ggRandomForests (version 1.0.0)

plot.gg_partial_list: Partial variable dependence plot, operates on a gg_partial_list object.

Description

Generate a risk adjusted (partial) variable dependence plot. The function plots the randomForestSRC::rfsrc response variable (y-axis) against the covariate of interest (specified when creating the gg_partial_list object).

Usage

## S3 method for class 'gg_partial_list':
plot(x, points = TRUE, smooth = "loess", ...)

Arguments

x

gg_partial_list object created from a gg_partial forest object

points

plot points (boolean)

smooth

use smooth curve (by type)

...

extra arguments

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

randomForestSRC::plot.variable gg_partial plot.gg_partial gg_variable plot.gg_variable

Examples

## ------------------------------------------------------------
## classification
## ------------------------------------------------------------

## iris "Petal.Width" partial dependence plot
##
# iris_rf <- rfsrc(Species ~., data = iris)
# iris_prtl <- plot.variable(iris_rf, xvar.names = "Petal.Width",
#                            partial=TRUE)
data(iris_prtl, package="ggRandomForests")

ggrf_obj <- gg_partial(iris_prtl)
plot(ggrf_obj)

## ------------------------------------------------------------
## regression
## ------------------------------------------------------------

## airquality "Wind" partial dependence plot
##
# airq_rf <- rfsrc(Ozone ~ ., data = airquality)
# airq_prtl <- plot.variable(airq_rf, xvar.names = "Wind",
#                            partial=TRUE, show.plot=FALSE)
data(airq_prtl, package="ggRandomForests")

ggrf_obj <- gg_partial(airq_prtl)
plot(ggrf_obj)

## ------------------------------------------------------------
## survival examples
## ------------------------------------------------------------
## survival "age" partial variable dependence plot
##
# data(veteran, package = "randomForestSRC")
# veteran_rf <- rfsrc(Surv(time,status)~., veteran, nsplit = 10, ntree = 100)
#
## 30 day partial plot for age
# veteran_prtl <- plot.variable(veteran_rf, surv.type = "surv",
#                               partial = TRUE, time=30,
#                               xvar.names = "age",
#                               show.plots=FALSE)
data(veteran_prtl, package="ggRandomForests")

ggrf_obj <- gg_partial(veteran_prtl)
plot(ggrf_obj)