Learn R Programming

ggRandomForests (version 2.2.1)

plot.gg_error: Plot a gg_error object

Description

A plot of the cumulative OOB error rates of the random forest as a function of number of trees.

Usage

# S3 method for gg_error
plot(x, ...)

Value

ggplot object

Arguments

x

gg_error object created from a rfsrc object

...

extra arguments passed to ggplot functions

Details

The gg_error plot is used to track the convergence of the randomForest. This figure is a reproduction of the error plot from the plot.rfsrc function.

References

Breiman L. (2001). Random forests, Machine Learning, 45:5-32.

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

Ishwaran H. and Kogalur U.B. (2013). Random Forests for Survival, Regression and Classification (RF-SRC), R package version 1.4.

See Also

gg_error rfsrc plot.rfsrc

Examples

Run this code
if (FALSE) {
 ## Examples from RFSRC package...
## ------------------------------------------------------------
## classification example
## ------------------------------------------------------------
## ------------- iris data
## You can build a randomForest
rfsrc_iris <- rfsrc(Species ~ ., data = iris, tree.err = TRUE)

# Get a data.frame containing error rates
gg_dta <- gg_error(rfsrc_iris)

# Plot the gg_error object
plot(gg_dta)

## RandomForest example
rf_iris <- randomForest::randomForest(Species ~ ., data = iris, 
                                      tree.err = TRUE, )
gg_dta <- gg_error(rf_iris)
plot(gg_dta)

gg_dta <- gg_error(rf_iris, training=TRUE)
plot(gg_dta)
## ------------------------------------------------------------
## Regression example
## ------------------------------------------------------------
## ------------- airq data
rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality, 
    na.action = "na.impute", tree.err = TRUE, )

# Get a data.frame containing error rates
gg_dta <- gg_error(rfsrc_airq)

# Plot the gg_error object
plot(gg_dta)


## ------------- Boston data
data(Boston, package = "MASS")
Boston$chas <- as.logical(Boston$chas)
rfsrc_boston <- rfsrc(medv ~ .,
   data = Boston,
   forest = TRUE,
   importance = TRUE,
   tree.err = TRUE,
   save.memory = TRUE)

# Get a data.frame containing error rates
gg_dta<- gg_error(rfsrc_boston)

# Plot the gg_error object
plot(gg_dta)

## ------------- mtcars data
rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars, tree.err = TRUE)
# Get a data.frame containing error rates
gg_dta<- gg_error(rfsrc_mtcars)

# Plot the gg_error object
plot(gg_dta)


## ------------------------------------------------------------
## Survival example
## ------------------------------------------------------------
## ------------- veteran data
## randomized trial of two treatment regimens for lung cancer
data(veteran, package = "randomForestSRC")
rfsrc_veteran <- rfsrc(Surv(time, status) ~ ., data = veteran,
                       tree.err = TRUE)

gg_dta <- gg_error(rfsrc_veteran)
plot(gg_dta)

## ------------- pbc data
# Load a cached randomForestSRC object
# We need to create this dataset
data(pbc, package = "randomForestSRC",) 
# For whatever reason, the age variable is in days... makes no sense to me
for (ind in seq_len(dim(pbc)[2])) {
 if (!is.factor(pbc[, ind])) {
   if (length(unique(pbc[which(!is.na(pbc[, ind])), ind])) <= 2) {
     if (sum(range(pbc[, ind], na.rm = TRUE) == c(0, 1)) == 2) {
       pbc[, ind] <- as.logical(pbc[, ind])
     }
   }
 } else {
   if (length(unique(pbc[which(!is.na(pbc[, ind])), ind])) <= 2) {
     if (sum(sort(unique(pbc[, ind])) == c(0, 1)) == 2) {
       pbc[, ind] <- as.logical(pbc[, ind])
     }
     if (sum(sort(unique(pbc[, ind])) == c(FALSE, TRUE)) == 2) {
       pbc[, ind] <- as.logical(pbc[, ind])
     }
   }
 }
 if (!is.logical(pbc[, ind]) &
     length(unique(pbc[which(!is.na(pbc[, ind])), ind])) <= 5) {
   pbc[, ind] <- factor(pbc[, ind])
 }
}
#Convert age to years
pbc$age <- pbc$age / 364.24

pbc$years <- pbc$days / 364.24
pbc <- pbc[, -which(colnames(pbc) == "days")]
pbc$treatment <- as.numeric(pbc$treatment)
pbc$treatment[which(pbc$treatment == 1)] <- "DPCA"
pbc$treatment[which(pbc$treatment == 2)] <- "placebo"
pbc$treatment <- factor(pbc$treatment)
dta_train <- pbc[-which(is.na(pbc$treatment)), ]
# Create a test set from the remaining patients
pbc_test <- pbc[which(is.na(pbc$treatment)), ]

#========
# build the forest:
rfsrc_pbc <- randomForestSRC::rfsrc(
  Surv(years, status) ~ .,
 dta_train,
 nsplit = 10,
 na.action = "na.impute",
 tree.err = TRUE, 
 forest = TRUE,
 importance = TRUE,
 save.memory = TRUE
)


gg_dta <- gg_error(rfsrc_pbc)
plot(gg_dta)

}

Run the code above in your browser using DataLab