plot.gg_rfsrc: Predicted response plot from a 'gg_rfsrc' object.

In ggRandomForests: Visually Exploring Random Forests

Predicted response plot from a gg_rfsrc object.

Description

Plot the predicted response from a gg_rfsrc object, the rfsrc prediction, using the OOB prediction from the forest.

Usage

## S3 method for class 'gg_rfsrc'
plot(x, ...)

Arguments

x	gg_rfsrc object created from a rfsrc object
...	arguments passed to gg_rfsrc.

Value

ggplot object

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_rfsrc rfsrc

Examples

## Not run: 
## ------------------------------------------------------------
## classification example
## ------------------------------------------------------------
## -------- iris data
# rfsrc_iris <- rfsrc(Species ~ ., data = iris)
data(rfsrc_iris, package="ggRandomForests")
gg_dta<- gg_rfsrc(rfsrc_iris)

plot(gg_dta)

## ------------------------------------------------------------
## Regression example
## ------------------------------------------------------------
## -------- air quality data
rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality, na.action = "na.impute")
gg_dta<- gg_rfsrc(rfsrc_airq)

plot(gg_dta)

## -------- Boston data
data(Boston, package = "MASS")
rfsrc_boston <- randomForestSRC::rfsrc(medv~., Boston)

plot(rfsrc_boston)

## -------- mtcars data
rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars)
gg_dta<- gg_rfsrc(rfsrc_mtcars)

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, ntree = 100)
gg_dta <- gg_rfsrc(rfsrc_veteran)
plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_veteran, conf.int=.95)
plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_veteran, by="trt")
plot(gg_dta)

## -------- pbc data
#' # 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",
 forest = TRUE,
 importance = TRUE,
 save.memory = TRUE
)

gg_dta <- gg_rfsrc(rfsrc_pbc)
plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_pbc, conf.int=.95)
plot(gg_dta)

gg_dta <- gg_rfsrc(rfsrc_pbc, by="treatment")
plot(gg_dta)



## End(Not run)

ggRandomForests documentation built on Sept. 1, 2022, 5:07 p.m.