rfsrc_data: Cached `rfsrc` objects for examples, diagnostics and vignettes.

Description

Data sets storing rfsrc objects corresponding to training data according to the following naming convention:

rfsrc_iris - randomForestSR[C] for the iris data set.
rfsrc_boston - randomForestS[R]C for the Boston housing data set (MASS package).
rfsrc_pbc - randomForest[S]RC for the pbc data set (randomForestSRC package)

Arguments

Format

rfsrc object

Details

Constructing random forests are computationally expensive. We cache rfsrc objects to improve the ggRandomForests examples, diagnostics and vignettes run times. (see cache_rfsrc_datasets to rebuild a complete set of these data sets.)

For each data set listed, we build a rfsrc. Tuning parameters used in each case are documented in the examples. Each data set is built with the cache_rfsrc_datasets with the randomForestSRC version listed in the ggRandomForests DESCRIPTION file.

rfsrc_iris - The famous (Fisher's or Anderson's) iris data set gives the measurements in centimeters of the variables sepal length and width and petal length and width, respectively, for 50 flowers from each of 3 species of iris. Build a classification random forest for predicting the species (setosa, versicolor, and virginica) on 5 variables (columns) and 150 observations (rows).
rfsrc_boston - The Boston housing values in suburbs of Boston from the MASS package. Build a regression random forest for predicting medv (median home values) on 13 covariates and 506 observations.
rfsrc_pbc - The pbc data from the Mayo Clinic trial in primary biliary cirrhosis (PBC) of the liver conducted between 1974 and 1984. A total of 424 PBC patients, referred to Mayo Clinic during that ten-year interval, met eligibility criteria for the randomized placebo controlled trial of the drug D-penicillamine. 312 cases participated in the randomized trial and contain largely complete data. Data from the randomForestSRC package. Build a survival random forest for time-to-event death data with 17 covariates and 312 observations (remaining 106 observations are held out).

References

#--------------------- randomForestSRC ---------------------

Ishwaran H. and Kogalur U.B. (2014). Random Forests for Survival, Regression and Classification (RF-SRC), R package version 1.5.5.

Ishwaran H. and Kogalur U.B. (2007). Random survival forests for R. R News 7(2), 25-31.

Ishwaran H., Kogalur U.B., Blackstone E.H. and Lauer M.S. (2008). Random survival forests. Ann. Appl. Statist. 2(3), 841-860.

#--------------------- Boston data set ---------------------

Belsley, D.A., E. Kuh, and R.E. Welsch. 1980. Regression Diagnostics. Identifying Influential Data and Sources of Collinearity. New York: Wiley.

Harrison, D., and D.L. Rubinfeld. 1978. "Hedonic Prices and the Demand for Clean Air." J. Environ. Economics and Management 5: 81-102. #--------------------- Iris data set ---------------------

Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988) The New S Language. Wadsworth \& Brooks/Cole. (has iris3 as iris.)

Fisher, R. A. (1936) The use of multiple measurements in taxonomic problems. Annals of Eugenics, 7, Part II, 179-188.

Anderson, Edgar (1935). The irises of the Gaspe Peninsula, Bulletin of the American Iris Society, 59, 2-5.

#--------------------- pbc data set ---------------------

Fleming T.R and Harrington D.P., (1991) Counting Processes and Survival Analysis. New York: Wiley.

T Therneau and P Grambsch (2000), Modeling Survival Data: Extending the Cox Model, Springer-Verlag, New York. ISBN: 0-387-98784-3.

Examples

Run this code

if (FALSE) {
#---------------------------------------------------------------------
# iris data - classification random forest
#---------------------------------------------------------------------
# rfsrc grow call
rfsrc_iris <- rfsrc(Species ~., data = iris)

# plot the forest generalization error convergence
gg_dta <- gg_error(rfsrc_iris)
plot(gg_dta)

# Plot the forest predictions
gg_dta <- gg_rfsrc(rfsrc_iris)
plot(gg_dta)

#---------------------------------------------------------------------
# MASS::Boston data - regression random forest
#---------------------------------------------------------------------
# Load the data...
data(Boston, package="MASS")
Boston$chas <- as.logical(Boston$chas)

# rfsrc grow call
rfsrc_boston <- rfsrc(medv~., data=Boston)

# plot the forest generalization error convergence
gg_dta <- gg_error(rfsrc_boston)
plot(gg_dta)

# Plot the forest predictions
gg_dta <- gg_rfsrc(rfsrc_boston)
plot(gg_dta)

#---------------------------------------------------------------------
# randomForestSRC::pbc data - survival random forest
#---------------------------------------------------------------------
# Load the data...
# For simplicity here. We do a bit of data tidying
# before running the stored random forest.
data(pbc, package="randomForestSRC")

# Remove non-randomized cases
dta.train <- pbc[-which(is.na(pbc$treatment)),]

# rfsrc grow call
rfsrc_pbc <- rfsrc(Surv(years, status) ~ ., dta.train, nsplit = 10,
                   na.action="na.impute")

# plot the forest generalization error convergence
gg_dta <- gg_error(rfsrc_pbc)
plot(gg_dta)

# Plot the forest predictions
gg_dta <- gg_rfsrc(rfsrc_pbc)
plot(gg_dta)

}