ggRandomForests (version 2.2.1)

plot.gg_variable: Plot a gg_variable object,

Description

Plot a gg_variable object,

Usage

# S3 method for gg_variable
plot(
  x,
  xvar,
  time,
  time_labels,
  panel = FALSE,
  oob = TRUE,
  points = TRUE,
  smooth = TRUE,
  ...
)

Value

A single ggplot object, or list of ggplot objects

Arguments

x

gg_variable object created from a rfsrc object

xvar

variable (or list of variables) of interest.

time

For survival, one or more times of interest

time_labels

string labels for times

panel

Should plots be faceted along multiple xvar?

oob

oob estimates (boolean)

points

plot the raw data points (boolean)

smooth

include a smooth curve (boolean)

...

arguments passed to the ggplot2 functions.

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.

Examples

if (FALSE) {
## ------------------------------------------------------------
## classification
## ------------------------------------------------------------
## -------- iris data
## iris
#rfsrc_iris <- rfsrc(Species ~., data = iris)
data(rfsrc_iris, package="ggRandomForests")

gg_dta <- gg_variable(rfsrc_iris)
plot(gg_dta, xvar="Sepal.Width")
plot(gg_dta, xvar="Sepal.Length")

## !! TODO !! this needs to be corrected
plot(gg_dta, xvar=rfsrc_iris$xvar.names,
     panel=TRUE, se=FALSE)

## ------------------------------------------------------------
## regression
## ------------------------------------------------------------
## -------- air quality data
#rfsrc_airq <- rfsrc(Ozone ~ ., data = airquality)
data(rfsrc_airq, package="ggRandomForests")
gg_dta <- gg_variable(rfsrc_airq)

# an ordinal variable
gg_dta[,"Month"] <- factor(gg_dta[,"Month"])

plot(gg_dta, xvar="Wind")
plot(gg_dta, xvar="Temp")
plot(gg_dta, xvar="Solar.R")

plot(gg_dta, xvar=c("Solar.R", "Wind", "Temp", "Day"), panel=TRUE)

plot(gg_dta, xvar="Month", notch=TRUE)

## -------- motor trend cars data
#rfsrc_mtcars <- rfsrc(mpg ~ ., data = mtcars)
data(rfsrc_mtcars, package="ggRandomForests")
gg_dta <- gg_variable(rfsrc_mtcars)

# mtcars$cyl is an ordinal variable
gg_dta$cyl <- factor(gg_dta$cyl)
gg_dta$am <- factor(gg_dta$am)
gg_dta$vs <- factor(gg_dta$vs)
gg_dta$gear <- factor(gg_dta$gear)
gg_dta$carb <- factor(gg_dta$carb)

plot(gg_dta, xvar="cyl")

# Others are continuous
plot(gg_dta, xvar="disp")
plot(gg_dta, xvar="hp")
plot(gg_dta, xvar="wt")

# panel
plot(gg_dta,xvar=c("disp","hp", "drat", "wt", "qsec"),  panel=TRUE)
plot(gg_dta, xvar=c("cyl", "vs", "am", "gear", "carb") ,panel=TRUE)

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

## ------------------------------------------------------------
## survival examples
## ------------------------------------------------------------
## -------- veteran data
## survival
data(veteran, package = "randomForestSRC")
rfsrc_veteran <- rfsrc(Surv(time,status)~., veteran, nsplit = 10,
                       ntree = 100)

# get the 1 year survival time.
gg_dta <- gg_variable(rfsrc_veteran, time=90)

# Generate variable dependance plots for age and diagtime
plot(gg_dta, xvar = "age")
plot(gg_dta, xvar = "diagtime")

# Generate coplots
plot(gg_dta, xvar = c("age", "diagtime"), panel=TRUE)

# If we want to compare survival at different time points, say 30, 90 day
# and 1 year
gg_dta <- gg_variable(rfsrc_veteran, time=c(30, 90, 365))

# Generate variable dependance plots for age and diagtime
plot(gg_dta, xvar = "age")
plot(gg_dta, xvar = "diagtime")

# Generate coplots
plot(gg_dta, xvar =  c("age", "diagtime"), panel=TRUE)

## -------- pbc data
}