsb)
stopCluster(forkCL)
# }
# NOT RUN {
# }
Run the code above in your browser using DataLab